Application of pattern recognition in detection of buried archaeological sites based on analysing environmental variables, Khorramabad Plain, West Iran

Abstract Archaeologists continue to search for techniques that enable them to analyze archaeological data efficiently with artificial intelligence approaches increasingly employed to create new knowledge from archaeological data. The purpose of this paper is to investigate the application of Pattern Recognition methods in detection of buried archaeological sites of the semi-arid Khorramabad Plain located in west Iran. This environment has provided suitable conditions for human habitation for over 40,000 years. However, environmental changes in the late Pleistocene and Holocene have caused erosion and sedimentation resulting in burial of some archaeological sites making archaeological landscape reconstructions more challenging. In this paper, the environmental variables that have influenced formation of archaeological sites of the Khorramabad Plain are identified through the application of Arc GIS. These variables are utilized to create an accurate predictive model based on the application of One-Class classification Pattern Recognition techniques. These techniques can be built using data from one class only, when the data from other classes are difficult to obtain, and are highly suitable in this context. The experimental results of this paper confirm one-class classifiers, including Auto-encoder Neural Network, k-means, principal component analysis data descriptor, minimum spanning tree data descriptor, k-nearest neighbour and Gaussian distribution as promising applications in creating an effective model for detecting buried archaeological sites. Among the investigated classifiers, minimum spanning tree data descriptor achieved the best performance on the Khorramabad Plain data set.