Predictive ability of logistic regression, auto-logistic regression and neural network models in empirical land-use change modeling-a case study

摘要: The objective of this study is to compare the abilities logistic, auto-logistic and artificial neural network (ANN) models for quantifying relationships between land uses their drivers. In addition, application results obtained by three techniques tested in a dynamic land-use change model (CLUE-s) Paochiao watershed region Taiwan. Relative operating characteristic curves (ROCs), kappa statistics, multiple resolution validation landscape metrics were used assess ability estimating relationship driving factors use its subsequent models. illustrate that case ANNs constitute powerful alternative logistic regression empirical modeling spatial processes. provide better fit pattern. performs than nearly as well ANNs. Auto-logistic are considered especially useful when performance more conventional not satisfactory or underlying data unknown. indicate an evaluation specify can improve