Predicting river water height using deep learning-based features
Issued Date
2022-12-01
Resource Type
eISSN
24059595
Scopus ID
2-s2.0-85127880802
Journal Title
ICT Express
Volume
8
Issue
4
Start Page
588
End Page
594
Rights Holder(s)
SCOPUS
Bibliographic Citation
ICT Express Vol.8 No.4 (2022) , 588-594
Suggested Citation
Borwarnginn P., Haga J.H., Kusakunniran W. Predicting river water height using deep learning-based features. ICT Express Vol.8 No.4 (2022) , 588-594. 594. doi:10.1016/j.icte.2022.03.012 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/84236
Title
Predicting river water height using deep learning-based features
Author(s)
Author's Affiliation
Other Contributor(s)
Abstract
The paper presents the river height prediction model using real-world historical sensor data such as rainfall, cumulative rainfall, and river water heights. The study evaluates using a Support Vector Regression, a Long Short-Term Memory, and a combination of a Long Short-Term Memory as the feature extraction and a support vector regression. Through experiments, various future predictions are tested, including a few hours or a day. As expected, RNN achieved the lowest error, but it could not capture rapid changes in river height levels. In comparison, the LSTM-SVR can better represent rapid transient changes in the data by using nonlinear kernels.