AUTHOR=Xiao Lu , Zhong Ming , Zha Dawei 

TITLE=Runoff Forecasting Using Machine-Learning Methods: Case Study in the Middle Reaches of Xijiang River

JOURNAL=Frontiers in Big Data

VOLUME=Volume 4 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2021.752406

DOI=10.3389/fdata.2021.752406

ISSN=2624-909X

ABSTRACT=Runoff forecasting is useful for flooding early warning and water resources management. In this study, back propagation (BP) neural network, generalized regression neural networks (GRNN), extreme learning machine (ELM) and wavelet neural network (WNN) models are employed, and a high-accuracy runoff forecast model is developed at Wuzhou station in the middle reaches of Xijiang River. The GRNN model is selected as optimal runoff forecasting model, and is also used to predict the streamflow and water level by considering the flood propagation time. Results show that: (1) the GRNN presents the best performance in the 7-day lead time of streamflow; (2) the WNN model shows the highest accuracy in the in the 7-day lead time of water level; (3) the GRNN model performs well in runoff forecasting by considering flood propagation time, increasing the QR of streamflow and water level forecast to 98.36% and 82.74%, respectively, and illustrate scientifically of the peak underestimation in streamflow and water level. This research proposes a high-accuracy runoff forecasting model using machine learning, which would improve the early warning capabilities of floods and droughts, the results also lay an important foundation for the mid-long term runoff forecasting