HESS Opinions: Never train a Long Short-Term Memory (LSTM) network on a single basin
| Autor: | F. Kratzert, M. Gauch, D. Klotz, G. Nearing |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2024 |
| Předmět: | |
| Zdroj: | Hydrology and Earth System Sciences, Vol 28, Pp 4187-4201 (2024) |
| Druh dokumentu: | article |
| ISSN: | 1027-5606 1607-7938 |
| DOI: | 10.5194/hess-28-4187-2024 |
| Popis: | Machine learning (ML) has played an increasing role in the hydrological sciences. In particular, Long Short-Term Memory (LSTM) networks are popular for rainfall–runoff modeling. A large majority of studies that use this type of model do not follow best practices, and there is one mistake in particular that is common: training deep learning models on small, homogeneous data sets, typically data from only a single hydrological basin. In this position paper, we show that LSTM rainfall–runoff models are best when trained with data from a large number of basins. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|