Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA

The Maritime Provinces of Canada play a significant role in the country's agricultural productivity, yet they face numerous changes due to climate change. Therefore, a reliable estimation of reference evapotranspiration (ETo) requires accurate determination of the pan coefficient (Kpan). Howeve...

Full description

Saved in:
Bibliographic Details
Main Authors: Saad Javed Cheema, Aitazaz A. Farooque, Mehdi Jamei, Khabat Khasravi, Farhat Abbas, Suqi Liu, Travis J. Esau, Kuljeet Singh Grewal
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002468
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233609664233472
author Saad Javed Cheema
Aitazaz A. Farooque
Mehdi Jamei
Khabat Khasravi
Farhat Abbas
Suqi Liu
Travis J. Esau
Kuljeet Singh Grewal
author_facet Saad Javed Cheema
Aitazaz A. Farooque
Mehdi Jamei
Khabat Khasravi
Farhat Abbas
Suqi Liu
Travis J. Esau
Kuljeet Singh Grewal
author_sort Saad Javed Cheema
collection DOAJ
description The Maritime Provinces of Canada play a significant role in the country's agricultural productivity, yet they face numerous changes due to climate change. Therefore, a reliable estimation of reference evapotranspiration (ETo) requires accurate determination of the pan coefficient (Kpan). However, this is quite challenging due to variations in climate change and the deep non-linearity of meteorological data. Intensive experiments for pan evaporation (Epan) were conducted to develop a model, which includes hill-climbing based BestFirst-ClassifierSubsetEval (BF), alternating model tree (AMT), and multi-objective optimization by ratio analysis (MOORA). The model was assessed by comparing its performance using Bidirectional long-short-term memory (Bi-LSTM), recurrent neural network (RNN), random forest (RF), elastic regression net (Elastic net), and Instance-based learner K-Nearest Neighbor (IBK). The model was further evaluated using five empirical equations of FAO-56. The input data included seven daily meteorological variables, including maximum, minimum, mean, relative humidity, Wind, and Slope, extracted from 2018 to 2023 datasets to compute ETo and Kpan locally measured Epan. Statistical indicators, including correlation coefficient (R), root mean square error (RMSE), Kling–Gupta efficiency (KGE), and Vulnerability, evaluated the model output. SHAP (Shapley Additive exPlanations) and Individual Conditional Expectation (ICE) were used to interpret the models' flexibility and visualize complex geographical phenomena and processes in an RF model. Overall, the outcomes revealed that the primary model (BF-AMT) outperformed all the data-driven and empirical models in terms of optimal metrics (RMSE=0.0143, Vulnerability=6.3260, and MOORA=0), followed by BF-Elastic net (RMSE=0.7891, Vulnerability=28.1081, and MOORA=0.073) and BF-Bi-LSTM (RMSE=0.0169, Vulnerability=64.8649, and MOORA=0.128), respectively. Finally, the SHAP results showed that wind and relative humidity were the most influential factors affecting the pan coefficient values.
format Article
id doaj-art-a0afe0b46bdf4aab962ed329b7977a69
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-a0afe0b46bdf4aab962ed329b7977a692025-08-20T05:05:15ZengElsevierEcological Informatics1574-95412025-12-019010323710.1016/j.ecoinf.2025.103237Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORASaad Javed Cheema0Aitazaz A. Farooque1Mehdi Jamei2Khabat Khasravi3Farhat Abbas4Suqi Liu5Travis J. Esau6Kuljeet Singh Grewal7School of Climate Change and Adaptation, University of Prince Edward Island, PEI, CanadaSchool of Climate Change and Adaptation, University of Prince Edward Island, PEI, Canada; Faculty of Sustainable Design Engineering, University of Prince Edward Island, PEI, Canada; Corresponding author at: School of Climate Change and Adaptation, University of Prince Edward Island, PEI, Canada.School of Climate Change and Adaptation, University of Prince Edward Island, PEI, Canada; Faculty of Civil Engineering and Architecture, Shahid Chamran University of Ahvaz, Ahvaz, IranSchool of Climate Change and Adaptation, University of Prince Edward Island, PEI, Canada; Faculty of Sustainable Design Engineering, University of Prince Edward Island, PEI, Canada; Faculty of Civil Engineering and Architecture, Shahid Chamran University of Ahvaz, Ahvaz, Iran; College of Engineering and Technology, University of Doha for Science and Technology, Doha, P. O. Box 24449, Qatar; Department of Agriculture, Government of Prince Edward Island, Charlottetown, PE, Canada; Department of Engineering, Faculty of Agriculture, Dalhousie University, Truro, NS B2N 5E3, Canada; Department of Natural Resources, Faculty of Agriculture and Natural Resources, Razi University, Kermanshah 6714414971, IranCollege of Engineering and Technology, University of Doha for Science and Technology, Doha, P. O. Box 24449, QatarDepartment of Agriculture, Government of Prince Edward Island, Charlottetown, PE, CanadaDepartment of Engineering, Faculty of Agriculture, Dalhousie University, Truro, NS B2N 5E3, CanadaFaculty of Sustainable Design Engineering, University of Prince Edward Island, PEI, CanadaThe Maritime Provinces of Canada play a significant role in the country's agricultural productivity, yet they face numerous changes due to climate change. Therefore, a reliable estimation of reference evapotranspiration (ETo) requires accurate determination of the pan coefficient (Kpan). However, this is quite challenging due to variations in climate change and the deep non-linearity of meteorological data. Intensive experiments for pan evaporation (Epan) were conducted to develop a model, which includes hill-climbing based BestFirst-ClassifierSubsetEval (BF), alternating model tree (AMT), and multi-objective optimization by ratio analysis (MOORA). The model was assessed by comparing its performance using Bidirectional long-short-term memory (Bi-LSTM), recurrent neural network (RNN), random forest (RF), elastic regression net (Elastic net), and Instance-based learner K-Nearest Neighbor (IBK). The model was further evaluated using five empirical equations of FAO-56. The input data included seven daily meteorological variables, including maximum, minimum, mean, relative humidity, Wind, and Slope, extracted from 2018 to 2023 datasets to compute ETo and Kpan locally measured Epan. Statistical indicators, including correlation coefficient (R), root mean square error (RMSE), Kling–Gupta efficiency (KGE), and Vulnerability, evaluated the model output. SHAP (Shapley Additive exPlanations) and Individual Conditional Expectation (ICE) were used to interpret the models' flexibility and visualize complex geographical phenomena and processes in an RF model. Overall, the outcomes revealed that the primary model (BF-AMT) outperformed all the data-driven and empirical models in terms of optimal metrics (RMSE=0.0143, Vulnerability=6.3260, and MOORA=0), followed by BF-Elastic net (RMSE=0.7891, Vulnerability=28.1081, and MOORA=0.073) and BF-Bi-LSTM (RMSE=0.0169, Vulnerability=64.8649, and MOORA=0.128), respectively. Finally, the SHAP results showed that wind and relative humidity were the most influential factors affecting the pan coefficient values.http://www.sciencedirect.com/science/article/pii/S1574954125002468Pan coefficientReference evapotranspirationMOORAClimate changeAlternating model treeBestFirst-ClassifierSubsetEval
spellingShingle Saad Javed Cheema
Aitazaz A. Farooque
Mehdi Jamei
Khabat Khasravi
Farhat Abbas
Suqi Liu
Travis J. Esau
Kuljeet Singh Grewal
Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA
Ecological Informatics
Pan coefficient
Reference evapotranspiration
MOORA
Climate change
Alternating model tree
BestFirst-ClassifierSubsetEval
title Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA
title_full Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA
title_fullStr Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA
title_full_unstemmed Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA
title_short Assessment of pan coefficient performance: A comparative study of empirical and model-driven approaches using a hill-climbing-based alternating model tree and MOORA
title_sort assessment of pan coefficient performance a comparative study of empirical and model driven approaches using a hill climbing based alternating model tree and moora
topic Pan coefficient
Reference evapotranspiration
MOORA
Climate change
Alternating model tree
BestFirst-ClassifierSubsetEval
url http://www.sciencedirect.com/science/article/pii/S1574954125002468
work_keys_str_mv AT saadjavedcheema assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT aitazazafarooque assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT mehdijamei assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT khabatkhasravi assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT farhatabbas assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT suqiliu assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT travisjesau assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora
AT kuljeetsinghgrewal assessmentofpancoefficientperformanceacomparativestudyofempiricalandmodeldrivenapproachesusingahillclimbingbasedalternatingmodeltreeandmoora