Effect of model formulation on the optimization of a genetic Takagi-Sugeno fuzzy system for fish habitat suitability evaluation

Article ID	Journal	Published Year	Pages	File Type
4376970	Ecological Modelling	2011	13 Pages	PDF

Abstract

âº We assess the effects of model formulation on species distribution modelling. âº We focus on model accuracy, threshold criteria and habitat suitability curves. âº A genetic Takagi-Sugeno fuzzy model is used. âº The product operation leads to the highest accuracy and consistent habitat suitability curves. âº Threshold criteria should be selected according to the model formulation used.

Keywords

HSC TNR SDMs Dem GARP MDT CCI GLMs HSI MSE ROC MaxEnt MST TSS true skill statistic ANNs AUC GAMs SVMs Cross validation Genetic algorithms Species distribution Maximum Entropy mean squared error TPR GPS Global Positioning System Genetic fuzzy systems habitat suitability index artificial neural networks Support vector machines true positive false positive area under the receiver operating characteristics curve digital elevation model Generalized additive models Species distribution models Generalized linear models Data-driven model false negative true negative True positive rate True negative rate receiver operating characteristics Gas