Satellite-Based Detection of Looted Archaeological Sites Using Machine Learning

TL;DR

This paper develops a satellite-based machine learning pipeline to detect looted archaeological sites, demonstrating high accuracy with CNNs and comparing traditional features, thereby aiding remote cultural heritage monitoring.

Contribution

It introduces a scalable satellite-based detection method using CNNs and foundation models, outperforming traditional ML on a large dataset of archaeological sites.

Findings

CNN classifiers with ImageNet pretraining achieve F1 score of 0.926

Traditional ML methods reach an F1 score of 0.710

Spatial masking and pretraining significantly improve detection performance

Abstract

Looting at archaeological sites poses a severe risk to cultural heritage, yet monitoring thousands of remote locations remains operationally difficult. We present a scalable and satellite-based pipeline to detect looted archaeological sites, using PlanetScope monthly mosaics (4.7m/pixel) and a curated dataset of 1,943 archaeological sites in Afghanistan (898 looted, 1,045 preserved) with multi-year imagery (2016--2023) and site-footprint masks. We compare (i) end-to-end CNN classifiers trained on raw RGB patches and (ii) traditional machine learning (ML) trained on handcrafted spectral/texture features and embeddings from recent remote-sensing foundation models. Results indicate that ImageNet-pretrained CNNs combined with spatial masking reach an F1 score of 0.926, clearly surpassing the strongest traditional ML setup, which attains an F1 score of 0.710 using SatCLIP-V+RF+Mean, i.e., location and vision embeddings fed into a Random Forest with mean-based temporal aggregation. Ablation studies demonstrate that ImageNet pretraining (even in the presence of domain shift) and spatial masking enhance performance. In contrast, geospatial foundation model embeddings perform competitively with handcrafted features, suggesting that looting signatures are extremely localized. The repository is available at https://github.com/microsoft/looted_site_detection.