Modeling daily reference evapotranspiration via a novel approach based on support vector regression coupled with whale optimization algorithm
(2020) In Agricultural Water Management 237.- Abstract
In achieving water resource management goals such as irrigation scheduling, an accurate estimate of reference evapotranspiration (ET0) is critical. Support vector regression (SVR) was applied to the modeling of daily ET0 at three meteorological stations in Iran subject to different climates: Isfahan (arid), Urmia (semi-arid), and Yazd (hyper-arid). Different pre-processing approaches [relief (RL), random forests (RF), principal component analysis (PCA), and Pearson's correlation (COR)] served to determine the SVR's optimal input combinations. While these approaches introduced different inputs to the SVR models, those drawn upon by the RF approach (i.e., RF-SVR) generated better results than other approaches. Models... (More)
In achieving water resource management goals such as irrigation scheduling, an accurate estimate of reference evapotranspiration (ET0) is critical. Support vector regression (SVR) was applied to the modeling of daily ET0 at three meteorological stations in Iran subject to different climates: Isfahan (arid), Urmia (semi-arid), and Yazd (hyper-arid). Different pre-processing approaches [relief (RL), random forests (RF), principal component analysis (PCA), and Pearson's correlation (COR)] served to determine the SVR's optimal input combinations. While these approaches introduced different inputs to the SVR models, those drawn upon by the RF approach (i.e., RF-SVR) generated better results than other approaches. Models performance was evaluated using the root mean square error (RMSE), normalized RMSE (NRMSE), mean absolute error (MAE), coefficient of determination (R2), and the Nash-Sutcliffe efficiency (E). A novel hybrid model, coupling SVR with a whale optimization algorithm (WOA), was also developed and applied to daily ET0 modeling. The hybrid models outperformed the SVR-only models, with the hybrid RF-SVR-WOA model having the best performance.
(Less)
- author
- Mohammadi, Babak LU and Mehdizadeh, Saeid
- publishing date
- 2020-07-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Hybrid model, Pre-processing, Reference evapotranspiration, Support vector regression, Whale optimization algorithm
- in
- Agricultural Water Management
- volume
- 237
- article number
- 106145
- publisher
- Elsevier
- external identifiers
-
- scopus:85082021395
- ISSN
- 0378-3774
- DOI
- 10.1016/j.agwat.2020.106145
- language
- English
- LU publication?
- no
- id
- 56cdb9f7-787d-4657-8795-0e8e7e74ce95
- date added to LUP
- 2020-12-30 05:23:22
- date last changed
- 2022-04-26 22:52:50
@article{56cdb9f7-787d-4657-8795-0e8e7e74ce95, abstract = {{<p>In achieving water resource management goals such as irrigation scheduling, an accurate estimate of reference evapotranspiration (ET<sub>0</sub>) is critical. Support vector regression (SVR) was applied to the modeling of daily ET<sub>0</sub> at three meteorological stations in Iran subject to different climates: Isfahan (arid), Urmia (semi-arid), and Yazd (hyper-arid). Different pre-processing approaches [relief (RL), random forests (RF), principal component analysis (PCA), and Pearson's correlation (COR)] served to determine the SVR's optimal input combinations. While these approaches introduced different inputs to the SVR models, those drawn upon by the RF approach (i.e., RF-SVR) generated better results than other approaches. Models performance was evaluated using the root mean square error (RMSE), normalized RMSE (NRMSE), mean absolute error (MAE), coefficient of determination (R<sup>2</sup>), and the Nash-Sutcliffe efficiency (E). A novel hybrid model, coupling SVR with a whale optimization algorithm (WOA), was also developed and applied to daily ET<sub>0</sub> modeling. The hybrid models outperformed the SVR-only models, with the hybrid RF-SVR-WOA model having the best performance.</p>}}, author = {{Mohammadi, Babak and Mehdizadeh, Saeid}}, issn = {{0378-3774}}, keywords = {{Hybrid model; Pre-processing; Reference evapotranspiration; Support vector regression; Whale optimization algorithm}}, language = {{eng}}, month = {{07}}, publisher = {{Elsevier}}, series = {{Agricultural Water Management}}, title = {{Modeling daily reference evapotranspiration via a novel approach based on support vector regression coupled with whale optimization algorithm}}, url = {{http://dx.doi.org/10.1016/j.agwat.2020.106145}}, doi = {{10.1016/j.agwat.2020.106145}}, volume = {{237}}, year = {{2020}}, }