A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates
In the current research, gene expression programming (GEP) was applied to model reference evapotranspiration (ETo) in 18 regions of Iran with limited meteorological data. Initially, a genetic algorithm (GA) was employed to detect the most important variables for estimating ETo among mean temperature...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-06-01
|
Series: | Atmosphere |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4433/10/6/311 |
_version_ | 1811264577888845824 |
---|---|
author | Mohammad Valipour Mohammad Ali Gholami Sefidkouhi Mahmoud Raeini-Sarjaz Sandra M. Guzman |
author_facet | Mohammad Valipour Mohammad Ali Gholami Sefidkouhi Mahmoud Raeini-Sarjaz Sandra M. Guzman |
author_sort | Mohammad Valipour |
collection | DOAJ |
description | In the current research, gene expression programming (GEP) was applied to model reference evapotranspiration (ETo) in 18 regions of Iran with limited meteorological data. Initially, a genetic algorithm (GA) was employed to detect the most important variables for estimating ETo among mean temperature (Tmean), maximum temperature (Tmax), minimum temperature (Tmin), relative humidity (RH), sunshine (n), and wind speed (WS). The results indicated that a coupled model containing the Tmean and WS can predict ETo accurately (RMSE = 0.3263 mm day<sup>−1</sup>) for arid, semiarid, and Mediterranean climates. Therefore, this model was adjusted using the GEP for all 18 synoptic stations. Under very humid climates, it is recommended to use a temperature-based GEP model versus wind speed-based GEP model. The optimal and lowest performance of the GEP belonged to Shahrekord (SK), RMSE = 0.0650 mm day<sup>−1</sup>, and Kerman (KE), RMSE = 0.4177 mm day<sup>−1</sup>, respectively. This research shows that the GEP is a robust tool to model ETo in semiarid and Mediterranean climates (R<sup>2</sup> > 0.80). However, GEP is recommended to be used cautiously under very humid climates and some of arid regions (R<sup>2</sup> < 0.50) due to its poor performance under such extreme conditions. |
first_indexed | 2024-04-12T20:06:28Z |
format | Article |
id | doaj.art-6806cabcd3094854a79afe6a6dc0523a |
institution | Directory Open Access Journal |
issn | 2073-4433 |
language | English |
last_indexed | 2024-04-12T20:06:28Z |
publishDate | 2019-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Atmosphere |
spelling | doaj.art-6806cabcd3094854a79afe6a6dc0523a2022-12-22T03:18:23ZengMDPI AGAtmosphere2073-44332019-06-0110631110.3390/atmos10060311atmos10060311A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various ClimatesMohammad Valipour0Mohammad Ali Gholami Sefidkouhi1Mahmoud Raeini-Sarjaz2Sandra M. Guzman3Department of Agricultural and Biological Engineering, Indian River Research and Education Center, University of Florida, Fort Pierce, FL 34945, USADepartment of Water Engineering, Sari Agricultural Sciences and Natural Resources University, Sari, IranDepartment of Water Engineering, Sari Agricultural Sciences and Natural Resources University, Sari, IranDepartment of Agricultural and Biological Engineering, Indian River Research and Education Center, University of Florida, Fort Pierce, FL 34945, USAIn the current research, gene expression programming (GEP) was applied to model reference evapotranspiration (ETo) in 18 regions of Iran with limited meteorological data. Initially, a genetic algorithm (GA) was employed to detect the most important variables for estimating ETo among mean temperature (Tmean), maximum temperature (Tmax), minimum temperature (Tmin), relative humidity (RH), sunshine (n), and wind speed (WS). The results indicated that a coupled model containing the Tmean and WS can predict ETo accurately (RMSE = 0.3263 mm day<sup>−1</sup>) for arid, semiarid, and Mediterranean climates. Therefore, this model was adjusted using the GEP for all 18 synoptic stations. Under very humid climates, it is recommended to use a temperature-based GEP model versus wind speed-based GEP model. The optimal and lowest performance of the GEP belonged to Shahrekord (SK), RMSE = 0.0650 mm day<sup>−1</sup>, and Kerman (KE), RMSE = 0.4177 mm day<sup>−1</sup>, respectively. This research shows that the GEP is a robust tool to model ETo in semiarid and Mediterranean climates (R<sup>2</sup> > 0.80). However, GEP is recommended to be used cautiously under very humid climates and some of arid regions (R<sup>2</sup> < 0.50) due to its poor performance under such extreme conditions.https://www.mdpi.com/2073-4433/10/6/311machine learningcrop water requirementIranhydrological extremesuncertaintyweather parameters |
spellingShingle | Mohammad Valipour Mohammad Ali Gholami Sefidkouhi Mahmoud Raeini-Sarjaz Sandra M. Guzman A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates Atmosphere machine learning crop water requirement Iran hydrological extremes uncertainty weather parameters |
title | A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates |
title_full | A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates |
title_fullStr | A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates |
title_full_unstemmed | A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates |
title_short | A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates |
title_sort | hybrid data driven machine learning technique for evapotranspiration modeling in various climates |
topic | machine learning crop water requirement Iran hydrological extremes uncertainty weather parameters |
url | https://www.mdpi.com/2073-4433/10/6/311 |
work_keys_str_mv | AT mohammadvalipour ahybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT mohammadaligholamisefidkouhi ahybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT mahmoudraeinisarjaz ahybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT sandramguzman ahybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT mohammadvalipour hybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT mohammadaligholamisefidkouhi hybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT mahmoudraeinisarjaz hybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates AT sandramguzman hybriddatadrivenmachinelearningtechniqueforevapotranspirationmodelinginvariousclimates |