Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods
Different regression-based machine learning techniques, including support vector machine (SVM), random forest (RF), Bagged trees algorithm (BaT), and Boosting trees algorithm (BoT) were adopted for modeling daily reference evapotranspiration (ET<sub>0</sub>) in a semi-arid region (Hemren...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/19/3449 |
| _version_ | 1797447203453665280 |
|---|---|
| author | Saad Sh. Sammen Ozgur Kisi Ahmed Mohammed Sami Al-Janabi Ahmed Elbeltagi Mohammad Zounemat-Kermani |
| author_facet | Saad Sh. Sammen Ozgur Kisi Ahmed Mohammed Sami Al-Janabi Ahmed Elbeltagi Mohammad Zounemat-Kermani |
| author_sort | Saad Sh. Sammen |
| collection | DOAJ |
| description | Different regression-based machine learning techniques, including support vector machine (SVM), random forest (RF), Bagged trees algorithm (BaT), and Boosting trees algorithm (BoT) were adopted for modeling daily reference evapotranspiration (ET<sub>0</sub>) in a semi-arid region (Hemren catchment basin in Iraq). An assessment of the methods with various input combinations of climatic parameters, including solar radiation (SR), wind speed (WS), relative humidity (RH), and maximum and minimum air temperatures (Tmax and Tmin), indicated that the RF method, especially with Tmax, Tmin, Tmean, and SR inputs, provided the best accuracy in estimating daily ET<sub>0</sub> in all stations, while the SVM had the worst accuracy. This work will help water users, developers, and decision makers in water resource planning and management to achieve sustainability. |
| first_indexed | 2024-03-09T13:51:31Z |
| format | Article |
| id | doaj.art-d72a260c93214467b3b5531f3e226fb7 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T13:51:31Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-d72a260c93214467b3b5531f3e226fb72023-11-30T20:50:05ZengMDPI AGWater2073-44412023-09-011519344910.3390/w15193449Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression MethodsSaad Sh. Sammen0Ozgur Kisi1Ahmed Mohammed Sami Al-Janabi2Ahmed Elbeltagi3Mohammad Zounemat-Kermani4Department of Civil Engineering, College of Engineering, Diyala University, Baquba 32001, IraqDepartment of Civil Engineering, Technical University of Lübeck, 23562 Lübeck, GermanyDepartment of Civil Engineering, Cihan University-Erbil, Kurdistan Region, Erbil 44001, IraqAgricultural Engineering Department, Faculty of Agriculture, Mansoura University, Mansoura 35516, EgyptDepartment of Water Engineering, Shahid Bahonar University of Kerman, Kerman 93630, IranDifferent regression-based machine learning techniques, including support vector machine (SVM), random forest (RF), Bagged trees algorithm (BaT), and Boosting trees algorithm (BoT) were adopted for modeling daily reference evapotranspiration (ET<sub>0</sub>) in a semi-arid region (Hemren catchment basin in Iraq). An assessment of the methods with various input combinations of climatic parameters, including solar radiation (SR), wind speed (WS), relative humidity (RH), and maximum and minimum air temperatures (Tmax and Tmin), indicated that the RF method, especially with Tmax, Tmin, Tmean, and SR inputs, provided the best accuracy in estimating daily ET<sub>0</sub> in all stations, while the SVM had the worst accuracy. This work will help water users, developers, and decision makers in water resource planning and management to achieve sustainability.https://www.mdpi.com/2073-4441/15/19/3449climatic inputsevapotranspirationHemren catchmentmachine learningpredictionsemi-arid region |
| spellingShingle | Saad Sh. Sammen Ozgur Kisi Ahmed Mohammed Sami Al-Janabi Ahmed Elbeltagi Mohammad Zounemat-Kermani Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods Water climatic inputs evapotranspiration Hemren catchment machine learning prediction semi-arid region |
| title | Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods |
| title_full | Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods |
| title_fullStr | Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods |
| title_full_unstemmed | Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods |
| title_short | Estimation of Reference Evapotranspiration in Semi-Arid Region with Limited Climatic Inputs Using Metaheuristic Regression Methods |
| title_sort | estimation of reference evapotranspiration in semi arid region with limited climatic inputs using metaheuristic regression methods |
| topic | climatic inputs evapotranspiration Hemren catchment machine learning prediction semi-arid region |
| url | https://www.mdpi.com/2073-4441/15/19/3449 |
| work_keys_str_mv | AT saadshsammen estimationofreferenceevapotranspirationinsemiaridregionwithlimitedclimaticinputsusingmetaheuristicregressionmethods AT ozgurkisi estimationofreferenceevapotranspirationinsemiaridregionwithlimitedclimaticinputsusingmetaheuristicregressionmethods AT ahmedmohammedsamialjanabi estimationofreferenceevapotranspirationinsemiaridregionwithlimitedclimaticinputsusingmetaheuristicregressionmethods AT ahmedelbeltagi estimationofreferenceevapotranspirationinsemiaridregionwithlimitedclimaticinputsusingmetaheuristicregressionmethods AT mohammadzounematkermani estimationofreferenceevapotranspirationinsemiaridregionwithlimitedclimaticinputsusingmetaheuristicregressionmethods |