Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Satellite-Based Detection of Looted Archaeological Sites Using Machine Learning

Girmaw Abebe Tadesse, Titien Bartette, Andrew Hassanali, Allen Kim, Jonathan Chemla, Andrew Zolli, Yves Ubelmann, Caleb Robinson, Inbal Becker-Reshef, Juan Lavista Ferres

TL;DR

Alation studies demonstrate that ImageNet pretraining (even in the presence of domain shift) and spatial masking enhance performance, and geospatial foundation model embeddings perform competitively with handcrafted features, suggesting that looting signatures are extremely localized.

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.

Satellite-Based Detection of Looted Archaeological Sites Using Machine Learning

TL;DR

Alation studies demonstrate that ImageNet pretraining (even in the presence of domain shift) and spatial masking enhance performance, and geospatial foundation model embeddings perform competitively with handcrafted features, suggesting that looting signatures are extremely localized.

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.
Paper Structure (22 sections, 2 figures, 7 tables)

This paper contains 22 sections, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset
  4. Methods
  5. Handcrafted features
  6. Feature examples.
  7. Embeddings from foundation models
  8. Models and Temporal Aggregation
  9. Traditional ML models on features:
  10. CNN models on raw RGB patches:
  11. Experimental Setup
  12. Preprocessing.
  13. Data splits and metrics.
  14. Augmentation and training details.
  15. Traditional ML configuration.
  16. ...and 7 more sections

Figures (2)

  • Figure 1: Overview of the archaeological sites in Afghanistan in this work. The sites are composed of $1045$preserved and $898$looted sites.
  • Figure 2: EfficientNet-B1 performance across individual years (2017--2023), pretrained with spatial masking. Error bars show std across folds.