Peru Road Surface and Passability Data for 64,800 km of Arterial Roads

HeiGIT produced this dataset covering 64,800 km of arterial roads in Peru using AI analysis of PlanetScope satellite imagery from 2020 and 2024. It provides high-resolution predictions for road surface, width, and logistical passability to supplement existing OpenStreetMap data.

Use Cases

• Evaluating disaster relief logistics using the Humanitarian Passability Index (HPI) to identify high-risk segments
• Tracking national infrastructure progress by comparing DL Surface Prediction 2020 against DL Surface Prediction 2024
• Planning heavy vehicle transport routes by filtering for Road Width Class 3 segments which support unimpeded flow

Strengths

• 89.2% model accuracy for road surface classification
• Covers 64,800 km of arterial road segments
• Includes multi-temporal surface predictions for change detection

Limitations

• Excludes minor, residential, and unclassified road types
• AI-derived predictions may contain errors compared to ground-truth surveys
• Geographic scope is restricted to Peru

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived deep learning models applied to PlanetScope satellite imagery and integrated with OpenStreetMap data

Time Range

2020-2024

Freshness

Last updated March 2026; contains satellite-derived data from 2020 and 2024.

Geography

Peru