Malaysia Arterial Road Surface and Passability Data (2020–2024)

Approximately 39,100 km of arterial roads in Malaysia, providing AI-derived surface types and width classifications generated by HeiGIT from 2020 and 2024 PlanetScope satellite imagery. It integrates OpenStreetMap (OSM) attributes with deep-learning predictions to fill data gaps for the 44.7% of arterial roads that lack surface tags in the original OSM records.

Use Cases

• Calculating logistical accessibility for heavy transport using the 'Humanitarian Passability Index' and 'Road Width Class'
• Identifying infrastructure development trends by filtering for 'Road Surface Change' from unpaved to paved
• Enhancing navigation datasets by filling null 'surface' tags with 'DL Surface Prediction' values

Strengths

• Surface model achieved 89.2% accuracy compared to 64.7% for standard OSM tags
• Provides surface data for 17,500 km of roads previously missing tags
• Includes temporal change detection between 2020 and 2024 imagery

Limitations

• AI-derived predictions from satellite imagery may contain classification errors compared to ground-level surveys
• Geographic scope is limited to Malaysia's arterial network only
• Width classes are categorical (1-3) rather than exact meter measurements

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning analysis of PlanetScope satellite imagery (3-5m resolution) integrated with OpenStreetMap vector data.

Time Range

2020-2024

Freshness

Last updated March 2026 with imagery analysis spanning up to 2024.

Geography

Malaysia