Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration
Abstract This study applies three methods, Gene Expression Programming (GEP), M5 tree (M5T) model and optimized Artificial Neural Network by Genetic Algorithm (ANN-GA) for estimation of reference evapotranspiration in Ahvaz and Dezful in the southwest of Iran. Comparison between results of the FAO P...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-02-01
|
| Series: | Applied Water Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13201-023-01895-5 |
| _version_ | 1797863863515873280 |
|---|---|
| author | Arash Adib Seyed Shahab Oddin Kalantarzadeh Mohammad Mahmoudian Shoushtari Morteza Lotfirad Ali Liaghat Masoud Oulapour |
| author_facet | Arash Adib Seyed Shahab Oddin Kalantarzadeh Mohammad Mahmoudian Shoushtari Morteza Lotfirad Ali Liaghat Masoud Oulapour |
| author_sort | Arash Adib |
| collection | DOAJ |
| description | Abstract This study applies three methods, Gene Expression Programming (GEP), M5 tree (M5T) model and optimized Artificial Neural Network by Genetic Algorithm (ANN-GA) for estimation of reference evapotranspiration in Ahvaz and Dezful in the southwest of Iran. Comparison between results of the FAO Penman-Monteith (FPM) method and the mentioned three methods shows that ANN-GA with the Levenberg-Marquardt training method is the best method and the M5T model is the second appropriate method for estimation of reference evapotranspiration. In Ahvaz, R 2 and RMSE of ANN-GA method are 0.996, 0.184 mm/day. For M5T method, these values are 0.997 and 0259 mm/day, and for GEP method, they are 0.979 and 0.521 mm/day. In Dezful, R 2 and RMSE of ANN-GA method are 0.994, 0.235 mm/day. For M5T method, these values are 0.992 and 0265 mm/day, and for GEP method, they are 0.963 and 0.544 mm/day. In addition, sensitivity analysis shows that the maximum temperature is the most effective parameter, and the wind speed is second effective parameter. In Dezful, the effect of the maximum temperature is more than those of Ahvaz but the effect of wind speed is less than those of Ahvaz. Because Ahvaz is more flatter than Dezful (the movement of wind in Ahvaz is freer than those of Dezful). The third effective meteorological parameter is the average relative humidity in Ahvaz and the sunny hours in Dezful. The reason for this subject is the less distant of Ahvaz from the Persian Gulf (it is source of moisture). |
| first_indexed | 2024-04-09T22:43:39Z |
| format | Article |
| id | doaj.art-40af08c50b694238bc7f1e385776590b |
| institution | Directory Open Access Journal |
| issn | 2190-5487 2190-5495 |
| language | English |
| last_indexed | 2024-04-09T22:43:39Z |
| publishDate | 2023-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Water Science |
| spelling | doaj.art-40af08c50b694238bc7f1e385776590b2023-03-22T12:01:36ZengSpringerOpenApplied Water Science2190-54872190-54952023-02-0113311710.1007/s13201-023-01895-5Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspirationArash Adib0Seyed Shahab Oddin Kalantarzadeh1Mohammad Mahmoudian Shoushtari2Morteza Lotfirad3Ali Liaghat4Masoud Oulapour5Civil Engineering and Architecture Faculty, Shahid Chamran University of AhvazCivil Engineering and Architecture Faculty, Shahid Chamran University of AhvazCivil Engineering and Architecture Faculty, Shahid Chamran University of AhvazCivil Engineering and Architecture Faculty, Shahid Chamran University of AhvazCivil Engineering Department, Engineering Faculty, Shiraz Branch, Islamic Azad UniversityCivil Engineering and Architecture Faculty, Shahid Chamran University of AhvazAbstract This study applies three methods, Gene Expression Programming (GEP), M5 tree (M5T) model and optimized Artificial Neural Network by Genetic Algorithm (ANN-GA) for estimation of reference evapotranspiration in Ahvaz and Dezful in the southwest of Iran. Comparison between results of the FAO Penman-Monteith (FPM) method and the mentioned three methods shows that ANN-GA with the Levenberg-Marquardt training method is the best method and the M5T model is the second appropriate method for estimation of reference evapotranspiration. In Ahvaz, R 2 and RMSE of ANN-GA method are 0.996, 0.184 mm/day. For M5T method, these values are 0.997 and 0259 mm/day, and for GEP method, they are 0.979 and 0.521 mm/day. In Dezful, R 2 and RMSE of ANN-GA method are 0.994, 0.235 mm/day. For M5T method, these values are 0.992 and 0265 mm/day, and for GEP method, they are 0.963 and 0.544 mm/day. In addition, sensitivity analysis shows that the maximum temperature is the most effective parameter, and the wind speed is second effective parameter. In Dezful, the effect of the maximum temperature is more than those of Ahvaz but the effect of wind speed is less than those of Ahvaz. Because Ahvaz is more flatter than Dezful (the movement of wind in Ahvaz is freer than those of Dezful). The third effective meteorological parameter is the average relative humidity in Ahvaz and the sunny hours in Dezful. The reason for this subject is the less distant of Ahvaz from the Persian Gulf (it is source of moisture).https://doi.org/10.1007/s13201-023-01895-5ANN-GAGEPM5T modelReference evapotranspirationThe FAO Penman-Monteith method |
| spellingShingle | Arash Adib Seyed Shahab Oddin Kalantarzadeh Mohammad Mahmoudian Shoushtari Morteza Lotfirad Ali Liaghat Masoud Oulapour Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration Applied Water Science ANN-GA GEP M5T model Reference evapotranspiration The FAO Penman-Monteith method |
| title | Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration |
| title_full | Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration |
| title_fullStr | Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration |
| title_full_unstemmed | Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration |
| title_short | Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration |
| title_sort | sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration |
| topic | ANN-GA GEP M5T model Reference evapotranspiration The FAO Penman-Monteith method |
| url | https://doi.org/10.1007/s13201-023-01895-5 |
| work_keys_str_mv | AT arashadib sensitiveanalysisofmeteorologicaldataandselectingappropriatemachinelearningmodelforestimationofreferenceevapotranspiration AT seyedshahaboddinkalantarzadeh sensitiveanalysisofmeteorologicaldataandselectingappropriatemachinelearningmodelforestimationofreferenceevapotranspiration AT mohammadmahmoudianshoushtari sensitiveanalysisofmeteorologicaldataandselectingappropriatemachinelearningmodelforestimationofreferenceevapotranspiration AT mortezalotfirad sensitiveanalysisofmeteorologicaldataandselectingappropriatemachinelearningmodelforestimationofreferenceevapotranspiration AT aliliaghat sensitiveanalysisofmeteorologicaldataandselectingappropriatemachinelearningmodelforestimationofreferenceevapotranspiration AT masoudoulapour sensitiveanalysisofmeteorologicaldataandselectingappropriatemachinelearningmodelforestimationofreferenceevapotranspiration |