Hybrid deep learning method for a week-ahead evapotranspiration forecasting
Article
Article Title | Hybrid deep learning method for a week-ahead evapotranspiration forecasting |
---|---|
ERA Journal ID | 864 |
Article Category | Article |
Authors | Ahmed, A. A. Masrur (Author), Deo, Ravinesh C. (Author), Feng, Qi (Author), Ghahramani, Afshin (Author), Raj, Nawin (Author), Yin, Zhenliang (Author) and Yang, Linshan (Author) |
Journal Title | Stochastic Environmental Research and Risk Assessment |
Journal Citation | 36 (3), pp. 831-849 |
Number of Pages | 19 |
Year | 2022 |
Publisher | Springer |
Place of Publication | Germany |
ISSN | 1436-3240 |
1436-3259 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/s00477-021-02078-x |
Web Address (URL) | https://link.springer.com/article/10.1007/s00477-021-02078-x |
Abstract | Reference crop evapotranspiration (ETo) is an integral hydrological factor in soil–plant-atmospheric water balance studies and the management of drought events. This paper proposes a new hybrid-deep learning approach, combining convolutional neural network (CNN) and gated recurrent unit (GRU) along with Ant Colony Optimization (ACO), for a multi-step (week 1 to 4) daily-ETo forecast. The method also assimilates a comprehensive dataset with 52 diverse predictors, i.e., satellite-derived moderate resolution imaging spectroradiometer, ground-based datasets from scientific information for landowners and synoptic-scale climate indices. To develop a vigorous CNN-GRU model, a feature selection stage entails the ant colony optimization method implemented to improve the ETo forecast model for the three selected sites in Australian Murray Darling Basin. The results demonstrate excellent forecasting capability of the hybrid CNN-GRU model against the counterpart benchmark models, evidenced by a relatively small mean absolute error and high efficiency. Overall, this study shows that the proposed hybrid CNN-GRU model successfully apprehends the complex and non-linear relationships between predictor variables and the daily ETo. |
Keywords | convolutional neural network; gated recurrent unit; hybrid-deep learning; ETo forecasting |
ANZSRC Field of Research 2020 | 460207. Modelling and simulation |
410404. Environmental management | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | School of Sciences |
Chinese Academy of Sciences, China | |
Centre for Sustainable Agricultural Systems | |
Institution of Origin | University of Southern Queensland |
Funding source | Grant ID USQ-CAS Postgraduate Research Scholarship |
https://research.usq.edu.au/item/q6q35/hybrid-deep-learning-method-for-a-week-ahead-evapotranspiration-forecasting
272
total views8
total downloads7
views this month0
downloads this month