Hydrological modelling using artificial neural networks

TLDR

Hydrological modelling with artificial neural networks is an emerging field marked by diverse techniques, varied geographic contexts, limited intermodel comparisons, and inconsistent skill reporting, underscoring a need for clearer guidance and systematic comparison with conventional statistical models. The review aims to outline ANN principles for rainfall‑runoff modelling and flood forecasting, propose a template to guide future model construction, and suggest research into extracting hydrological rules from ANN weights and developing complexity‑penalizing performance metrics. The review details ANN modelling principles, common architectures and training algorithms, and discusses data division, preprocessing, standardization, and performance evaluation, culminating in a template to aid future model construction.

Abstract

This review considers the application of artificial neural networks (ANNs) to rainfall-runoff modelling and flood forecasting. This is an emerging field of research, characterized by a wide variety of techniques, a diversity of geographical contexts, a general absence of intermodel comparisons, and inconsistent reporting of model skill. This article begins by outlining the basic principles of ANN modelling, common network architectures and training algorithms. The discussion then addresses related themes of the division and preprocessing of data for model calibration/validation; data standardization techniques; and methods of evaluating ANN model performance. A literature survey underlines the need for clear guidance in current modelling practice, as well as the comparison of ANN methods with more conventional statistical models. Accordingly, a template is proposed in order to assist the construction of future ANN rainfall-runoff models. Finally, it is suggested that research might focus on the extraction of hydrological ‘rules’ from ANN weights, and on the development of standard performance measures that penalize unnecessary model complexity.