Abstract
AbstractThis study investigates the capability of sequence-to-sequence machine learning (ML) architectures in an effort to develop streamflow forecasting tools for Canadian watersheds. Such tools are useful to inform local and region-specific water management and flood forecasting related activities. Two powerful deep-learning variants of the Recurrent Neural Network were investigated, namely the standard and attention-based encoder-decoder long short-term memory (LSTM) models. Both models were forced with past hydro-meteorological states and daily meteorological data with a look-back time window of several days. These models were tested for 10 different watersheds from the Ottawa River watershed, located within the Great Lakes Saint-Lawrence region of Canada, an economic powerhouse of the country. The results of training and testing phases suggest that both models are able to simulate overall hydrograph patterns well when compared to observational records. Between the two models, the attention model significantly outperforms the standard model in all watersheds, suggesting the importance and usefulness of the attention mechanism in ML architectures, not well explored for hydrological applications. The mean performance accuracy of the attention model on unseen data, when assessed in terms of mean Nash–Sutcliffe Efficiency and Kling-Gupta Efficiency is, respectively, found to be 0.985 and 0.954 for these watersheds. Streamflow forecasts with lead times of up to 5 days with the attention model demonstrate overall skillful performance with well above the benchmark accuracy of 70%. The results of the study suggest that the encoder–decoder LSTM, with attention mechanism, is a powerful modelling choice for developing streamflow forecasting systems for Canadian watersheds.
Funder
National Research Council Canada
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Software
Reference65 articles.
1. Rockwood DM (1964) Streamflow synthesis and reservoir regulation. US Army Engineer Division, North Pacific, Portland, Oregon, Engineering Studies Project 171.
2. Arnold J, Williams, J, Srinivasan, R, et al (1994) SWAT-soil and water assessment tool. US Department of Agriculture, Agricultural Research Service, Grassland, Soil and Water Research Laboratory, Temple, TX, 1994
3. Refshaard J, Storm B et al. (1995) MIKE SHE. Computer models of watershed hydrology, pp. 809–846
4. Kouwen N (1988) WATFLOOD: a Micro-computer based flood forecasting system based on real-time weather Radar. Canad Water Resour J/Revue Canadienne des Ressources Hydriques 13:62–77. https://doi.org/10.4296/cwrj1301062
5. Kouwen N, Soulis ED, Pietroniro A et al (1993) Grouped response units for distributed hydrologic modeling. J Water Resour Plan Manag 119:289–305
Cited by
42 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