Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell

<p>Long short-term memory (LSTM) networks have demonstrated state-of-the-art performance for rainfall-runoff hydrological modelling. However, most studies focus on predictions at a daily scale, limiting the benefits of sub-daily (e.g. hourly) predictions in applications like flood forecasting....

Full description

Saved in:
Bibliographic Details
Main Authors: E. Acuña Espinoza, F. Kratzert, D. Klotz, M. Gauch, M. Álvarez Chaves, R. Loritz, U. Ehret
Format: Article
Language:English
Published: Copernicus Publications 2025-03-01
Series:Hydrology and Earth System Sciences
Online Access:https://hess.copernicus.org/articles/29/1749/2025/hess-29-1749-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850206050122203136
author E. Acuña Espinoza
F. Kratzert
D. Klotz
D. Klotz
M. Gauch
M. Álvarez Chaves
R. Loritz
U. Ehret
author_facet E. Acuña Espinoza
F. Kratzert
D. Klotz
D. Klotz
M. Gauch
M. Álvarez Chaves
R. Loritz
U. Ehret
author_sort E. Acuña Espinoza
collection DOAJ
description <p>Long short-term memory (LSTM) networks have demonstrated state-of-the-art performance for rainfall-runoff hydrological modelling. However, most studies focus on predictions at a daily scale, limiting the benefits of sub-daily (e.g. hourly) predictions in applications like flood forecasting. Moreover, training an LSTM network exclusively on sub-daily data is computationally expensive and may lead to model learning difficulties due to the extended sequence lengths. In this study, we introduce a new architecture, multi-frequency LSTM (MF-LSTM), designed to use input of various temporal frequencies to produce sub-daily (e.g. hourly) predictions at a moderate computational cost. Building on two existing methods previously proposed by the co-authors of this study, MF-LSTM processes older inputs at coarser temporal resolutions than more recent ones. MF-LSTM gives the possibility of handling different temporal frequencies, with different numbers of input dimensions, in a single LSTM cell, enhancing the generality and simplicity of use. Our experiments, conducted on 516 basins from the CAMELS-US dataset, demonstrate that MF-LSTM retains state-of-the-art performance while offering a simpler design. Moreover, the MF-LSTM architecture reported a 5 times reduction in processing time compared to models trained exclusively on hourly data.</p>
format Article
id doaj-art-63dc8d3d52f94368bc8e328512840e06
institution OA Journals
issn 1027-5606
1607-7938
language English
publishDate 2025-03-01
publisher Copernicus Publications
record_format Article
series Hydrology and Earth System Sciences
spelling doaj-art-63dc8d3d52f94368bc8e328512840e062025-08-20T02:10:57ZengCopernicus PublicationsHydrology and Earth System Sciences1027-56061607-79382025-03-01291749175810.5194/hess-29-1749-2025Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cellE. Acuña Espinoza0F. Kratzert1D. Klotz2D. Klotz3M. Gauch4M. Álvarez Chaves5R. Loritz6U. Ehret7Institute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, GermanyGoogle Research, Vienna, AustriaGoogle Research, Vienna, AustriaMachine Learning in Earth Science, Interdisciplinary Transformation University Austria, Linz, AustriaGoogle Research, Zurich, SwitzerlandStuttgart Center for Simulation Science, Statistical Model-Data Integration, University of Stuttgart, Stuttgart, GermanyInstitute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, GermanyInstitute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany<p>Long short-term memory (LSTM) networks have demonstrated state-of-the-art performance for rainfall-runoff hydrological modelling. However, most studies focus on predictions at a daily scale, limiting the benefits of sub-daily (e.g. hourly) predictions in applications like flood forecasting. Moreover, training an LSTM network exclusively on sub-daily data is computationally expensive and may lead to model learning difficulties due to the extended sequence lengths. In this study, we introduce a new architecture, multi-frequency LSTM (MF-LSTM), designed to use input of various temporal frequencies to produce sub-daily (e.g. hourly) predictions at a moderate computational cost. Building on two existing methods previously proposed by the co-authors of this study, MF-LSTM processes older inputs at coarser temporal resolutions than more recent ones. MF-LSTM gives the possibility of handling different temporal frequencies, with different numbers of input dimensions, in a single LSTM cell, enhancing the generality and simplicity of use. Our experiments, conducted on 516 basins from the CAMELS-US dataset, demonstrate that MF-LSTM retains state-of-the-art performance while offering a simpler design. Moreover, the MF-LSTM architecture reported a 5 times reduction in processing time compared to models trained exclusively on hourly data.</p>https://hess.copernicus.org/articles/29/1749/2025/hess-29-1749-2025.pdf
spellingShingle E. Acuña Espinoza
F. Kratzert
D. Klotz
D. Klotz
M. Gauch
M. Álvarez Chaves
R. Loritz
U. Ehret
Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell
Hydrology and Earth System Sciences
title Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell
title_full Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell
title_fullStr Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell
title_full_unstemmed Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell
title_short Technical note: An approach for handling multiple temporal frequencies with different input dimensions using a single LSTM cell
title_sort technical note an approach for handling multiple temporal frequencies with different input dimensions using a single lstm cell
url https://hess.copernicus.org/articles/29/1749/2025/hess-29-1749-2025.pdf
work_keys_str_mv AT eacunaespinoza technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT fkratzert technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT dklotz technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT dklotz technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT mgauch technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT malvarezchaves technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT rloritz technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell
AT uehret technicalnoteanapproachforhandlingmultipletemporalfrequencieswithdifferentinputdimensionsusingasinglelstmcell