Next Article in Journal
An Autonomous Device for Solar Hydrogen Production from Sea Water
Next Article in Special Issue
Real-Time Flood Warning System Application
Previous Article in Journal
Remote Analysis of the Chlorophyll-a Concentration Using Sentinel-2 MSI Images in a Semiarid Environment in Northeastern Brazil
Previous Article in Special Issue
Hydraulic Numerical Simulations of La Sabana River Floodplain, Mexico, as a Tool for a Flood Terrain Response Analysis
Article

River Stage Modeling with a Deep Neural Network Using Long-Term Rainfall Time Series as Input Data: Application to the Shimanto-River Watershed

1
Environmental and Mathematical Sciences Course, Kochi University of Technology, Kochi 782-8502, Japan
2
Kochi University of Technology, Kochi 782-8502, Japan
3
School of Environmental Science and Engineering, Kochi University of Technology, Kochi 782-8502, Japan
*
Author to whom correspondence should be addressed.
Emeritus Professor.
Academic Editors: Ray-Shyan Wu and Dong-Sin Shih
Water 2022, 14(3), 452; https://doi.org/10.3390/w14030452
Received: 13 December 2021 / Revised: 20 January 2022 / Accepted: 27 January 2022 / Published: 2 February 2022
The increasing frequency of devastating floods from heavy rainfall—associated with climate change—has made river stage prediction more important. For steep, forest-covered mountainous watersheds, deep-learning models may improve prediction of river stages from rainfall. Here we use the framework of multilayer perceptron (MLP) neural networks to develop such a river stage model. The MLP is constructed for the Shimanto river, which lies in southwestern Japan under a mild, rain-heavy climate. Our input for stage estimation, as well as prediction, is a long-term rainfall time series. With a one-year time series of rainfall, the model estimates the stage with RMSE less than 67 cm for about 10 m of stage peaks, as well as accurately simulating stage-time fluctuations. Furthermore, the forecast model can predict the stage without rainfall forecasts up to three hours ahead. To estimate the base flow stages as well as flood peaks with high precision, we found that the rainfall time series should be at least one year. This indicates that the use of a long rainfall time series enables one to model the contributions of ground water and evaporation. Given that the delay between the arrival time of rainfall at a rain-gauge to the outlet change is well-simulated, the physical concepts of runoff appear to be soundly embedded in the MLP. View Full-Text
Keywords: flood runoff; deep neural network; river stage; precipitation; visualization; data-driven modeling flood runoff; deep neural network; river stage; precipitation; visualization; data-driven modeling
Show Figures

Figure 1

MDPI and ACS Style

Wakatsuki, Y.; Nakane, H.; Hashino, T. River Stage Modeling with a Deep Neural Network Using Long-Term Rainfall Time Series as Input Data: Application to the Shimanto-River Watershed. Water 2022, 14, 452. https://doi.org/10.3390/w14030452

AMA Style

Wakatsuki Y, Nakane H, Hashino T. River Stage Modeling with a Deep Neural Network Using Long-Term Rainfall Time Series as Input Data: Application to the Shimanto-River Watershed. Water. 2022; 14(3):452. https://doi.org/10.3390/w14030452

Chicago/Turabian Style

Wakatsuki, Yuki, Hideaki Nakane, and Tempei Hashino. 2022. "River Stage Modeling with a Deep Neural Network Using Long-Term Rainfall Time Series as Input Data: Application to the Shimanto-River Watershed" Water 14, no. 3: 452. https://doi.org/10.3390/w14030452

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