ABSTRACT
Integrated Water Resources Management (IWRM) is the process of developing and managing water, land, and other related resources together in an equitable manner without affecting its sustainability. The computational tools range from simple lumped models to complex distributed watershed models and along with them many soft computing tools and statistical methods found a way to solve complex and challenging water resources problems. Fuzzy logic, ANN, SVM, genetic algorithm, and other deep learning methods are widely applied for watershed modelling, flood forecasting, downscaling climatic inputs, water quality modelling, and ground water modelling. This chapter discusses the overview of soft computing methods used for IWRM, their applications, efficiency, limitations, and future scope. An extensive review of the state-of-the-art literature was performed. Results revealed that hybrid models performed better in several studies. Also, the performance of models varies in terms of prediction accuracy as well as uncertainty in predictions. No model can be accepted as a best one universally; performance of each model changed based on characteristics of data used.
