M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China

TLDR

The study evaluates the applicability and performance of the M5 model tree technique for flood forecasting in the upper Huai River, China. The authors compare M5 trees to multilayer perceptron ANNs, building a modular mixture of models that splits flood samples by hydrological characteristics and trains separate M5 and ANN models for each group. M5 trees are more transparent, train faster, and always converge, achieving accuracy comparable to ANNs, while the hybrid model combining M5 trees and ANNs delivers the best prediction performance.

Abstract

The applicability and performance of the so-called M5 model tree machine learning technique is investigated in a flood forecasting problem for the upper reach of the Huai River in China. In one of configurations this technique is compared to multilayer perceptron artificial neural network (ANN). It is shown that model trees, being analogous to piecewise linear functions, have certain advantages compared to ANNs—they are more transparent and hence acceptable by decision makers, are very fast in training and always converge. The accuracy of M5 trees is similar to that of ANNs. The improved accuracy in predicting high floods was achieved by building a modular model (mixture of models); in it the flood samples with special hydrological characteristics are split into groups for which separate M5 and ANN models are built. The hybrid model combining model tree and ANN gives the best prediction result.