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 0.0182 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 0.0027 and 0.0035 (in million kms), corressponding to 14.8517% and 19.1617% respectively of the total road length in the dataset region. 0.012 million km or 65.9867% 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 0.0047% 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 0.1947 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 0.0052 and 0.009 (in million kms), corressponding to 2.6901% and 4.614% respectively of the total road length in the dataset region. 0.1805 million km or 92.6958% 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 0.0009% 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 0.0082 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 0.0016 and 0.0021 (in million kms), corressponding to 19.2541% and 26.1252% respectively of the total road length in the dataset region. 0.0045 million km or 54.6206% 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 1.3384% 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 0.0 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 0.0 and 0.0 (in million kms), corressponding to nan% and nan% respectively of the total road length in the dataset region. 0.0 million km or nan% 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 nan% 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 0.033 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 0.0023 and 0.0093 (in million kms), corressponding to 6.8539% and 28.3574% respectively of the total road length in the dataset region. 0.0214 million km or 64.7888% 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 0.0199% 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 0.0383 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 0.019 and 0.0016 (in million kms), corressponding to 49.6203% and 4.0805% respectively of the total road length in the dataset region. 0.0177 million km or 46.2992% 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 3.6516% 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 0.6464 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 0.1355 and 0.015 (in million kms), corressponding to 20.9638% and 2.315% respectively of the total road length in the dataset region. 0.4959 million km or 76.7212% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0026 million km of information (corressponding to 0.5269% 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 0.2076 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 0.0592 and 0.009 (in million kms), corressponding to 28.5262% and 4.3441% respectively of the total road length in the dataset region. 0.1393 million km or 67.1297% 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 0.6061% 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 0.1236 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 0.0017 and 0.0858 (in million kms), corressponding to 1.395% and 69.4411% respectively of the total road length in the dataset region. 0.036 million km or 29.1639% 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 0.0399% 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 0.0005 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 0.0001 and 0.0002 (in million kms), corressponding to 24.1218% and 39.5312% respectively of the total road length in the dataset region. 0.0002 million km or 36.347% 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 0.0016 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 0.0001 (in million kms), corressponding to 33.3379% and 4.7594% respectively of the total road length in the dataset region. 0.001 million km or 61.9027% 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 0.3883% 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 0.3757 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 0.0812 and 0.0347 (in million kms), corressponding to 21.6018% and 9.2479% respectively of the total road length in the dataset region. 0.2598 million km or 69.1503% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.001 million km of information (corressponding to 0.3722% 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 0.0809 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 0.0023 and 0.0402 (in million kms), corressponding to 2.8493% and 49.7398% respectively of the total road length in the dataset region. 0.0383 million km or 47.4108% 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 0.0414% 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 0.0009 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 36.7846% and 5.7242% respectively of the total road length in the dataset region. 0.0005 million km or 57.4912% 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 0.1198 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 0.0159 and 0.0279 (in million kms), corressponding to 13.2564% and 23.3326% respectively of the total road length in the dataset region. 0.0759 million km or 63.411% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.001 million km of information (corressponding to 1.3092% 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 0.5122 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 0.11 and 0.0709 (in million kms), corressponding to 21.4685% and 13.8363% respectively of the total road length in the dataset region. 0.3314 million km or 64.6952% 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 0.3629% 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 0.1685 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 0.0425 and 0.0231 (in million kms), corressponding to 25.2141% and 13.6839% respectively of the total road length in the dataset region. 0.103 million km or 61.102% 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 0.6305% 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 0.0004 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 0.0 (in million kms), corressponding to 52.4849% and 3.1422% respectively of the total road length in the dataset region. 0.0002 million km or 44.3729% 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 4.0521% 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 0.0051 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 0.0022 and 0.0004 (in million kms), corressponding to 43.7051% and 6.9187% respectively of the total road length in the dataset region. 0.0025 million km or 49.3763% 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 1.6916% 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 0.0515 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 0.0152 and 0.0207 (in million kms), corressponding to 29.5165% and 40.2862% respectively of the total road length in the dataset region. 0.0155 million km or 30.1973% 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 0.0964% 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 0.0 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 0.0 and 0.0 (in million kms), corressponding to nan% and nan% respectively of the total road length in the dataset region. 0.0 million km or nan% 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 nan% 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 0.0005 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 0.0001 and 0.0 (in million kms), corressponding to 20.18% and 4.092% respectively of the total road length in the dataset region. 0.0003 million km or 75.728% 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 0.0165 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 0.0049 and 0.0043 (in million kms), corressponding to 29.7678% and 25.8374% respectively of the total road length in the dataset region. 0.0073 million km or 44.3947% 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 0.0075% 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 0.477 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 0.0363 and 0.079 (in million kms), corressponding to 7.6172% and 16.5703% respectively of the total road length in the dataset region. 0.3616 million km or 75.8125% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0018 million km of information (corressponding to 0.5095% 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 0.0906 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 0.0057 and 0.0348 (in million kms), corressponding to 6.3081% and 38.4045% respectively of the total road length in the dataset region. 0.0501 million km or 55.2875% 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 0.5286% 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.