Co-active neurofuzzy inference system for evapotranspiration modeling

This study proposes co-active neuro-fuzzy inference system (CANFIS) for daily reference evapotranspiration (ET0) modeling by using daily atmospheric parameters obtained from California Irrigation Management Information System (CIMIS) database. The CANFIS model is trained and tested using three stations from different geographical locations in California. The model is compared with the well-known conventional ET0 models such as the CIMIS Penman equation, the Penman-Monteith equation standardized by the Food and Agriculture Organization (FAO-56 PM), the Hargreaves equation and the Turc equation. Meteorological variables; solar radiation, air temperature, relative humidity and wind speed taken from CIMIS database for 4 years (January 2002-December 2005) are used to evaluate the performance analysis of the models. Statistics such as average, standard deviation, minimum and maximum values, as well as criteria such as root mean square error (RMSE), the efficiency coefficient (E) and determination coefficient (R (2)) are used to measure the performance of the CANFIS. Considerably well performance is achieved in modeling ET0 by using CANFIS. It is concluded from the results that CANFIS can be proposed as an alternative ET0 model to the existing conventional models.