A genetic programming technique for lake level modeling

Abstract

The potential of gene expression programming (GEP) approach for modeling monthly lake levels is investigated. The application of the methodology is presented for the monthly water level data of Van Lake, which is the biggest lake in Turkey. The root mean square errors, mean absolute relative errors, determination coefficient, and modified coefficient of efficiency (E M) are used for evaluating the accuracy of the genetic programming-based models. The results of the proposed models are compared with those of the neuro-fuzzy models. The comparison results indicate that the suggested GEP-based models perform better than the neuro-fuzzy models in forecasting monthly lake levels. © IWA Publishing 2014.