Comparison of six different soft computing methods in modeling evaporation in different climates

Abstract. Evaporation plays important roles in regional water resources management,terrestrial ecological process and regional climate change. This study investigated the abilities of six different soft computing methods, Multi-layer perceptron (MLP), generalized regression neural network (GRNN), fuzzy genetic (FG), least square support vector machine (LSSVM), multivariate adaptive regression spline (MARS), adaptive neuro-fuzzy inference systems with grid partition (ANFIS-GP), and two regression methods, multiple linear regression (MLR) and Stephens and Stewart model (SS) in predicting monthly Ep. Long-term climatic data at eight stations in different climates, air temperature (Ta), solar radiation (Rg), sunshine hours (Hs), relative humidity (RH) and wind speed (Ws) during 1961–2000 are used for model development and validation. The first part of applications focused on testing and comparing the model accuracies using different local input combinations. The results showed that the models have different accuracies in different climates and the MLP model performed superior to the other models in predicting monthly Ep at most stations, while GRNN model performed better in Tibetan Plateau. The accuracies of above models ranked as: MLP, GRNN, LSSVM, FG, ANFIS-GP, MARS and MLR. Generalized models were also developed and tested with data of eight stations. The overall results indicated that the soft computing techniques generally performed better than the regression methods, but MLR and SS models can be more preferred at some climatic zones instead of complex nonlinear models, for example, the BJ, CQ and HK stations.