Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks
This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input t...
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IWA Publishing
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/f36464a284db4bdab36e3713acd52fd7 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:f36464a284db4bdab36e3713acd52fd7 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:f36464a284db4bdab36e3713acd52fd72021-11-23T18:48:47ZMulti-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks1464-71411465-173410.2166/hydro.2021.095https://doaj.org/article/f36464a284db4bdab36e3713acd52fd72021-11-01T00:00:00Zhttp://jh.iwaponline.com/content/23/6/1312https://doaj.org/toc/1464-7141https://doaj.org/toc/1465-1734This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other concatenates the coarse and fine temporal resolutions of the input time-series data over time before considering them as the input to RNN. In both approaches, first, the finer temporal resolution data are utilized to learn the fine temporal scale behavior of the target data. Then, coarser temporal resolution data are expected to capture long-duration dependencies between the input and target variables. The proposed approaches were implemented for hourly rainfall–runoff modeling at a snow-dominated watershed by employing a long short-term memory network, which is a type of RNN. Subsequently, the daily and hourly meteorological data were utilized as the input, and hourly flow discharge was considered as the target data. The results confirm that both of the proposed approaches can reduce the required computational time for the training of RNN significantly. Lastly, one of the proposed approaches improves the estimation accuracy considerably in addition to computational efficiency. HIGHLIGHTS This study proposed approaches to reduce the required computational time for RNN.; Multi-time-scale time-series data are used as input.; As a case study, rainfall–runoff modeling was targeted.; The proposed approaches significantly reduced the required computation time.; Meanwhile, one of the approaches improved the estimation accuracy, too.;Kei IshidaMasato KiyamaAli ErcanMotoki AmagasakiTongbi TuIWA Publishingarticledeep learningfine temporal resolutionlong short-term memory networkrainfall–runoff modelingtime-series modelingInformation technologyT58.5-58.64Environmental technology. Sanitary engineeringTD1-1066ENJournal of Hydroinformatics, Vol 23, Iss 6, Pp 1312-1324 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
deep learning fine temporal resolution long short-term memory network rainfall–runoff modeling time-series modeling Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066 |
| spellingShingle |
deep learning fine temporal resolution long short-term memory network rainfall–runoff modeling time-series modeling Information technology T58.5-58.64 Environmental technology. Sanitary engineering TD1-1066 Kei Ishida Masato Kiyama Ali Ercan Motoki Amagasaki Tongbi Tu Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| description |
This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other concatenates the coarse and fine temporal resolutions of the input time-series data over time before considering them as the input to RNN. In both approaches, first, the finer temporal resolution data are utilized to learn the fine temporal scale behavior of the target data. Then, coarser temporal resolution data are expected to capture long-duration dependencies between the input and target variables. The proposed approaches were implemented for hourly rainfall–runoff modeling at a snow-dominated watershed by employing a long short-term memory network, which is a type of RNN. Subsequently, the daily and hourly meteorological data were utilized as the input, and hourly flow discharge was considered as the target data. The results confirm that both of the proposed approaches can reduce the required computational time for the training of RNN significantly. Lastly, one of the proposed approaches improves the estimation accuracy considerably in addition to computational efficiency. HIGHLIGHTS
This study proposed approaches to reduce the required computational time for RNN.;
Multi-time-scale time-series data are used as input.;
As a case study, rainfall–runoff modeling was targeted.;
The proposed approaches significantly reduced the required computation time.;
Meanwhile, one of the approaches improved the estimation accuracy, too.; |
| format |
article |
| author |
Kei Ishida Masato Kiyama Ali Ercan Motoki Amagasaki Tongbi Tu |
| author_facet |
Kei Ishida Masato Kiyama Ali Ercan Motoki Amagasaki Tongbi Tu |
| author_sort |
Kei Ishida |
| title |
Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| title_short |
Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| title_full |
Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| title_fullStr |
Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| title_full_unstemmed |
Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| title_sort |
multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks |
| publisher |
IWA Publishing |
| publishDate |
2021 |
| url |
https://doaj.org/article/f36464a284db4bdab36e3713acd52fd7 |
| work_keys_str_mv |
AT keiishida multitimescaleinputapproachesforhourlyscalerainfallrunoffmodelingbasedonrecurrentneuralnetworks AT masatokiyama multitimescaleinputapproachesforhourlyscalerainfallrunoffmodelingbasedonrecurrentneuralnetworks AT aliercan multitimescaleinputapproachesforhourlyscalerainfallrunoffmodelingbasedonrecurrentneuralnetworks AT motokiamagasaki multitimescaleinputapproachesforhourlyscalerainfallrunoffmodelingbasedonrecurrentneuralnetworks AT tongbitu multitimescaleinputapproachesforhourlyscalerainfallrunoffmodelingbasedonrecurrentneuralnetworks |
| _version_ |
1718416189242212352 |