HeiGIT (Heidelberg Institute for Geoinformation Technology)

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.1691 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0696 and 0.0099 (in million kms), corressponding to 41.182% and 5.8528% respectively of the total road length in the dataset region. 0.0896 million km or 52.9652% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0013 million km of information (corressponding to 1.451% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.1237 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0084 and 0.0079 (in million kms), corressponding to 6.7686% and 6.3892% respectively of the total road length in the dataset region. 0.1075 million km or 86.8422% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0006 million km of information (corressponding to 0.586% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 1.4803 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.3769 and 0.2051 (in million kms), corressponding to 25.4635% and 13.8563% respectively of the total road length in the dataset region. 0.8983 million km or 60.6802% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0047 million km of information (corressponding to 0.5263% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0014 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0002 and 0.0001 (in million kms), corressponding to 10.8132% and 3.9969% respectively of the total road length in the dataset region. 0.0012 million km or 85.1899% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 0.0% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.1226 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0086 and 0.0133 (in million kms), corressponding to 7.0293% and 10.8203% respectively of the total road length in the dataset region. 0.1007 million km or 82.1504% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0012 million km of information (corressponding to 1.1915% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0013 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0006 and 0.0001 (in million kms), corressponding to 44.4544% and 11.2305% respectively of the total road length in the dataset region. 0.0006 million km or 44.3151% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 2.1131% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.5261 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0059 and 0.0688 (in million kms), corressponding to 1.113% and 13.0681% respectively of the total road length in the dataset region. 0.4515 million km or 85.8189% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0004 million km of information (corressponding to 0.0791% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.2325 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0993 and 0.0612 (in million kms), corressponding to 42.6968% and 26.3068% respectively of the total road length in the dataset region. 0.0721 million km or 30.9965% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0009 million km of information (corressponding to 1.2582% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.066 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0095 and 0.0425 (in million kms), corressponding to 14.3662% and 64.3445% respectively of the total road length in the dataset region. 0.014 million km or 21.2893% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0004 million km of information (corressponding to 2.6528% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 4.8023 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.5281 and 0.2874 (in million kms), corressponding to 10.9979% and 5.9838% respectively of the total road length in the dataset region. 3.9868 million km or 83.0183% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0218 million km of information (corressponding to 0.5461% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.3263 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0411 and 0.0178 (in million kms), corressponding to 12.5997% and 5.4678% respectively of the total road length in the dataset region. 0.2674 million km or 81.9325% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0043 million km of information (corressponding to 1.6254% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0517 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0099 and 0.002 (in million kms), corressponding to 19.1793% and 3.8679% respectively of the total road length in the dataset region. 0.0398 million km or 76.9528% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0001 million km of information (corressponding to 0.2769% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.1279 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.025 and 0.0415 (in million kms), corressponding to 19.5376% and 32.4556% respectively of the total road length in the dataset region. 0.0614 million km or 48.0068% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0007 million km of information (corressponding to 1.1673% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0012 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0005 and 0.0002 (in million kms), corressponding to 41.6484% and 15.126% respectively of the total road length in the dataset region. 0.0005 million km or 43.2257% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 0.1918% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.652 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0758 and 0.0598 (in million kms), corressponding to 11.6191% and 9.1793% respectively of the total road length in the dataset region. 0.5164 million km or 79.2016% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0048 million km of information (corressponding to 0.9208% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.2839 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0207 and 0.0169 (in million kms), corressponding to 7.3023% and 5.936% respectively of the total road length in the dataset region. 0.2463 million km or 86.7617% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0009 million km of information (corressponding to 0.3533% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.2286 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0078 and 0.1059 (in million kms), corressponding to 3.3918% and 46.3487% respectively of the total road length in the dataset region. 0.1149 million km or 50.2595% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 0.031% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0023 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0005 and 0.0004 (in million kms), corressponding to 22.6332% and 15.5253% respectively of the total road length in the dataset region. 0.0014 million km or 61.8416% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 0.0012% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.2997 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0451 and 0.0687 (in million kms), corressponding to 15.0369% and 22.9079% respectively of the total road length in the dataset region. 0.186 million km or 62.0553% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 0.0229% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.2967 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0184 and 0.1884 (in million kms), corressponding to 6.212% and 63.4962% respectively of the total road length in the dataset region. 0.0899 million km or 30.2918% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0003 million km of information (corressponding to 0.3234% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0007 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0003 and 0.0 (in million kms), corressponding to 42.8935% and 4.5943% respectively of the total road length in the dataset region. 0.0004 million km or 52.5122% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0 million km of information (corressponding to 0.0044% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.1225 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0274 and 0.0489 (in million kms), corressponding to 22.3404% and 39.9742% respectively of the total road length in the dataset region. 0.0461 million km or 37.6854% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0001 million km of information (corressponding to 0.2331% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.2602 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0143 and 0.1565 (in million kms), corressponding to 5.491% and 60.1302% respectively of the total road length in the dataset region. 0.0895 million km or 34.3788% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0001 million km of information (corressponding to 0.0708% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 0.0497 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0117 and 0.0111 (in million kms), corressponding to 23.4856% and 22.3095% respectively of the total road length in the dataset region. 0.0269 million km or 54.2049% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0008 million km of information (corressponding to 3.0011% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 1.3337 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.3707 and 0.1929 (in million kms), corressponding to 27.7976% and 14.461% respectively of the total road length in the dataset region. 0.7701 million km or 57.7413% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0032 million km of information (corressponding to 0.4136% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.