Model trees as an alternative to neural networks in rainfall—runoff modelling

TLDR

The study compares artificial neural networks and model trees for rainfall‑runoff forecasting. The authors evaluate both methods by forecasting runoff at 1, 3, and 6‑hour horizons for a European catchment. Both ANNs and MTs achieve excellent 1‑hour predictions, acceptable 3‑hour predictions, and conditionally acceptable 6‑hour predictions; ANNs slightly outperform MTs at longer lead times, but MTs offer greater interpretability and flexibility.

Abstract

Abstract This paper investigates the comparative performance of two data-driven modelling techniques, namely, artificial neural networks (ANNs) and model trees (MTs), in rainfall—runoff transformation. The applicability of these techniques is studied by predicting runoff one, three and six hours ahead for a European catchment. The result shows that both ANNs and MTs produce excellent results for 1-h ahead prediction, acceptable results for 3-h ahead prediction and conditionally acceptable result for 6-h ahead prediction. Both techniques have almost similar performance for 1-h ahead prediction of runoff, but the result of the ANN is slightly better than the MT for higher lead times. However, the advantage of the MT is that the result is more understandable and allows one to build a family of models of varying complexity and accuracy.