Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models
FAO Blaney-Criddle has been generally an accepted method for estimating reference crop evapotranspiration. In this regard, it is inevitable to estimate the b-factor provided by the Food and Agriculture Organization (FAO) of the United Nations Irrigation and Drainage Paper number 24. In this study, f...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/13/10/1536 |
| _version_ | 1797475427778822144 |
|---|---|
| author | Suthira Thongkao Pakorn Ditthakit Sirimon Pinthong Nureehan Salaeh Ismail Elkhrachy Nguyen Thi Thuy Linh Quoc Bao Pham |
| author_facet | Suthira Thongkao Pakorn Ditthakit Sirimon Pinthong Nureehan Salaeh Ismail Elkhrachy Nguyen Thi Thuy Linh Quoc Bao Pham |
| author_sort | Suthira Thongkao |
| collection | DOAJ |
| description | FAO Blaney-Criddle has been generally an accepted method for estimating reference crop evapotranspiration. In this regard, it is inevitable to estimate the b-factor provided by the Food and Agriculture Organization (FAO) of the United Nations Irrigation and Drainage Paper number 24. In this study, five soft computing methods, namely random forest (RF), M5 model tree (M5), support vector regression with the polynomial function (SVR-poly), support vector regression with radial basis function kernel (SVR-rbf), and random tree (RT), were adapted to estimate the b-factor. And Their performances were also compared. The suitable hyper-parameters for each soft computing method were investigated. Five statistical indices were deployed to evaluate their performance, i.e., the coefficient of determination (<i>r</i><sup>2</sup>), the mean absolute relative error (MARE), the maximum absolute relative error (MXARE), the standard deviation of the absolute relative error (DEV), and the number of samples with an error greater than 2% (NE > 2%). Findings reveal that SVR-rbf gave the highest performance among five soft computing models, followed by the M5, RF, SVR-poly, and RT. The M5 also derived a new explicit equation for b estimation. SVR-rbf provided a bit lower efficacy than the radial basis function network but outperformed the regression equations. Models’ Applicability for estimating monthly reference evapotranspiration <i>(ETo)</i> was demonstrated. |
| first_indexed | 2024-03-09T20:44:55Z |
| format | Article |
| id | doaj.art-a3471be348524ce7af3dc0f45ee161d9 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-09T20:44:55Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-a3471be348524ce7af3dc0f45ee161d92023-11-23T22:49:40ZengMDPI AGAtmosphere2073-44332022-09-011310153610.3390/atmos13101536Estimating FAO Blaney-Criddle b-Factor Using Soft Computing ModelsSuthira Thongkao0Pakorn Ditthakit1Sirimon Pinthong2Nureehan Salaeh3Ismail Elkhrachy4Nguyen Thi Thuy Linh5Quoc Bao Pham6Center of Excellence in Sustainable Disaster Management (CESDM), Walailak University, 222, Thaiburi, Thasala, Nakhon Si Thammarat 80160, ThailandCenter of Excellence in Sustainable Disaster Management (CESDM), Walailak University, 222, Thaiburi, Thasala, Nakhon Si Thammarat 80160, ThailandCenter of Excellence in Sustainable Disaster Management (CESDM), Walailak University, 222, Thaiburi, Thasala, Nakhon Si Thammarat 80160, ThailandCenter of Excellence in Sustainable Disaster Management (CESDM), Walailak University, 222, Thaiburi, Thasala, Nakhon Si Thammarat 80160, ThailandCivil Engineering Department, College of Engineering, Najran University, King Abdulaziz Road, P.O. Box 1988, Najran 66291, Saudi ArabiaInstitute of Applied Technology, Thu Dau Mot University, Thu Dau Mot 75000, Binh Duong, VietnamInstitute of Applied Technology, Thu Dau Mot University, Thu Dau Mot 75000, Binh Duong, VietnamFAO Blaney-Criddle has been generally an accepted method for estimating reference crop evapotranspiration. In this regard, it is inevitable to estimate the b-factor provided by the Food and Agriculture Organization (FAO) of the United Nations Irrigation and Drainage Paper number 24. In this study, five soft computing methods, namely random forest (RF), M5 model tree (M5), support vector regression with the polynomial function (SVR-poly), support vector regression with radial basis function kernel (SVR-rbf), and random tree (RT), were adapted to estimate the b-factor. And Their performances were also compared. The suitable hyper-parameters for each soft computing method were investigated. Five statistical indices were deployed to evaluate their performance, i.e., the coefficient of determination (<i>r</i><sup>2</sup>), the mean absolute relative error (MARE), the maximum absolute relative error (MXARE), the standard deviation of the absolute relative error (DEV), and the number of samples with an error greater than 2% (NE > 2%). Findings reveal that SVR-rbf gave the highest performance among five soft computing models, followed by the M5, RF, SVR-poly, and RT. The M5 also derived a new explicit equation for b estimation. SVR-rbf provided a bit lower efficacy than the radial basis function network but outperformed the regression equations. Models’ Applicability for estimating monthly reference evapotranspiration <i>(ETo)</i> was demonstrated.https://www.mdpi.com/2073-4433/13/10/1536Blaney-Criddle b-Factormachine learningM5 model treerandom forestrandom treereference crop evapotranspiration |
| spellingShingle | Suthira Thongkao Pakorn Ditthakit Sirimon Pinthong Nureehan Salaeh Ismail Elkhrachy Nguyen Thi Thuy Linh Quoc Bao Pham Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models Atmosphere Blaney-Criddle b-Factor machine learning M5 model tree random forest random tree reference crop evapotranspiration |
| title | Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models |
| title_full | Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models |
| title_fullStr | Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models |
| title_full_unstemmed | Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models |
| title_short | Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models |
| title_sort | estimating fao blaney criddle b factor using soft computing models |
| topic | Blaney-Criddle b-Factor machine learning M5 model tree random forest random tree reference crop evapotranspiration |
| url | https://www.mdpi.com/2073-4433/13/10/1536 |
| work_keys_str_mv | AT suthirathongkao estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels AT pakornditthakit estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels AT sirimonpinthong estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels AT nureehansalaeh estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels AT ismailelkhrachy estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels AT nguyenthithuylinh estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels AT quocbaopham estimatingfaoblaneycriddlebfactorusingsoftcomputingmodels |