Abstract
Abstract. 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.
Subject
General Earth and Planetary Sciences,General Engineering,General Environmental Science
Reference61 articles.
1. Abrahart, R. J. and See, L.: Comparing neural network and autoregressive moving
average techniques for the provision of continuous river flow forecasts in
two contrasting catchments, Hydrol. Proc., 14, 2157–2172, 2000. a
2. 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.
a, b, c, d
3. Bannister, R.: A review of operational methods of variational and
ensemble-variational data assimilation, Q. J. Roy. Meteor. Soc., 143, 607–633, 2017. a
4. Bengio, S., Vinyals, O., Jaitly, N., and Shazeer, N.: Scheduled sampling for
sequence prediction with recurrent neural networks, arXiv [preprint],
https://doi.org/10.48550/arXiv.1506.03099, 2015. a
5. Cameron, D., Kneale, P., and See, L.: An evaluation of a traditional and a
neural net modelling approach to flood forecasting for an upland catchment,
Hydrol. Proc., 16, 1033–1046, https://doi.org/10.1002/hyp.317, 2002. a
Cited by
17 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献