Omnibus weights of evidence method implemented in GeoDAS GIS for information extraction and integration for prediction

Weights of evidence (WoFE) is an artificial intelligent method for integration of information from diverse sources for predictive purpose in supporting decision-making. Weights of evidence method has been commonly used to predict point events by integrating point training layer and binary or ternary evidence layers. Omnibus weights of evidence (OWoFE) integrates fuzzy training layer and diverse evidential layers. This Omnibus weights of evidence method has been implemented in a GIS system "C GeoData Analysis System which provides new features in comparison with the ordinary weights of evidence method: (1) dual fuzzy weights of evidence (DFWoFE), in which training layer and evidence layers can be fuzzy sets. DFWoFE can be used to predict not only point events but also area or line events. In this model a fuzzy training layer can be defined based on point, line and areas using fuzzy membership function; (2) Logistic Model for Weights of Evidence Method on the basis of local singularity theory which has been proposed for mapping geo-anomalies for delineating mineral potential targets. A new index similar to the singularity has been introduced to form a log-linear model for integrating evidential layers. The model can be used as alternative to the conventional logistic model used in weights of evidence method; (3) Degree-of exploration model for WoFE through building a degree-of-exploration map would be possible to assess possible spatial correlations between the degree-of-exploration and potential evidence layers. Importantly, it also would make it possible to estimate undiscovered resources, if the degree-of-exploration map is combined with other models that predict where such resources are most likely to occur. The methods and systems were validated using a case study of mineral potential prediction in Gejiu mineral district.
Key words: Weights of evidence, Fuzzy set, degree of exploration, GIS, GeoDAS