Predicting rainfall intensity using a genetic algorithm approach

Abstract

A genetic algorithm rainfall intensity (GARI) model has been developed and used to predict the intensities for given return period. It is a one-step solution procedure that may not require any mathematical transformation. The problem formulation is given and the genetic algorithm solution of the problem is presented. The results show that the proposed GARI model can be used to solve the rainfall intensity-duration-frequency relations with lowest mean-squared error between measured and predicted intensities. Predicted intensities are in good agreement between measured and predicted values for given return period. Copyright © 2006 John Wiley & Sons, Ltd.