Multiscale anthropogenic feature detection in the Argentinian Andes: satellite machine learning, UAV, and pedestrian survey

Abstract

The Cusi Cusi micro region in Argentina’s Andes presents a unique challenge for cultural heritageresearch. This rugged area lies within the Puna of Jujuy at elevations from 3800 to 4200 metres abovesea level. Archaeological, historical, and features indicate long term human presence, includinglivestock enclosures, agricultural terraces, and settlement structures. The region is situated within the‘Lithium Triangle’ and faces challenges in resource ownership, Indigenous rights, and landscapechange, highlighting the importance of documenting cultural and environmental heritage. We presentan integration of satellite and unpiloted aerial vehicle (UAV) imagery with pedestrian survey datasets,machine learning (ML), and physical ground truthing to explore anthropogenic activities in thelandscape. Satellite-basedML detects features while UAV data improves resolution and assessmentof present activities. Targeted pedestrian survey validates results and provides potential dating. Thiscombined approach identifies loci of activities and offers a framework for investigating other ruggedregions.