期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2002
卷号：XXXIV Part 4
出版社：Copernicus Publications
摘要：Weights of evidence model is used to predict occurrence of an event with known evidences in a study area where training data are available to estimate the relative importance of each evidence by statistical methods. It provides a quantitative method for integrating multiple sources of evidences. It avoids subjective choice of evidences and subjective estimation of weights for evidences with comparing with other methods, such as Fuzzy logic method. This paper discusses our implementation of Weights of Evidence model as a data integration method in a GIS environment, and demonstrates working of the model using an application in the prediction of Sn-W-U mineral occurrence in the South Mountain Batholith in Nova Scotia, Canada. After introduction of the principal of weights of evidence model, the case study case is described, including data collection, data processing, and data integration with use of weights of evidence model. Finally, a Sn-W-U potential map with posterior probability values in the study area is generated and shown in this paper. Based on analysis of weights of five evidential maps and the final prediction result, it is concluded that the prediction result is successful and the model is useful in the study
关键词：Weights of evidence model; binary pattern; conditional probability; Geographical Information System; Mineral ; resources assessment; Sn-W-U mineral occurrence
