Next Article in Journal
Nitrate Removal and Woodchip Properties across a Paired Denitrifying Bioreactor Treating Centralized Agricultural Ditch Flows
Previous Article in Journal
Water Use Characteristics of Two Dominant Species in the Mega-Dunes of the Badain Jaran Desert
Article

Development and Assessment of Water-Level Prediction Models for Small Reservoirs Using a Deep Learning Algorithm

Department of Environmental Management, Faculty of Agriculture, Kindai University, 3327-204 Nakamachi, Nara 631-8505, Japan
*
Authors to whom correspondence should be addressed.
Academic Editor: Xiaohu Wen
Water 2022, 14(1), 55; https://doi.org/10.3390/w14010055
Received: 29 November 2021 / Revised: 22 December 2021 / Accepted: 23 December 2021 / Published: 28 December 2021
(This article belongs to the Section Urban Water Management)
In this study, we aimed to develop and assess a hydrological model using a deep learning algorithm for improved water management. Single-output long short-term memory (LSTM SO) and encoder-decoder long short-term memory (LSTM ED) models were developed, and their performances were compared using different input variables. We used water-level and rainfall data from 2018 to 2020 in the Takayama Reservoir (Nara Prefecture, Japan) to train, test, and assess both models. The root-mean-squared error and Nash–Sutcliffe efficiency were estimated to compare the model performances. The results showed that the LSTM ED model had better accuracy. Analysis of water levels and water-level changes presented better results than the analysis of water levels. However, the accuracy of the model was significantly lower when predicting water levels outside the range of the training datasets. Within this range, the developed model could be used for water management to reduce the risk of downstream flooding, while ensuring sufficient water storage for irrigation, because of its ability to determine an appropriate amount of water for release from the reservoir before rainfall events. View Full-Text
Keywords: reservoir-water level; long short-term memory; encoder-decoder; flood control; irrigation; water-management tool reservoir-water level; long short-term memory; encoder-decoder; flood control; irrigation; water-management tool
Show Figures

Figure 1

MDPI and ACS Style

Kusudo, T.; Yamamoto, A.; Kimura, M.; Matsuno, Y. Development and Assessment of Water-Level Prediction Models for Small Reservoirs Using a Deep Learning Algorithm. Water 2022, 14, 55. https://doi.org/10.3390/w14010055

AMA Style

Kusudo T, Yamamoto A, Kimura M, Matsuno Y. Development and Assessment of Water-Level Prediction Models for Small Reservoirs Using a Deep Learning Algorithm. Water. 2022; 14(1):55. https://doi.org/10.3390/w14010055

Chicago/Turabian Style

Kusudo, Tsumugu, Atsushi Yamamoto, Masaomi Kimura, and Yutaka Matsuno. 2022. "Development and Assessment of Water-Level Prediction Models for Small Reservoirs Using a Deep Learning Algorithm" Water 14, no. 1: 55. https://doi.org/10.3390/w14010055

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop