Pan Evaporation Simulation Based on Daily Meteorological Data Using Soft Computing Techniques and Multiple Linear Regression

摘要: Evaporation, a major component of hydrologic cycle, is an important parameter to many applications in water resource management, irrigation scheduling, and environmental studies. In this study, two soft computing techniques: (a) Artificial Neural Network (ANN), (b) Co-active Neuro-Fuzzy Inference System (CANFIS); Multiple Linear Regression (MLR) were used simulate daily pan evaporation (Ep) at Pantnagar, located the foothills Himalayas Uttarakhand state India. Daily meteorological data such as maximum minimum air temperature, relative humidity morning (7 AM) afternoon (2 PM), wind speed, sun shine hours form January 1, 2001 December 31, 2004 for developing ANN, CANFIS MLR models. A comparison based on statistical indices root mean squared error (RMSE), coefficient efficiency (CE) correlation (r) was made among estimated magnitudes Ep by The architecture ANN managed NeuroSolutions 5.0 software produced NeuroDimension, Inc., Florida. designed with hyperbolic tangent activation function Delta-Bar-Delta learning algorithm similarly Gaussian membership function, Takagi-Sugeno-Kang fuzzy model, algorithm. results indicated that performance model 6-9-1 general superior models; however, models better than all input variables single hidden layer found be best simulating Pantnagar.