The efficiency of genetic programming model in simulating rainfall-runoff process (Case Study: Khorramabad river basin)

Predicting the river discharge is one of the important subjects in water resourcesengineering. This subject is of utmost importance in terms of planning,management, and policy of water resources with the aim of economic andenvironmental development, especially in a country like Iran with limited waterresources. Awareness of the relation between rainfall and runoff of basins is aninseparable past of water design studies. Lack of sufficient data on rainfall-runoffdue to the absence of appropriate hydrometric stations reveals the importanceof using indirect methods and heuristic algorithms for estimating the basins runoff more than before. In the present research, the genetic programmingmodel has been employed to simulate the rainfall-runoff process ofKhorramabad River basin, and in order to introduce the patterns and identify thebest pattern dominating the nature of flow, all statistical data were divided intotwo groups of training and experiment (52 percent training and 48 percentexperiment) and the program was implemented for 1000 replications using fittingfunctions and going through replication and developmental processes so as tofind the optimal replication. Moreover, in order to evaluate the relations obtainedfrom the simulator model, Root Mean Square Error (RMSE) and Mean SquaredError (MSE) indexes and Coefficient of Determination (R2) have been used. Theinvestigations demonstrate that the employed equation 3 has the greatestrelevance with the observational data. Therefore, it is recommended that the saidequation be used for the rainfall-runoff studies of the abovementioned basin.Based on the results, the genetic programming model is an accurate directmethod for predicting the discharge of Khorramabad River basin.

Keywords:

Simulation , Rainfall-runoff , Heuristic algorithm , Genetic programming