Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis
Evaporation is a very important process; it is one of the most critical factors in agricultural, hydrological, and meteorological studies. Due to the interactions of multiple climatic factors, evaporation is considered as a complex and nonlinear phenomenon to model. Thus, machine learning methods ha...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/11/1/66 |
| _version_ | 1818926182619414528 |
|---|---|
| author | Sevda Shabani Saeed Samadianfard Mohammad Taghi Sattari Amir Mosavi Shahaboddin Shamshirband Tibor Kmet Annamária R. Várkonyi-Kóczy |
| author_facet | Sevda Shabani Saeed Samadianfard Mohammad Taghi Sattari Amir Mosavi Shahaboddin Shamshirband Tibor Kmet Annamária R. Várkonyi-Kóczy |
| author_sort | Sevda Shabani |
| collection | DOAJ |
| description | Evaporation is a very important process; it is one of the most critical factors in agricultural, hydrological, and meteorological studies. Due to the interactions of multiple climatic factors, evaporation is considered as a complex and nonlinear phenomenon to model. Thus, machine learning methods have gained popularity in this realm. In the present study, four machine learning methods of Gaussian Process Regression (GPR), K-Nearest Neighbors (KNN), Random Forest (RF) and Support Vector Regression (SVR) were used to predict the pan evaporation (PE). Meteorological data including PE, temperature (T), relative humidity (RH), wind speed (W), and sunny hours (S) collected from 2011 through 2017. The accuracy of the studied methods was determined using the statistical indices of Root Mean Squared Error (RMSE), correlation coefficient (R) and Mean Absolute Error (MAE). Furthermore, the Taylor charts utilized for evaluating the accuracy of the mentioned models. The results of this study showed that at Gonbad-e Kavus, Gorgan and Bandar Torkman stations, GPR with RMSE of 1.521 mm/day, 1.244 mm/day, and 1.254 mm/day, KNN with RMSE of 1.991 mm/day, 1.775 mm/day, and 1.577 mm/day, RF with RMSE of 1.614 mm/day, 1.337 mm/day, and 1.316 mm/day, and SVR with RMSE of 1.55 mm/day, 1.262 mm/day, and 1.275 mm/day had more appropriate performances in estimating PE values. It was found that GPR for Gonbad-e Kavus Station with input parameters of T, W and S and GPR for Gorgan and Bandar Torkmen stations with input parameters of T, RH, W and S had the most accurate predictions and were proposed for precise estimation of PE. The findings of the current study indicated that the PE values may be accurately estimated with few easily measured meteorological parameters. |
| first_indexed | 2024-12-20T02:53:03Z |
| format | Article |
| id | doaj.art-bb7037dd99904a589c97ff4091990f5b |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-12-20T02:53:03Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-bb7037dd99904a589c97ff4091990f5b2022-12-21T19:55:59ZengMDPI AGAtmosphere2073-44332020-01-011116610.3390/atmos11010066atmos11010066Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative AnalysisSevda Shabani0Saeed Samadianfard1Mohammad Taghi Sattari2Amir Mosavi3Shahaboddin Shamshirband4Tibor Kmet5Annamária R. Várkonyi-Kóczy6Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz 51666, IranDepartment of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz 51666, IranDepartment of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz 51666, IranInstitute of Automation, Kalman Kando Faculty of Electrical Engineering, Obuda University, 1034 Budapest, HungaryDepartment for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Viet NamDepartment of Mathematics and Informatics, J. Selye University, 94501 Komarno, SlovakiaInstitute of Automation, Kalman Kando Faculty of Electrical Engineering, Obuda University, 1034 Budapest, HungaryEvaporation is a very important process; it is one of the most critical factors in agricultural, hydrological, and meteorological studies. Due to the interactions of multiple climatic factors, evaporation is considered as a complex and nonlinear phenomenon to model. Thus, machine learning methods have gained popularity in this realm. In the present study, four machine learning methods of Gaussian Process Regression (GPR), K-Nearest Neighbors (KNN), Random Forest (RF) and Support Vector Regression (SVR) were used to predict the pan evaporation (PE). Meteorological data including PE, temperature (T), relative humidity (RH), wind speed (W), and sunny hours (S) collected from 2011 through 2017. The accuracy of the studied methods was determined using the statistical indices of Root Mean Squared Error (RMSE), correlation coefficient (R) and Mean Absolute Error (MAE). Furthermore, the Taylor charts utilized for evaluating the accuracy of the mentioned models. The results of this study showed that at Gonbad-e Kavus, Gorgan and Bandar Torkman stations, GPR with RMSE of 1.521 mm/day, 1.244 mm/day, and 1.254 mm/day, KNN with RMSE of 1.991 mm/day, 1.775 mm/day, and 1.577 mm/day, RF with RMSE of 1.614 mm/day, 1.337 mm/day, and 1.316 mm/day, and SVR with RMSE of 1.55 mm/day, 1.262 mm/day, and 1.275 mm/day had more appropriate performances in estimating PE values. It was found that GPR for Gonbad-e Kavus Station with input parameters of T, W and S and GPR for Gorgan and Bandar Torkmen stations with input parameters of T, RH, W and S had the most accurate predictions and were proposed for precise estimation of PE. The findings of the current study indicated that the PE values may be accurately estimated with few easily measured meteorological parameters.https://www.mdpi.com/2073-4433/11/1/66machine learningmeteorological parameterspan evaporationadvanced statistical analysishydrological cyclebig datahydroinformaticsrandom forest (rf)support vector regression (svr) |
| spellingShingle | Sevda Shabani Saeed Samadianfard Mohammad Taghi Sattari Amir Mosavi Shahaboddin Shamshirband Tibor Kmet Annamária R. Várkonyi-Kóczy Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis Atmosphere machine learning meteorological parameters pan evaporation advanced statistical analysis hydrological cycle big data hydroinformatics random forest (rf) support vector regression (svr) |
| title | Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis |
| title_full | Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis |
| title_fullStr | Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis |
| title_full_unstemmed | Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis |
| title_short | Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis |
| title_sort | modeling pan evaporation using gaussian process regression k nearest neighbors random forest and support vector machines comparative analysis |
| topic | machine learning meteorological parameters pan evaporation advanced statistical analysis hydrological cycle big data hydroinformatics random forest (rf) support vector regression (svr) |
| url | https://www.mdpi.com/2073-4433/11/1/66 |
| work_keys_str_mv | AT sevdashabani modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis AT saeedsamadianfard modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis AT mohammadtaghisattari modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis AT amirmosavi modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis AT shahaboddinshamshirband modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis AT tiborkmet modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis AT annamariarvarkonyikoczy modelingpanevaporationusinggaussianprocessregressionknearestneighborsrandomforestandsupportvectormachinescomparativeanalysis |