Application of Convolutional Neural Networks on Digital Terrain Models for Analyzing Spatial Relations in Archaeology

Abstract

Archaeological research is increasingly embedding individual sites in archaeological contexts and aims at reconstructing entire historical landscapes. In doing so, it benefits from technological developments in the field of archaeological prospection over the last 20 years, including LiDAR-based Digital Terrain Models, special visualizations, and automated site detection. The latter can generate comprehensive datasets with manageable effort that are useful for answering large-scale archaeological research questions. This article presents a highly automated workflow, in which a Convolutional Neural Network is used to detect burial mounds in the proximity of remotely located hollow ways. Detected mounds are then analyzed with respect to their distribution and a possible spatial relation to hollow ways. The detection works well, produces a reasonable number of results, and achieved a precision of at least 77%. The distribution of mounds shows a clear maximum in the radius of 2000–2500 m. This supports future research such as visibility or cost path analysis.

Bathymetric LiDAR and Semi‐Automated Feature Extraction Assist Underwater Archaeological Surveys

“…Semi-and fully automated feature extraction has a growing history in archaeological research (Câmara et al 2022;Davis 2019;Fiorucci et al 2020;Lambers and Traviglia 2016). Researchers have successfully developed methods to identify a range of archaeological feature types, including mounds and earthworks (Berganzo-Besga et al 2021;Caspari and Crespo 2019;Cerrillo-Cuenca 2017;Kokalj et al 2023;Meyer-Heß, Pfeffer, and Juergens 2022;Orengo et al 2020;Sărășan et al 2020), charcoal kilns and hearths (Bonhage et al 2021;Davis and Lundin 2021;Trier, Reksten, and Løseth 2021), roadways (Verschoof-van der Vaart and Landauer 2020), agricultural and other subsistence features (Bickler and Jones 2021;Küçükdemirci et al 2022;Trier and Pilø 2012) and craters from wartime artillery (Magnini, Bettineschi, and De Guio 2017), among others.…”

“…2021; Caspari and Crespo 2019; Cerrillo‐Cuenca 2017; Davis, Sanger, and Lipo 2019; Kokalj et al. 2023; Meyer‐Heß, Pfeffer, and Juergens 2022; Orengo et al. 2020; Sărășan et al.…”