Assessment of ground subsidence using GIS and the weights-of-evidence model

摘要: Abstract The weights-of-evidence model, one of the Bayesian probability models was applied in evaluating a ground subsidence spatial hazard near abandoned underground coal mines (AUCMs) at Magyori area, Samcheok City Korea using GIS. Using location and database containing information such as mining tunnel, borehole, topography, geology, land use, model to calculate each relevant factor's rating for area Korea. Seven major factors controlling or related were determined from analysis existing area; depth drift distance tunnel map, slope gradient obtained topographical water level permeability borehole data, geology use. Tests conditional independence performed selection factors, allowing 6 combinations be analyzed. For mapping hazard, contrast values, W + − , overlaid spatially. results validated receiver operating characteristic (ROC) with previous locations. In case all factor used, under ROC curve (AUC) showed 0.9667, which corresponds an accuracy 96.67%. combinations, drift, use 90.71% (AUC: 0.9071) is best result produced this analysis. can used prevention land-use planning AUCM areas.