New Caledonia Road Passability and Surface Data for 1,800 km of Arterial Roads

HeiGIT generated this geospatial dataset covering approximately 1,800 km of arterial roads in New Caledonia using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides deep-learning predictions for road surface, width, and a Humanitarian Passability Index (HPI) to supplement existing OpenStreetMap (OSM) attributes. The data specifically targets motorway, trunk, primary, and secondary road classes.

Use Cases

• Logistics planning using the Humanitarian Passability Index (HPI) to identify routes suitable for heavy truck transport
• Infrastructure monitoring by analyzing the Road Surface Change (2020-2024) field to detect national development trends
• Emergency response routing based on Road Width Class to determine if segments support two-lane flow or risk blockage

Strengths

• 89.2% surface prediction accuracy outperforming standard OSM surface tags
• Multi-temporal coverage allowing for 4-year infrastructure change detection
• Standardized 6-point Humanitarian Passability Index for logistical planning

Limitations

• Geographic scope is limited to New Caledonia
• Excludes minor and residential road networks
• AI-derived predictions may have reduced accuracy in areas with dense canopy or cloud cover

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT)

Collection Method

Deep learning models applied to PlanetScope satellite imagery (3m resolution) integrated with OpenStreetMap vector data.

Time Range

2020-2024

Freshness

Contains temporal comparisons between 2020 and 2024 satellite imagery; last updated March 2026.

Geography

New Caledonia