New double decomposition deep learning methods for river water level forecasting
Article
Article Title | New double decomposition deep learning methods for river water level forecasting |
---|---|
ERA Journal ID | 3551 |
Article Category | Article |
Authors | Ahmed, A. A. Masrur (Author), Deo, Ravinesh C. (Author), Ghahramani, Afshin (Author), Feng, Qi (Author), Raj, Nawin (Author), Yin, Zhenliang (Author) and Yang, Linshan (Author) |
Journal Title | Science of the Total Environment |
Journal Citation | 831, pp. 1-21 |
Article Number | 154722 |
Number of Pages | 21 |
Year | 2022 |
Publisher | Elsevier |
Place of Publication | Netherlands |
ISSN | 0048-9697 |
1879-1026 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.scitotenv.2022.154722 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0048969722018150 |
Abstract | Forecasting river water levels or streamflow water levels (SWL) is vital to optimising the practical and sustainable use of available water resources. We propose a new deep learning hybrid model for SWL forecasting using convolutional neural networks (CNN), bi-directional long-short term memory (BiLSTM), and ant colony optimisation (ACO) with a two-phase decomposition approach at the 7-day, 14-day, and 28-day forecast horizons. The newly developed CBILSTM method is coupled with complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and variational mode decomposition (VMD) methods to extract the most significant features within predictor variables to build a hybrid CVMD-CBiLSTM model. We integrate three distinct datasets (satellite-derived, climate mode indices, and ground-based meteorological observations) to improve the forecasting capability of the CVMD-CBiLSTM model, applied at nineteen different gauging stations in the Australian Murray River system. This proposed model returns a significantly accurate performance with ~98% of all prediction errors within less than ±0.020 m and a low relative root mean square of ~0.08%, demonstrating its superiority over several benchmark models. The results show that using the new hybrid deep learning algorithm with ACO feature selection can significantly improve the accuracy of forecasted river water levels, and therefore, the method is attractive for adopting remote sensing data to the model ground-based river flow for strategic water savings planning initiatives and dealing with climate change-induced extreme events such as drought events. |
Keywords | River water level; Satellite data; Climate indices; Deep hybrid learning; Feature extraction; Feature decomposition; Murray River |
ANZSRC Field of Research 2020 | 460207. Modelling and simulation |
370704. Surface water hydrology | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | School of Mathematics, Physics and Computing |
Centre for Sustainable Agricultural Systems | |
Chinese Academy of Sciences, China | |
Institution of Origin | University of Southern Queensland |
Funding source | Grant ID USQ-CAS Postgraduate Research Scholarship |
https://research.usq.edu.au/item/q758y/new-double-decomposition-deep-learning-methods-for-river-water-level-forecasting
159
total views3
total downloads4
views this month0
downloads this month