Canada: Road Surface Data

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name Haiti **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0525 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0031 million km (5.8369%) - Unpaved roads: 0.0109 million km (20.7147%) About 0.0385 million km (73.4485%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0001 million km (0.3296%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between paved and unpaved roads across the region. Surface information is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name: "France: **Planet** Road Surface". The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 15.7615 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 6.2742 million km (39.8068%) - Unpaved roads: 1.0159 million km (6.4456%) About 9.1728 million km (58.1974%) of roads lack surface information in OSM. To reduce this gap, the Mapillary-derived surface dataset provides an additional 0.6775 million km (7.3862%) of surface information. Intended Use This dataset supports transportation planning, infrastructure assessment, climate emissions analysis, and GIS applications. AI Features - pred_class: Model-predicted surface class ("paved" or "unpaved") - pred_label: Binary label (0 = paved, 1 = unpaved) - osm_surface_class: Surface classification derived from OSM tags - combined_surface_osm_priority: Combined classification prioritizing OSM - combined_surface_DL_priority: Combined classification prioritizing DL prediction - n_of_predictions_used: Number of predictions used for estimation - predicted_length: DL-estimated length (meters) - DL_mean_timestamp: Mean timestamp of predictions OSM Attributes - name - name:en - name:* (local language) - highway - surface - smoothness - width - lanes - oneway - bridge - layer - source Urban Classification Attributes - continent - country_iso_a2 - urban (0 = rural, 1 = urban) - urban_area - osm_id - osm_type Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name Greenland **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0025 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0001 million km (5.2146%) - Unpaved roads: 0.0009 million km (38.0451%) About 0.0014 million km (56.7402%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (0.1402%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between paved and unpaved roads across the region. Surface information is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name: "United States of America: **Planet** Road Surface". The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 111.7039 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 36.2779 million km (32.4768%) - Unpaved roads: 13.31 million km (11.9154%) About 72.6432 million km (65.0319%) of roads lack surface information in OSM. To reduce this gap, the Mapillary-derived surface dataset provides an additional 5.0864 million km (7.0019%) of surface information. Intended Use This dataset supports transportation planning, infrastructure assessment, climate emissions analysis, and GIS applications. AI Features - pred_class: Model-predicted surface class ("paved" or "unpaved") - pred_label: Binary label (0 = paved, 1 = unpaved) - osm_surface_class: Surface classification derived from OSM tags - combined_surface_osm_priority: Combined classification prioritizing OSM - combined_surface_DL_priority: Combined classification prioritizing DL prediction - n_of_predictions_used: Number of predictions used for estimation - predicted_length: DL-estimated length (meters) - DL_mean_timestamp: Mean timestamp of predictions OSM Attributes - name - name:en - name:* (local language) - highway - surface - smoothness - width - lanes - oneway - bridge - layer - source Urban Classification Attributes - continent - country_iso_a2 - urban (0 = rural, 1 = urban) - urban_area - osm_id - osm_type Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name Suriname **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0182 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0027 million km (14.8517%) - Unpaved roads: 0.0035 million km (19.1617%) About 0.012 million km (65.9867%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (0.0047%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between paved and unpaved roads across the region. Surface information is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name: "Germany: **Planet** Road Surface". The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 21.4159 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 11.9981 million km (56.0243%) - Unpaved roads: 3.8254 million km (17.8622%) About 6.166 million km (28.7914%) of roads lack surface information in OSM. To reduce this gap, the Mapillary-derived surface dataset provides an additional 1.3618 million km (22.0859%) of surface information. Intended Use This dataset supports transportation planning, infrastructure assessment, climate emissions analysis, and GIS applications. AI Features - pred_class: Model-predicted surface class ("paved" or "unpaved") - pred_label: Binary label (0 = paved, 1 = unpaved) - osm_surface_class: Surface classification derived from OSM tags - combined_surface_osm_priority: Combined classification prioritizing OSM - combined_surface_DL_priority: Combined classification prioritizing DL prediction - n_of_predictions_used: Number of predictions used for estimation - predicted_length: DL-estimated length (meters) - DL_mean_timestamp: Mean timestamp of predictions OSM Attributes - name - name:en - name:* (local language) - highway - surface - smoothness - width - lanes - oneway - bridge - layer - source Urban Classification Attributes - continent - country_iso_a2 - urban (0 = rural, 1 = urban) - urban_area - osm_id - osm_type Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org