Archaeological Sites Detection with a Human-AI Collaboration Workflow

TL;DR

This paper demonstrates how pre-trained deep learning models can assist archaeologists in detecting sites in satellite imagery through a collaborative workflow that combines AI predictions with human expertise.

Contribution

It introduces a human-AI collaboration framework for archaeological site detection, emphasizing the integration of domain knowledge and iterative dataset refinement.

Findings

Best model achieves around 80% detection accuracy

Human expertise is crucial for dataset creation and evaluation

AI predictions can be used to generate heatmaps or GIS-ready vector data

Abstract

This paper illustrates the results obtained by using pre-trained semantic segmentation deep learning models for the detection of archaeological sites within the Mesopotamian floodplains environment. The models were fine-tuned using openly available satellite imagery and vector shapes coming from a large corpus of annotations (i.e., surveyed sites). A randomized test showed that the best model reaches a detection accuracy in the neighborhood of 80%. Integrating domain expertise was crucial to define how to build the dataset and how to evaluate the predictions, since defining if a proposed mask counts as a prediction is very subjective. Furthermore, even an inaccurate prediction can be useful when put into context and interpreted by a trained archaeologist. Coming from these considerations we close the paper with a vision for a Human-AI collaboration workflow. Starting with an annotated dataset that is refined by the human expert we obtain a model whose predictions can either be combined to create a heatmap, to be overlaid on satellite and/or aerial imagery, or alternatively can be vectorized to make further analysis in a GIS software easier and automatic. In turn, the archaeologists can analyze the predictions, organize their onsite surveys, and refine the dataset with new, corrected, annotation