Archaeological Predictive Modeling Using Machine Learning and Statistical Methods for Japan and China

Abstract

Archaeological predictive modeling (APM) is an essential method for quantitatively assessing the probability of archaeological sites present in a region. It is a necessary tool for archaeological research and cultural heritage management. In particular, the predictive modeling process could help us understand the relationship between past human civilizations and the natural environment; moreover, a better understanding of the mechanisms of the human–land relationship can provide new ideas for sustainable development. This study aims to investigate the impact of topographic and hydrological factors on archaeological sites in the Japanese archipelago and Shaanxi Province, China and proposes a hybrid integration approach for APM. This approach employed a conditional attention mechanism (AM) using deep learning and a frequency ratio (FR) model, in addition to a separate FR model and the widely-used machine learning MaxEnt method. The models’ outcomes were cross-checked using the four-fold cross-validation method, and the models’ performances were compared using the area under the receiver operating characteristic curve (AUC) and Kvamme’s Gain. The results showed that in both study areas, the AM_FR model exhibited the most satisfactory performances.

An Overview of GIS-RS Applications for Archaeological and Cultural Heritage under the DBAR-Heritage Mission

“…The resulting models are then computed, analyzed, and displayed within a GIS environment. Over time, archaeological predictive models have undergone continuous refinement, progressing from binary logistic regression [88,[99][100][101][102][103], LAMAP (locally adaptive model of archaeological potential) [104], spatial autocorrelation methods [105,106], and the maximum entropy model [102,107] to the machine learning approach [108,109]. These advancements have significantly enhanced the accuracy of site prediction models, offering invaluable decision support for archaeological research.…”

“…Machine learning, a critical branch of AI, is increasingly employed to identify patterns and extract information from remote sensing and geospatial data. This method proves especially beneficial in analyzing Earth observation data, thanks to its autonomous learning capabilities, pattern recognition, and minimal need for human intervention [108,220,221]. The emergence of deep learning and deep neural network technologies has constituted a major leap forward in remote sensing research, particularly in processing and analyzing large volumes of data.…”