“DeepAndes” AI helps archaeologists in South America discover hidden sites with aerial imagery

Artificial intelligence is revolutionizing archaeological research, particularly in South America where the GeoPACHA web application is helping experts discover and document ancient sites throughout the Andes. By analyzing vast amounts of satellite and aerial imagery, AI models trained on human-labeled archaeological sites can rapidly identify potential remains that would take researchers years to locate manually. This technological partnership between AI and archaeology demonstrates how machine learning can accelerate discovery while still leveraging human expertise to validate findings.

The big picture: The GeoPACHA platform (Geospatial Platform for Andean Culture, History and Archaeology) has transformed from a manual image analysis project to an AI-powered archaeological discovery system capable of processing enormous datasets of the Andean landscape.

• During its initial phase (2020-2021), researchers manually examined 180,000 square kilometers of high-resolution imagery to identify archaeological remains.
• The project now employs an AI foundation model called DeepAndes that has been trained to recognize archaeological sites from satellite imagery.

How it works: DeepAndes functions similarly to large language models but instead specializes in identifying archaeological features within Andean landscapes.

• Steven Wernke, director of the Vanderbilt Institute for Spatial Research and GeoPACHA team member, describes the system as a “latent ‘expert’ of the land forms and land cover of the Andean world.”
• Human-labeled archaeological sites are used to fine-tune the model, enabling it to develop expertise in identifying similar patterns across vast territories.

Why this matters: AI-assisted archaeological research dramatically accelerates the discovery process while helping preserve cultural heritage that might otherwise remain hidden or be destroyed before documentation.

• The technology enables researchers to survey massive regions that would be impossible to examine manually within reasonable timeframes.
• Archaeological sites throughout South America face ongoing threats from development, climate change, and looting, making rapid identification crucial for preservation efforts.

The human element: Despite its power, AI remains a complementary tool rather than a replacement for archaeological expertise.

• Human researchers are still essential for verifying AI-identified sites and providing the contextual understanding necessary for meaningful interpretation.
• The project demonstrates how human-AI collaboration can produce results superior to either working independently.