Search

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. [ABSTRACT FROM AUTHOR]

We report in this paper the muography of an archaeological site located in the highly populated "Sanità" district in the center of Naples, ten meters below the current street level. Several detectors capable of detecting muons - high energy charged particles produced by cosmic rays in the upper layers of atmosphere - were installed underground at the depth of 18 m, to measure the muon flux over several weeks. By measuring the differential flux with our detectors in a wide angular range, we have produced a radiographic image of the upper layers. Despite the architectural complexity of the site, we have clearly observed the known structures as well as a few unknown ones. One of the observed new structures is compatible with the existence of a hidden, currently inaccessible, burial chamber. [ABSTRACT FROM AUTHOR]

This paper seeks to reconstruct the management of food resources in the early Neolithic site of Cabecicos Negros in southeastern Spain. For this purpose, we have studied 29 potsherds from Cabecicos Negros (Andalusia, Spain). Applying the methods of gas chromatography and mass spectrometry we were able to recompose the daily use of the sherds related to the consumption and storage of food products. Among the results obtained in this work, we were able to show new evidence of the exploitation of dairy products in the south of the Iberian Peninsula, as well as provide information on the exploitation and management of the early domestic animals herds. To improve the archaeological results obtained, isotopic results were compared with a modern reference of 53 fat samples from the adipose tissue of domestic pigs and wild boars. [ABSTRACT FROM AUTHOR]

The recently described site of Kalinga in the Philippines adds to our understanding of Early-Middle Pleistocene hominin behaviour. Yet, disentangling the natural from the anthropogenic modifications that have taken place in such an old archaeological site is challenging. In this paper we use a set of taphonomic tools at hand to rectify the distortion made by natural processes during the formation of the Kalinga site. From the description of the ribs completeness, surface damages and scattering in the excavation, one can reconstruct the butchery, transport and deposition sequence of the rhino carcass and its post-depositional disturbances and diagenetic evolution of the site. We conclude that the rhino and the stone artefacts potentially used to deflesh the carcass were transported by a mudflow from its butchery place over a few meters only and got stuck and mixed with an older faunal assemblage that was transported by a small stream. [ABSTRACT FROM AUTHOR]