Articles | Volume 386
https://doi.org/10.5194/piahs-386-141-2024
https://doi.org/10.5194/piahs-386-141-2024
Post-conference publication
 | 
19 Apr 2024
Post-conference publication |  | 19 Apr 2024

Dual-Stage Attention-Based LSTM Network for Multiple Time Steps Flood Forecasting

Fan Wang, Weiqi Wang, Wuxia Bi, Wenqing Lin, and Dawei Zhang

Related authors

Global experiences in flood management – perspectives through ICFM Webinar Series
Cheng Zhang and Wuxia Bi
Proc. IAHS, 386, 307–312, https://doi.org/10.5194/piahs-386-307-2024,https://doi.org/10.5194/piahs-386-307-2024, 2024
Short summary
High-resolution ensemble projections and uncertainty assessment of regional climate change over China in CORDEX East Asia
Huanghe Gu, Zhongbo Yu, Chuanguo Yang, Qin Ju, Tao Yang, and Dawei Zhang
Hydrol. Earth Syst. Sci., 22, 3087–3103, https://doi.org/10.5194/hess-22-3087-2018,https://doi.org/10.5194/hess-22-3087-2018, 2018
Short summary

Cited articles

Addor, N., Newman, A. J., Mizukami, N., and Clark, M. P.: The CAMELS data set: catchment attributes and meteorology for large-sample studies, Hydrol. Earth Syst. Sci., 21, 5293–5313, https://doi.org/10.5194/hess-21-5293-2017, 2017. 
Dazzi, S., Vacondio, R., and Mignosa, P.: Flood Stage Forecasting Using Machine-Learning Methods: A Case Study on the Parma River (Italy), Water, 13, 1612, https://doi.org/10.3390/w13121612, 2021. 
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997. 
Kao, I. F., Zhou, Y. L., Chang, L. C., and Chang, F. J.: Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting, J. Hydrol., 583, 124631, https://doi.org/10.1016/j.jhydrol.2020.124631, 2020. 
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018. 
Download
Short summary
Flood forecasting is important for controlling floods, and lately people have been paying more attention to using data-driven models instead of just physical or conceptual ones. This study uses an state of art neural networks to make the most out of all kinds of historical data and precipitation forecasts for predicting floods over different time scales. We tested it in serval watersheds in China, and it turned out to be really accurate and reliable.