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 0.2216 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 0.0069 and 0.0435 (in million kms), corressponding to 3.1158% and 19.613% respectively of the total road length in the dataset region. 0.1712 million km or 77.2712% 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 0.1706% 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 0.0027 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 0.001 and 0.0001 (in million kms), corressponding to 36.1234% and 4.9146% respectively of the total road length in the dataset region. 0.0016 million km or 58.962% 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 1.0074% 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 0.0012 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0003 and 0.0001 (in million kms), corressponding to 22.438% and 8.0695% respectively of the total road length in the dataset region. 0.0008 million km or 69.4925% 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 0.0092% 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 0.3754 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 0.0831 and 0.1096 (in million kms), corressponding to 22.1336% and 29.1861% respectively of the total road length in the dataset region. 0.1828 million km or 48.6803% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0004 million km of information (corressponding to 0.2298% 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 0.0001 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 35.7427% and 8.463% respectively of the total road length in the dataset region. 0.0 million km or 55.7943% 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 0.4493% 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 0.0008 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 0.0002 (in million kms), corressponding to 28.0152% and 20.951% respectively of the total road length in the dataset region. 0.0004 million km or 51.0338% 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 12.5671% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 1.0504 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 0.2143 and 0.3681 (in million kms), corressponding to 20.4009% and 35.046% respectively of the total road length in the dataset region. 0.468 million km or 44.5531% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0039 million km of information (corressponding to 0.8381% 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 0.0315 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 0.0061 and 0.0038 (in million kms), corressponding to 19.2236% and 11.9438% respectively of the total road length in the dataset region. 0.0217 million km or 68.8326% 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 0.032% 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 0.1506 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 0.0515 and 0.0058 (in million kms), corressponding to 34.1772% and 3.8397% respectively of the total road length in the dataset region. 0.0934 million km or 61.9832% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0021 million km of information (corressponding to 2.2783% 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 0.3786 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 0.1698 and 0.0411 (in million kms), corressponding to 44.8525% and 10.8654% respectively of the total road length in the dataset region. 0.1677 million km or 44.2821% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0067 million km of information (corressponding to 4.0082% 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 0.0025 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 0.0002 (in million kms), corressponding to 11.6003% and 7.7376% respectively of the total road length in the dataset region. 0.002 million km or 80.6621% 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 0.2084% 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 0.1256 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 0.007 and 0.0353 (in million kms), corressponding to 5.6084% and 28.0629% respectively of the total road length in the dataset region. 0.0833 million km or 66.3287% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0001 million km of information (corressponding to 0.1191% of total missing information on road surface) It is intended for use in transportation planning, infrastructure analysis, climate emissions and geographic information system (GIS) applications. This dataset provides comprehensive information on road and urban area features, including location, surface quality, and classification metadata. This dataset includes attributes from OpenStreetMap (OSM) data, AI predictions for road surface, and urban classifications. AI features: pred_class: Model-predicted class for the road surface, with values "paved" or "unpaved." pred_label: Binary label associated with pred_class (0 = paved, 1 = unpaved). osm_surface_class: Classification of the surface type from OSM, categorized as "paved" or "unpaved." combined_surface_osm_priority: Surface classification combining pred_label and surface(OSM) while prioritizing the OSM surface tag, classified as "paved" or "unpaved." combined_surface_DL_priority: Surface classification combining pred_label and surface(OSM) while prioritizing DL prediction pred_label, classified as "paved" or "unpaved." n_of_predictions_used: Number of predictions used for the feature length estimation. predicted_length: Predicted length based on the DL model’s estimations, in meters. DL_mean_timestamp: Mean timestamp of the predictions used, for comparison. OSM features may have these attributes(Learn what tags mean here): name: Name of the feature, if available in OSM. name:en: Name of the feature in English, if available in OSM. name:* (in local language): Name of the feature in the local official language, where available. highway: Road classification based on OSM tags (e.g., residential, motorway, footway). surface: Description of the surface material of the road (e.g., asphalt, gravel, dirt). smoothness: Assessment of surface smoothness (e.g., excellent, good, intermediate, bad). width: Width of the road, where available. lanes: Number of lanes on the road. oneway: Indicates if the road is one-way (yes or no). bridge: Specifies if the feature is a bridge (yes or no). layer: Indicates the layer of the feature in cases where multiple features are stacked (e.g., bridges, tunnels). source: Source of the data, indicating the origin or authority of specific attributes. Urban classification features may have these attributes: continent: The continent where the data point is located (e.g., Europe, Asia). country_iso_a2: The ISO Alpha-2 code representing the country (e.g., "US" for the United States). urban: Binary indicator for urban areas based on the GHSU Urban Layer 2019. (0 = rural, 1 = urban) urban_area: Name of the urban area or city where the data point is located. osm_id: Unique identifier assigned by OpenStreetMap (OSM) to each feature. osm_type: Type of OSM element (e.g., node, way, relation). The data originates from OpenStreetMap (OSM) and is augmented with model predictions using images downloaded from Mapillary in combination with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS2020 urban layer. This dataset is one of many HeiGIT exports on HDX. See the HeiGIT website for more information. We are looking forward to hearing about your use-case! Feel free to reach out to us and tell us about your research at communications@heigit.org – we would be happy to amplify your work.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM) data, distinguishing between **paved** and **unpaved** surfaces across the region. This information is based on road surface prediction derived from hybrid deep learning approach. For more information on Methods, refer to the [paper](http://arxiv.org/abs/2410.19874) Roughly 1.2175 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 0.1437 and 0.0911 (in million kms), corressponding to 11.805% and 7.4802% respectively of the total road length in the dataset region. 0.9827 million km or 80.7148% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0113 million km of information (corressponding to 1.1482% 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 0.1795 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 0.0186 and 0.1288 (in million kms), corressponding to 10.3493% and 71.7843% respectively of the total road length in the dataset region. 0.0321 million km or 17.8665% 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 0.078% 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 0.0812 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 0.0201 and 0.0049 (in million kms), corressponding to 24.8049% and 6.0959% respectively of the total road length in the dataset region. 0.0561 million km or 69.0992% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0002 million km of information (corressponding to 0.3268% 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 0.2016 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 0.0197 and 0.1094 (in million kms), corressponding to 9.7506% and 54.2725% respectively of the total road length in the dataset region. 0.0725 million km or 35.9769% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0001 million km of information (corressponding to 0.0915% 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 0.2481 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 0.0952 and 0.0329 (in million kms), corressponding to 38.3796% and 13.2798% respectively of the total road length in the dataset region. 0.1199 million km or 48.3406% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0057 million km of information (corressponding to 4.7806% 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 0.4242 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 0.1112 and 0.1025 (in million kms), corressponding to 26.2097% and 24.1636% respectively of the total road length in the dataset region. 0.2105 million km or 49.6267% of road surface information is missing in OSM. In order to fill this gap, Mapillary derived road surface dataset provides an additional 0.0004 million km of information (corressponding to 0.1878% 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 16.9583% and 8.6397% respectively of the total road length in the dataset region. 0.0004 million km or 74.402% 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 0.8552% 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 0.0942 million km of roads are mapped in OSM in this region. Based on AI-mapped estimates the share of paved and unpaved roads is approximately 0.0084 and 0.0338 (in million kms), corressponding to 8.9226% and 35.895% respectively of the total road length in the dataset region. 0.052 million km or 55.1824% 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 0.5702% 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 0.01 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 0.0014 and 0.0014 (in million kms), corressponding to 13.9118% and 14.1514% respectively of the total road length in the dataset region. 0.0072 million km or 71.9368% 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 0.6837% 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.