Integrated analysis of spatial data from multiple sources: Using evidential reasoning and artificial neural network techniques for geological mapping

Abstract

As the availability of digital spatial data, other than from remote sensing, increases, it becomes increasingly important to develop algorithms to handle both remote sensing and other spatial data. For classification purposes, commonly used remote sensing algorithms such as the maximum-likelihood classifier and the minimum-distance classifier can only be used to deal with spatial data of interval and ratio scales. They are not applicable to spatial data of nominal or ordinal scale as exemplified by data digitized from a categorical map. Bayesian theory, mathematical theory of evidence, and artificial neural networks, on the other hand, are capable of handling data with any measurement scale. In this paper, we introduce an evidential reasoning and a back-propagation feed-forward neural network algorithm and evaluate their applications to classification problems. A multisource data set including Landsat Thematic Mapper, aeromagnetic, radiometric, and gravity data has been used in the classification of four rock types in Melville Peninsula, Northwest Territories, Canada. The highest overall accuracy of 96.0 percent and average accuracy of 92.1 percent were achieved with the neural network algorithm while the evidential reasoning method produced an overall accuracy of 94.7 percent and average accuracy of 89.3 percent. The evidential reasoning method resulted in three highest individual class accuracies out of the four classes.