Comparison of two data-driven modelling techniques for long-term streamflow prediction using limited datasets

Abstract

. His focus is in the fields of hydrological modelling and climate change impacts on water resources, with particular interest in the development of models using evolutionary computation and artificial intelligence techniques. His current research relates to the use of genetic programming and differential evolution-trained neural networks to model streamflow response to local hydro-climatic variables in the upper uMkhomazi River. He focuses on developing and applying evolutionary optimisation techniques to solve real-world science and engineering design problems at minimum cost and for maximum benefit. He is renowned for the development of a multi-objective evolutionary algorithm called multi-objective differential evolution algorithm (MDEA) which is used by many researchers worldwide.