Fuzzy-GA Approach for Estimating Rainfall over Uppe r Chi- Mun Basins of Thailand

Abstract

The present study examines the fuzzy sets model for computing rainfall over the Upper Chi-Mun basins in the Northeastern region of Thaila nd based on historical weather data from five stations’ rain gauges under the radar umb rella, temperature, relative humidity, and radar reflectivity. Data were collected during June 2009 to August 2009 of the rainfall reflectivity record from the Royal Rainmaking Resea rch Centre at Pimai, Nakhon Ratchasima Province, and for the surface rainfall, automatic rain gauges were used. The results showed that the Fuzzy-GAs model could be us ed effectively to estimate rainfall given only three parameters: temperature, relative humidity and radar reflectivity. Furthermore, the results show that the genetic algo rithm calibration provided the optimal conditions of the membership function. The simulati on results indicated that the results of the Fuzzy-GA model were close to the observed rainf all data more than the results of a multiple linear regression model for both calibrati on and validation processes. Consequently, we are confident that a Fuzzy-GA mode l is a useful tool for estimating rainfall. Keywords: Fuzzy set, Genetic algorithm, Optimization techniqu e, Radar reflectivity.