An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration

Mohammad Ehteram, Vijay P. Singh, Ahmad Ferdowsi, Sayed Farhad Mousavi, Saeed Farzin, Hojat Karami, Nuruol Syuhadaa Mohd, Haitham Abdulmohsin Afan, Sai Hin Lai, Ozgur Kisi, Marlinda Abdul Malek, Ali Najah Ahmed, Ahmed El-Shafie

Research output: Contribution to journalArticle

Abstract

Reference evapotranspiration (ET0) plays a fundamental role in irrigated agriculture. The objective of this study is to simulate monthly ET0 at a meteorological station in India using a new method, an improved support vector machine (SVM) based on the cuckoo algorithm (CA), which is known as SVM-CA. Maximum temperature, minimum temperature, relative humidity, wind speed and sunshine hours were selected as inputs for the models used in the simulation. The results of the simulation using SVM-CA were compared with those from experimental models, genetic programming (GP), model tree (M5T) and the adaptive neuro-fuzzy inference system (ANFIS). The achieved results demonstrate that the proposed SVM-CA model is able to simulate ET0 more accurately than the GP, M5T and ANFIS models. Two major indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), indicated that the SVM-CA outperformed the other methods with respective reductions of 5-15% and 5-17% compared with the GP model, 12-21% and 10-22% compared with the M5T model, and 7-15% and 5-18% compared with the ANFIS model, respectively. Therefore, the proposed SVM-CA model has high potential for accurate simulation of monthly ET0 values compared with the other models.

Original languageEnglish
Article numbere0217499
JournalPLoS ONE
Volume14
Issue number5
DOIs
Publication statusPublished - 01 May 2019

Fingerprint

Evapotranspiration
evapotranspiration
Support vector machines
Genetic Models
Genetic programming
Fuzzy inference
Temperature
Sunlight
Humidity
Agriculture
Support Vector Machine
support vector machines
India
Theoretical Models
Mean square error
wind speed
Atmospheric humidity
relative humidity
temperature
solar radiation

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Cite this

Ehteram, M., Singh, V. P., Ferdowsi, A., Mousavi, S. F., Farzin, S., Karami, H., ... El-Shafie, A. (2019). An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration. PLoS ONE, 14(5), [e0217499]. https://doi.org/10.1371/journal.pone.0217499
Ehteram, Mohammad ; Singh, Vijay P. ; Ferdowsi, Ahmad ; Mousavi, Sayed Farhad ; Farzin, Saeed ; Karami, Hojat ; Mohd, Nuruol Syuhadaa ; Afan, Haitham Abdulmohsin ; Lai, Sai Hin ; Kisi, Ozgur ; Abdul Malek, Marlinda ; Ahmed, Ali Najah ; El-Shafie, Ahmed. / An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration. In: PLoS ONE. 2019 ; Vol. 14, No. 5.
@article{ef4e6d3a6d304a999b735e3cd7afd1c2,
title = "An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration",
abstract = "Reference evapotranspiration (ET0) plays a fundamental role in irrigated agriculture. The objective of this study is to simulate monthly ET0 at a meteorological station in India using a new method, an improved support vector machine (SVM) based on the cuckoo algorithm (CA), which is known as SVM-CA. Maximum temperature, minimum temperature, relative humidity, wind speed and sunshine hours were selected as inputs for the models used in the simulation. The results of the simulation using SVM-CA were compared with those from experimental models, genetic programming (GP), model tree (M5T) and the adaptive neuro-fuzzy inference system (ANFIS). The achieved results demonstrate that the proposed SVM-CA model is able to simulate ET0 more accurately than the GP, M5T and ANFIS models. Two major indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), indicated that the SVM-CA outperformed the other methods with respective reductions of 5-15{\%} and 5-17{\%} compared with the GP model, 12-21{\%} and 10-22{\%} compared with the M5T model, and 7-15{\%} and 5-18{\%} compared with the ANFIS model, respectively. Therefore, the proposed SVM-CA model has high potential for accurate simulation of monthly ET0 values compared with the other models.",
author = "Mohammad Ehteram and Singh, {Vijay P.} and Ahmad Ferdowsi and Mousavi, {Sayed Farhad} and Saeed Farzin and Hojat Karami and Mohd, {Nuruol Syuhadaa} and Afan, {Haitham Abdulmohsin} and Lai, {Sai Hin} and Ozgur Kisi and {Abdul Malek}, Marlinda and Ahmed, {Ali Najah} and Ahmed El-Shafie",
year = "2019",
month = "5",
day = "1",
doi = "10.1371/journal.pone.0217499",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "5",

}

Ehteram, M, Singh, VP, Ferdowsi, A, Mousavi, SF, Farzin, S, Karami, H, Mohd, NS, Afan, HA, Lai, SH, Kisi, O, Abdul Malek, M, Ahmed, AN & El-Shafie, A 2019, 'An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration', PLoS ONE, vol. 14, no. 5, e0217499. https://doi.org/10.1371/journal.pone.0217499

An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration. / Ehteram, Mohammad; Singh, Vijay P.; Ferdowsi, Ahmad; Mousavi, Sayed Farhad; Farzin, Saeed; Karami, Hojat; Mohd, Nuruol Syuhadaa; Afan, Haitham Abdulmohsin; Lai, Sai Hin; Kisi, Ozgur; Abdul Malek, Marlinda; Ahmed, Ali Najah; El-Shafie, Ahmed.

In: PLoS ONE, Vol. 14, No. 5, e0217499, 01.05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An improved model based on the support vector machine and cuckoo algorithm for simulating reference evapotranspiration

AU - Ehteram, Mohammad

AU - Singh, Vijay P.

AU - Ferdowsi, Ahmad

AU - Mousavi, Sayed Farhad

AU - Farzin, Saeed

AU - Karami, Hojat

AU - Mohd, Nuruol Syuhadaa

AU - Afan, Haitham Abdulmohsin

AU - Lai, Sai Hin

AU - Kisi, Ozgur

AU - Abdul Malek, Marlinda

AU - Ahmed, Ali Najah

AU - El-Shafie, Ahmed

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Reference evapotranspiration (ET0) plays a fundamental role in irrigated agriculture. The objective of this study is to simulate monthly ET0 at a meteorological station in India using a new method, an improved support vector machine (SVM) based on the cuckoo algorithm (CA), which is known as SVM-CA. Maximum temperature, minimum temperature, relative humidity, wind speed and sunshine hours were selected as inputs for the models used in the simulation. The results of the simulation using SVM-CA were compared with those from experimental models, genetic programming (GP), model tree (M5T) and the adaptive neuro-fuzzy inference system (ANFIS). The achieved results demonstrate that the proposed SVM-CA model is able to simulate ET0 more accurately than the GP, M5T and ANFIS models. Two major indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), indicated that the SVM-CA outperformed the other methods with respective reductions of 5-15% and 5-17% compared with the GP model, 12-21% and 10-22% compared with the M5T model, and 7-15% and 5-18% compared with the ANFIS model, respectively. Therefore, the proposed SVM-CA model has high potential for accurate simulation of monthly ET0 values compared with the other models.

AB - Reference evapotranspiration (ET0) plays a fundamental role in irrigated agriculture. The objective of this study is to simulate monthly ET0 at a meteorological station in India using a new method, an improved support vector machine (SVM) based on the cuckoo algorithm (CA), which is known as SVM-CA. Maximum temperature, minimum temperature, relative humidity, wind speed and sunshine hours were selected as inputs for the models used in the simulation. The results of the simulation using SVM-CA were compared with those from experimental models, genetic programming (GP), model tree (M5T) and the adaptive neuro-fuzzy inference system (ANFIS). The achieved results demonstrate that the proposed SVM-CA model is able to simulate ET0 more accurately than the GP, M5T and ANFIS models. Two major indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), indicated that the SVM-CA outperformed the other methods with respective reductions of 5-15% and 5-17% compared with the GP model, 12-21% and 10-22% compared with the M5T model, and 7-15% and 5-18% compared with the ANFIS model, respectively. Therefore, the proposed SVM-CA model has high potential for accurate simulation of monthly ET0 values compared with the other models.

UR - http://www.scopus.com/inward/record.url?scp=85066480927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066480927&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0217499

DO - 10.1371/journal.pone.0217499

M3 - Article

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 5

M1 - e0217499

ER -