期刊
HYDROLOGY AND EARTH SYSTEM SCIENCES
卷 26, 期 21, 页码 5493-5513出版社
COPERNICUS GESELLSCHAFT MBH
DOI: 10.5194/hess-26-5493-2022
关键词
-
资金
- Google Faculty Research Award
- Linz Institute of Technology DeepFlood project
- Verbund AG
Ingesting real-time observation data is crucial for many hydrological forecasting systems. This paper compares two strategies, autoregression and variational data assimilation, for incorporating real-time streamflow observations into LSTM rainfall-runoff models. The results show that autoregression is both more accurate and computationally efficient, but it is sensitive to missing data. However, this can be mitigated by using an appropriate training strategy in data assimilation.
Ingesting near-real-time observation data is a critical component of many operational hydrological forecasting systems. In this paper, we compare two strategies for ingesting near-real-time streamflow observations into long short-term memory (LSTM) rainfall-runoff models: autoregression (a forward method) and variational data assimilation. Autoregression is both more accurate and more computationally efficient than data assimilation Autoregression is sensitive to missing data, however an appropriate (and simple) training strategy mitigates this problem. We introduce a data assimilation procedure for recurrent deep learning models that uses backpropagation to make the state updates.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据