Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

作者：Qianyang Wang, Yuan Liu, Qimeng Yue, Yuexin Zheng, Xiaolei Yao, Jingshan Yu · 发表于：Water · 年份：2020 · DOI：10.3390/w12123532 · 被引用次数：19 · 研究领域：Hydrological Forecasting Using AI、Hydrology and Watershed Management Studies、Flood Risk Assessment and Management

A gated recurrent unit (GRU) network, which is a kind of artificial neural network (ANN), has been increasingly applied to runoff forecasting. However, knowledge about the impact of different input data filtering strategies and the implications of different architectures on the GRU runoff forecasting model’s performance is still insufficient. This study has selected the daily rainfall and runoff data from 2007 to 2014 in the Wei River basin in Shaanxi, China, and assessed six different scenarios to explore the patterns of that impact. In the scenarios, four manually-selected rainfall or runoff data combinations and principal component analysis (PCA) denoised input have been considered along with single directional and bi-directional GRU network architectures. The performance has been evaluated from the aspect of robustness to 48 various hypermeter combinations, also, optimized accuracy in one-day-ahead (T + 1) and two-day-ahead (T + 2) forecasting for the overall forecasting process and the flood peak forecasts. The results suggest that the rainfall data can enhance the robustness of the model, especially in T + 2 forecasting. Additionally, it slightly introduces noise and affects the optimized prediction accuracy in T + 1 forecasting, but significantly improves the accuracy in T + 2 forecasting. Though with relevance (R = 0.409~0.763, Grey correlation grade >0.99), the runoff data at the adjacent tributary has an adverse effect on the robustness, but can enhance the accur...