Development of stage–discharge rating curve using model tree and neural networks: An application to Peachtree Creek in Atlanta

Abstract

The applicability and the performance of the M5P model tree machine learning technique is investigated in modeling of the stage–discharge problem for Peachtree Creek in Atlanta, Georgia. The stage–discharge relationship has an important bearing on the correct assessment of discharge. This technique is compared to three different algorithms of artificial neural network and conventional rating curve. It is shown that the model trees, being analogous to piecewise linear functions, have certain advantages over neural networks; they are more transparent and hence acceptable by decision makers, they are very fast in training, and they always converge. The accuracy of M5P trees is superior to neural network models and conventional model. It was found that M5P outperformed when fewer data events were available for model development. In other words, M5P has potential to be a useful and practical tool for cases where less measured data is available for modeling stage–discharge problem. This study has also showed high consistency between the training and testing phases of modeling when using M5P compared to neural network models and conventional method. Furthermore, a partition analysis has been performed. This analysis reveals that the results obtained using M5P model performed better than ANN for both the high flows and the low flows.