The document compares the use of artificial neural networks (ANNs) and model trees (MTs) for rainfall-runoff modelling. It tests these techniques on a European catchment to predict runoff 1, 3, and 6 hours ahead. The results show that both ANNs and MTs produced excellent results for 1-hour ahead prediction, acceptable results for 3-hour prediction, and conditional acceptable results for 6-hour prediction. While the performance of ANNs and MTs was similar for 1-hour predictions, ANNs performed slightly better for longer lead times. However, MTs have the advantage of producing more understandable and adjustable models of varying complexity and accuracy.