The classical city of Butrint in southern Albania embodies over three millennia of settlement history. A Roman colony wasestablished sometime after 31BC, whichled to the expansion ofthe city southwards onto a low-lying floodplain where settlement continued wellinto the late antique period. In this paper we describe the results of a detailed magnetometry survey undertaken to investigate Roman settlement upon the floodplain.The study included the use of multilayer perceptron neuralnetworks to further process the magnetic data and derive estimates of feature burial depths, allowing a three-dimensional reconstruction of buried subsurface remains to be made. The neural network approach potentially offers several advantages in terms of efficiency and flexibility over more conventional data inversion techniques.The paper demonstrates how this can lead to an enhanced interpretation of magnetic survey data, which when combined with other geoarchaeological data can provide a clearer picture of settlement evolution within the context of landscape change.The value of this processing technique is also evident within the context of cultural resource management strategies, which potentially restrict more intrusive methods of investigation.
The use of magnetic surveys for archaeological prospecting is a well-established and versatile technique, and a wide range of data processing routines are often applied to further enhance acquired data or derive source parameters. Of particular interest in this respect is the application of artificial neural networks (ANNs) to predict source parameters such as the burial depths of detected features of interest. Within this study, ANNs based upon a multilayer perceptron architecture are used to perform the nonlinear mapping between buried wall features detected within the magnetic data and their corresponding burial depth for surveys in the ancient city of Butrint in southern Albania, achieving a greater level of information from the survey data.Suitable network training examples and test data were generated using forward models based upon ground-truth observations. The training procedure adopts a supervised learning routine that is optimized using a conjugate gradient method, while the learning algorithm also prunes network elements to prevent overregularization by reducing model complexity. Data processing was further enhanced by introducing rotational invariance using Zernike moments and by utilizing the combined output of a number, or committee, of networks. When applied to a section of survey data from Butrint, the ANN routine successfully predicted the burial depth of a number of detected wall features, with an rms error on the order of 0.20 m, and provided a coherent map of the buried building foundations. The neural network approach offered advantages in terms of efficiency and flexibility over more conventional data-inversion techniques within the context of the study, giving fast solutions for large, complex data sets while having high noise tolerance
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.