Prediction of River Stage Using Multistep-Ahead Machine Learning Techniques for a Tidal River of Taiwan
Open Access
Abstract
Time-series prediction of a river stage during typhoons or storms is essential for flood control or flood disaster prevention. Data-driven models using machine learning (ML) techniques have become an attractive and effective approach to modeling and analyzing river stage dynamics. However, relatively new ML techniques, such as the light gradient boosting machine regression (LGBMR), have rarely been applied to predict the river stage in a tidal river. In this study, data-driven ML models were developed under a multistep-ahead prediction framework and evaluated for river stage modeling. Four ML techniques, namely support vector regression (SVR), random forest regression (RFR), multilayer perceptron regression (MLPR), and LGBMR, were employed to establish data-driven ML models with Bayesian optimization. The models were applied to simulate river stage hydrographs of the tidal reach of the Lan-Yang River Basin in Northeastern Taiwan. Historical measurements of rainfall, river stages, and tidal levels were collected from 2004 to 2017 and used for training and validation of the four models. Four scenarios were used to investigate the effect of the combinations of input variables on river stage predictions. The results indicated that (1) the tidal level at a previous stage significantly affected the prediction results; (2) the LGBMR model achieves more favorable prediction performance than the SVR, RFR, and MLPR models; and (3) the LGBMR model could efficiently and accurately predict the 1–6-h river stage in the tidal river. This study provides an extensive and insightful comparison of four data-driven ML models for river stage forecasting that can be helpful for model selection and flood mitigation.Keywords
This publication has 62 references indexed in Scilit:
- Predicting typhoon-induced storm surge tide with a two-dimensional hydrodynamic model and artificial neural network modelNatural Hazards and Earth System Sciences, 2012
- Comparison of ANN approach with 2D and 3D hydrodynamic models for simulating estuary water stageAdvances in Engineering Software, 2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Effective typhoon characteristics and their effects on hourly reservoir inflow forecastingAdvances in Water Resources, 2010
- Potential of support vector regression for prediction of monthly streamflow using endogenous propertyHydrological Processes, 2009
- River stage prediction based on a distributed support vector regressionJournal of Hydrology, 2008
- Data-driven modelling: some past experiences and new approachesJournal of Hydroinformatics, 2008
- Support vector regression for real-time flood stage forecastingJournal of Hydrology, 2006
- FLOOD STAGE FORECASTING WITH SUPPORT VECTOR MACHINES1Jawra Journal of the American Water Resources Association, 2002
- Learning representations by back-propagating errorsNature, 1986