Articles | Volume 26, issue 22
Hydrol. Earth Syst. Sci., 26, 5793–5816, 2022
https://doi.org/10.5194/hess-26-5793-2022
Hydrol. Earth Syst. Sci., 26, 5793–5816, 2022
https://doi.org/10.5194/hess-26-5793-2022
Research article
17 Nov 2022
Research article | 17 Nov 2022

How can we benefit from regime information to make more effective use of long short-term memory (LSTM) runoff models?

Reyhaneh Hashemi et al.

Data sets

Database of watershed-scale hydroclimatic observations in France O. Delaigue, B. Génot, L. Lebecherel, P. Brigode, and P.-Y. Bourgin https://doi.org/10.15454/UV01P1

Download
Short summary
Hydrologists have long dreamed of a tool that could adequately predict runoff in catchments. Data-driven long short-term memory (LSTM) models appear very promising to the hydrology community in this respect. Here, we have sought to benefit from traditional practices in hydrology to improve the effectiveness of LSTM models. We discovered that one LSTM parameter has a hydrologic interpretation and that there is a need to increase the data and to tune two parameters, thereby improving predictions.