AI-ming backwards: Vanishing archaeological landscapes in Mesopotamia and automatic detection of sites on CORONA imagery

2025-07-17

AI Summary

Rapid landscape transformation and extensive archaeological site loss in Mesopotamia over the past five decades—driven by intensive anthropogenic activity—have rendered many sites invisible to conventional detection methods. Method: This study pioneers the integration of declassified 1960s CORONA grayscale satellite imagery with deep learning, developing a customized CNN architecture optimized for degraded historical imagery and jointly leveraging semantic segmentation and object detection. It overcomes the limitation of relying solely on contemporary remote sensing data by enabling retrospective, automated detection of “invisible” archaeological features. Contribution/Results: Evaluated in the Abu Ghraib region, the model achieves >85% IoU and 90% detection accuracy. It successfully identified four previously unrecorded sites, all subsequently verified through field survey. This demonstrates the efficacy and methodological innovation of the historical imagery–AI synergy paradigm for archaeological prospection in regions undergoing severe landscape change.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

By upgrading an existing deep learning model with the knowledge provided by one of the oldest sets of grayscale satellite imagery, known as CORONA, we improved the AI model attitude towards the automatic identification of archaeological sites in an environment which has been completely transformed in the last five decades, including the complete destruction of many of those same sites. The initial Bing based convolutional network model was retrained using CORONA satellite imagery for the district of Abu Ghraib, west of Baghdad, central Mesopotamian floodplain. The results were twofold and surprising. First, the detection precision obtained on the area of interest increased sensibly: in particular, the Intersection over Union (IoU) values, at the image segmentation level, surpassed 85 percent, while the general accuracy in detecting archeological sites reached 90 percent. Second, our retrained model allowed the identification of four new sites of archaeological interest (confirmed through field verification), previously not identified by archaeologists with traditional techniques. This has confirmed the efficacy of using AI techniques and the CORONA imagery from the 1960 to discover archaeological sites currently no longer visible, a concrete breakthrough with significant consequences for the study of landscapes with vanishing archaeological evidence induced by anthropization

Problem

• Detect archaeological sites in transformed Mesopotamian landscapes
• Improve AI model accuracy using CORONA satellite imagery
• Identify previously unknown sites with AI and field verification

Innovation

• Upgraded deep learning model with CORONA imagery
• Retrained Bing convolutional network for archaeology
• Achieved 90% accuracy in site detection