Roads of Ghana

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 Ghana **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.2043 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0251 million km (12.2772%) - Unpaved roads: 0.035 million km (17.1205%) About 0.1443 million km (70.6023%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0012 million km (0.83%) 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

Railway lines and stations tagged `railway=*`: rail lines, tram tracks, and stations. Useful for transport accessibility analysis and basemap context. Coverage reflects where volunteer mappers have been active. Urban areas are usually well represented, remote areas may be sparse. Cross-check critical decisions with local field knowledge. - Source: OpenStreetMap, a free, collaborative world map - Tags: railway - Part of the country exports on HDX by HOT

Airports and aviation infrastructure: airports, heliports, helipads, runways, terminals, and emergency landing sites tagged via `aeroway`, `building`, or `emergency`. Useful for logistics, evacuation routing, and aerial-response planning. Coverage reflects where volunteer mappers have been active. Urban areas are usually well represented, remote areas may be sparse. Cross-check critical decisions with local field knowledge. - Source: OpenStreetMap, a free, collaborative world map - Tags: aeroway, building, emergency - Part of the country exports on HDX by HOT

Sea ports, harbours and ferry terminals. Useful for maritime logistics, supply-chain analysis, and coastal access planning. Coverage reflects where volunteer mappers have been active. Urban areas are usually well represented, remote areas may be sparse. Cross-check critical decisions with local field knowledge. - Source: OpenStreetMap, a free, collaborative world map - Tags: industrial=port, harbour, port, amenity=ferry_terminal, building=ferry_terminal - Part of the country exports on HDX by HOT

Ghana Major Cities Accessibility Map represents an estimated cumulative travel time/cost (raster grid) accessibility map, for Ghana's major cities . The map is an output of the sub-Saharan African Corridor pilot project for Mobile Warehouse Location . Modeled cities are: Accra (5,390,455); Kumasi (2,477,604); Cape Coast (1,256,805); Sékondi/Takoradi (726,905); Tamale (562,919) - https://www.populationdata.net/pays/ghana/. The calculation of cost/time distance surfaces is based on some assumptions: A. Road travel time/cost is computed for large trucks, it is assumed accessibility for large cargo freight vehicles, tertiary and local traffic roads are not included; B. Lake and river navigation are treated as a surface (polygons) not taking into consideration navigation infrastructure (points). Travel time surface production steps are: rasterization of transportation network and surfaces and definition of cell travel time; creation of time/cost; computation of a cumulative cost/time accessibility layer to cities . **Data publication:** 2020-08-04 **Contact points:** Metadata Contact: [FAO-Data](mailto:fao-data@fao.org) Resource Contact: [Nelson Ribeiro](mailto:Nelson.RosasRibeiroFilho@fao.org) **Data lineage:** lineage statement Produced using OpenStreetMap data for road, railways and places; GAUL country border; FAO Inland Waters in Africa; FAO Major Rivers in Africa; FAO Ports; **Resource constraints:** This work is made available under the Creative Commons Attribution 4.0 International license (CC-BY 4.0). **Online resources:**

Accessibility: Travel Time-Cost to Major Maritime Ports (Ghana - ~1km) is a travel time/cost surface (raster grid), produced for Ghana's Takoradi and Tema Ports. The map was produced under the scope of the sub-Saharan African Corridor, mobile storage (movable warehouse) location pilot project. The calculation of cost/time distance surfaces is based on some assumptions: A. Road travel time/cost is computed for large trucks only, it is assumed that the accessibility is related to large cargo freight vehicles, tertiary and local traffic roads are not included; B. Lake and river navigation are treated as a surface (polygons) not taking into consideration navigation infrastructure (points); C. Major river navigation is included in Ghana using Horton Strahler number to theoretically define navigable river segments (River Volta). The steps to produce travel time surfaces are: rasterization of transportation network vector layers, grid aggregation (cell statistics) into a single time/cost layer, and computation of a cumulative time/cost layer from start point or points. **Data publication:** 2020-08-04 **Contact points:** Metadata Contact: [FAO-Data](mailto:fao-data@fao.org) Resource Contact: [Nelson Ribeiro](mailto:Nelson.RosasRibeiroFilho@fao.org) **Data lineage:** lineage statement Produced using OpenStreetMap data for road, railways; GAUL country border; FAO Inland Waters in Africa; FAO Major Rivers in Africa; FAO Ports; **Resource constraints:** This work is made available under the Creative Commons Attribution 4.0 International license (CC-BY 4.0). **Online resources:**