HERITAGE: A Global Multi-Temporal Satellite Dataset for Archaeological Site Monitoring

HERITAGE is a satellite image dataset for monitoring archaeological sites, derived from Planet Labs monthly basemap mosaics at 4.77 m/pixel. It covers 1,982 sites across 16 countries with monthly observations from January 2016 through May 2025 (113 months, 212,776 images). The Afghanistan subset contains 1,943 sites with binary looting labels (898 looted, 1,045 preserved), per-site bounding masks, and month-of-disturbance annotations for 118 sites with confirmed change events. The global subset adds 39 sites across 15 additional countries. Site coordinates are withheld; the processing pipeline and ground-truth labels are released with the imagery. Files: HERITAGE.zip (full dataset, ~11 GB compressed), ground_truth.csv (top-level preview of the Afghanistan labels), README.md (data dictionary and acquisition details), LICENSE (MIT). This is a private deposit during peer review for Nature Scientific Data. Use the secret reviewer link provided in the manuscript to access the files.