Integrated techniques were developed, applied, and validated for the analysis of ground subsidence hazards by abandoned coal mines in Samcheok, Korea, using a geographic information system (GIS). Slope, depth of drift, distance from drift, groundwater level, permeability, geology, and land use were extracted or calculated from the digital elevation model, topographic, drift distribution, borehole, geologic, and land use database. By using the constructed spatial database, the relations between the ground subsidence location and seven related factors were identified and quantified by frequency ratio (FR), weights-of-evidence (WOE), logistic regression (LR), and artificial neural network (ANN) models. The relations were used as factor ratings in the overlay analysis to create ground subsidence hazard indices and maps. The four ground subsidence hazard maps were reflected as the new input factors and integrated using FR, WOE, LR, and ANN models to make a hazard map. All of the subsidence hazard maps were validated by comparison with known ground subsidence locations that were not used in the analysis. As a result, the integrated ground subsidence hazard maps used four new subsidence-related input factors that showed a greater accuracy (96.46% for FR, 97.22% for WOE, 97.20% for LR, and 96.70% for ANN, respectively), than the individual ground subsidence maps (95.54% for FR, 94.22% for WOE, 96.89% for LR, and 94.45% for ANN, respectively) using the first seven factors. (C) 2010 Elsevier B.V. All rights reserved.