Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model

Estimating actual evapotranspiration (ETₐ) is crucial for water resource management, yet existing methods face limitations. Traditional approaches, including eddy covariance and remote sensing-based energy balance methods, often struggle with high costs, limited spatial and temporal coverage, and re...

Full description

Saved in:
Bibliographic Details
Main Authors: Fatima K. Abu Salem, Sara Awad, Yasmine Hamdar, Samer Kharroubi, Hadi Jaafar
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2024-12-01
Series:Artificial Intelligence in Agriculture
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589721724000400
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846123337938370560
author Fatima K. Abu Salem
Sara Awad
Yasmine Hamdar
Samer Kharroubi
Hadi Jaafar
author_facet Fatima K. Abu Salem
Sara Awad
Yasmine Hamdar
Samer Kharroubi
Hadi Jaafar
author_sort Fatima K. Abu Salem
collection DOAJ
description Estimating actual evapotranspiration (ETₐ) is crucial for water resource management, yet existing methods face limitations. Traditional approaches, including eddy covariance and remote sensing-based energy balance methods, often struggle with high costs, limited spatial and temporal coverage, and reduced predictive accuracy, particularly for classical empirical models. While machine learning has emerged as a promising alternative, it still presents challenges, notably in underestimating ETₐ during periods of high heat. We attribute this to insufficient learning on the rare but highly relevant ETₐ values of interest, or the not-so-big climatic datasets available for use. In this manuscript, we demonstrate how few-shot, meta-learning models (MAML) that are specifically designed for enhanced generalizability on not-so-big datasets can outperform basic machine learning models in upscaling ETₐ from two major in-situ towers, the Ameriflux and Euroflux. Using limited remotely sensed land surface data from the METRIC-EEFlux and limited climatic variables, we demonstrate that the chosen models can attain quantifiable utility within the utility-based-regression paradigm towards impactful practical considerations. Our initial explorations reveal that EEflux ETₐ deviates significantly from in-situ observations measured through the Ameriflux and EEflux towers (R2=39%). Instead, MAML shows best performance in approximating ETₐ than basic machine learning algorithms and EEFlux (R2=71% on entire testing dataset, R2=0.88 on the Csa climate, R2=0.79 on the Cfa climate, and R2=0.78 on the CSH vegetation class), and continues to improve without overfitting even when exposed to a relatively small training dataset. Its high F2 score (96 %) indicates that MAML has very high precision and recall for rare cases, which is significant for irrigation. Of independent interest, this study confirms that limited remotely sensed EEflux products contribute significantly to knowledge about ground truth ETₐ and can thus be of valuable use in settings where access to good quality and high-volume data is compromised.
format Article
id doaj-art-61541f1ba7074d68a01961acb3b1b754
institution Kabale University
issn 2589-7217
language English
publishDate 2024-12-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Artificial Intelligence in Agriculture
spelling doaj-art-61541f1ba7074d68a01961acb3b1b7542024-12-14T06:31:54ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172024-12-01144355Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) modelFatima K. Abu Salem0Sara Awad1Yasmine Hamdar2Samer Kharroubi3Hadi Jaafar4Department of Computer Science, Faculty of Arts and Sciences, American University of Beirut, Beirut, LebanonDepartment of Computer Science, Faculty of Arts and Sciences, American University of Beirut, Beirut, LebanonDepartment of Computer Science, Faculty of Arts and Sciences, American University of Beirut, Beirut, LebanonDepartment of Nutrition and Food Sciences, Faculty of Agricultural and Food Sciences, American University of Beirut, Beirut, LebanonDepartment of Agriculture, Faculty of Agricultural and Food Sciences, American University of Beirut, Beirut, Lebanon; Corresponding author.Estimating actual evapotranspiration (ETₐ) is crucial for water resource management, yet existing methods face limitations. Traditional approaches, including eddy covariance and remote sensing-based energy balance methods, often struggle with high costs, limited spatial and temporal coverage, and reduced predictive accuracy, particularly for classical empirical models. While machine learning has emerged as a promising alternative, it still presents challenges, notably in underestimating ETₐ during periods of high heat. We attribute this to insufficient learning on the rare but highly relevant ETₐ values of interest, or the not-so-big climatic datasets available for use. In this manuscript, we demonstrate how few-shot, meta-learning models (MAML) that are specifically designed for enhanced generalizability on not-so-big datasets can outperform basic machine learning models in upscaling ETₐ from two major in-situ towers, the Ameriflux and Euroflux. Using limited remotely sensed land surface data from the METRIC-EEFlux and limited climatic variables, we demonstrate that the chosen models can attain quantifiable utility within the utility-based-regression paradigm towards impactful practical considerations. Our initial explorations reveal that EEflux ETₐ deviates significantly from in-situ observations measured through the Ameriflux and EEflux towers (R2=39%). Instead, MAML shows best performance in approximating ETₐ than basic machine learning algorithms and EEFlux (R2=71% on entire testing dataset, R2=0.88 on the Csa climate, R2=0.79 on the Cfa climate, and R2=0.78 on the CSH vegetation class), and continues to improve without overfitting even when exposed to a relatively small training dataset. Its high F2 score (96 %) indicates that MAML has very high precision and recall for rare cases, which is significant for irrigation. Of independent interest, this study confirms that limited remotely sensed EEflux products contribute significantly to knowledge about ground truth ETₐ and can thus be of valuable use in settings where access to good quality and high-volume data is compromised.http://www.sciencedirect.com/science/article/pii/S2589721724000400EvapotranspirationMachine learningArtificial intelligenceEEFlux
spellingShingle Fatima K. Abu Salem
Sara Awad
Yasmine Hamdar
Samer Kharroubi
Hadi Jaafar
Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model
Artificial Intelligence in Agriculture
Evapotranspiration
Machine learning
Artificial intelligence
EEFlux
title Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model
title_full Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model
title_fullStr Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model
title_full_unstemmed Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model
title_short Utility-based regression and meta-learning techniques for modeling actual ET: Comparison to (METRIC-EEFLUX) model
title_sort utility based regression and meta learning techniques for modeling actual et comparison to metric eeflux model
topic Evapotranspiration
Machine learning
Artificial intelligence
EEFlux
url http://www.sciencedirect.com/science/article/pii/S2589721724000400
work_keys_str_mv AT fatimakabusalem utilitybasedregressionandmetalearningtechniquesformodelingactualetcomparisontometriceefluxmodel
AT saraawad utilitybasedregressionandmetalearningtechniquesformodelingactualetcomparisontometriceefluxmodel
AT yasminehamdar utilitybasedregressionandmetalearningtechniquesformodelingactualetcomparisontometriceefluxmodel
AT samerkharroubi utilitybasedregressionandmetalearningtechniquesformodelingactualetcomparisontometriceefluxmodel
AT hadijaafar utilitybasedregressionandmetalearningtechniquesformodelingactualetcomparisontometriceefluxmodel