A human–AI collaboration workflow for archaeological sites detection
Scientific Reports volume 13, Article number: 8699 (2023 ) Cite this article
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, annotations.
This paper documents the outcomes of a collaboration between data scientists and archaeologists with the goal of creating an artificial intelligence (AI) system capable of assisting in the task of detecting potential archaeological sites from aerial or, in our case, satellite imagery. Using semantic segmentation models allowed us to draw precise outlines and human-in-the-loop evaluation showed that detection accuracy is in the neighborhood of 80%.
