Maldives Arterial Road Surface and Passability with 2020-2024 Change Data

HeiGIT produced this dataset of AI-derived road surface, width, and passability metrics for arterial roads in the Maldives using PlanetScope satellite imagery from 2020 and 2024. It covers approximately 100 km of road segments classified in OpenStreetMap as motorway, trunk, primary, and secondary routes. The data provides a high-accuracy alternative to existing crowdsourced tags, specifically targeting logistical accessibility.

Use Cases

• Evaluating logistical accessibility for heavy transport using 'Road Width Class' and 'Humanitarian Passability Index'
• Identifying infrastructure development trends via the 'Road Surface Change' indicator
• Enhancing navigation datasets by filling missing 'surface' tags with 'DL Surface Prediction 2024'

Strengths

• 89.2% surface classification accuracy
• Multi-temporal coverage for change detection
• Standardized 6-point Humanitarian Passability Index

Limitations

• Small total road length of approximately 100 km
• Restricted to high-capacity road classes only
• AI-derived predictions may contain errors compared to physical ground truth

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

Deep learning analysis of PlanetScope satellite imagery combined with OpenStreetMap road geometries

Time Range

2020-2024

Freshness

Last updated March 2026; utilizes satellite imagery from 2020 and 2024.

Geography

Maldives