FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

Comparing a long short-term memory (LSTM) neural network with a physically-based hydrological model for streamflow forecasting over a Canadian catchment

Downloads

Downloads per month over past year

Sabzipour, Behmard, Arsenault, Richard, Troin, Magali, Martel, Jean-Luc, Brissette, François, Brunet, Frédéric and Mai, Juliane. 2023. « Comparing a long short-term memory (LSTM) neural network with a physically-based hydrological model for streamflow forecasting over a Canadian catchment ». Journal of Hydrology, vol. 627, nº Part A.
Compte des citations dans Scopus : 3.

[thumbnail of Arsenault-R-2023-28095.pdf]
Preview
PDF
Arsenault-R-2023-28095.pdf - Published Version
Use licence: Creative Commons CC BY.

Download (10MB) | Preview

Abstract

Streamflow forecasting is crucial in water planning and management. Physically-based hydrological models have been used for a long time in these fields, but improving forecast quality is still an active area of research. Recently, some artificial neural networks have been found to be effective in simulating and predicting short-term streamflow. In this study, we examine the reliability of Long Short-Term Memory (LSTM) deep learning model in predicting streamflow for lead times of up to ten days over a Canadian catchment. The performance of the LSTM model is compared to that of a process-based distributed hydrological model, with both models using the same weather ensemble forecasts. Furthermore, the LSTM’s ability to integrate observed streamflow on the forecast issue date is compared to the data assimilation process required for the hydrological model to reduce initial state biases. Results indicate that the LSTM model forecasted streamflows are more reliable and accurate for leadtimes up to 7 and 9 days, respectively. Additionally, it is shown that the LSTM model using recent observed flows as a predictor can forecast flows with smaller errors in the first forecasting days without requiring an explicit data assimilation step, with the LSTM model generating a median value of mean absolute error (MAE) for the first day of lead-time across all forecast issue dates of 25 m3/s compared to 115 m3/s for the assimilated hydrological model.

Item Type: Peer reviewed article published in a journal
Professor:
Professor
Arsenault, Richard
Martel, Jean-Luc
Brissette, François
Affiliation: Génie de la construction, Génie de la construction, Génie de la construction
Date Deposited: 23 Nov 2023 16:54
Last Modified: 18 Dec 2023 16:16
URI: https://espace2.etsmtl.ca/id/eprint/28095

Actions (login required)

View Item View Item