Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods

Monitoring tools are needed to maximise living systems' ability to mitigate emissions and adapt to changing environmental conditions. Therefore, it is important to be able to predict the fundamental fluxes in crops, in this case vineyards, such as sensible heat flux (H), latent heat flux (LE) and ca...

Descripción completa

Detalles Bibliográficos
Autores principales: García-Rodríguez, David, Catret, Pablo, Iglesias, Domingo J., Martínez, Juan J., López, Ernesto, García, Antonio
Formato: article
Lenguaje:Inglés
Publicado: Elsevier 2024
Materias:
Acceso en línea:https://hdl.handle.net/20.500.11939/8965
https://www.sciencedirect.com/science/article/pii/S1574954124001808
_version_ 1855032887009607680
author García-Rodríguez, David
Catret, Pablo
Iglesias, Domingo J.
Martínez, Juan J.
López, Ernesto
García, Antonio
author_browse Catret, Pablo
García, Antonio
García-Rodríguez, David
Iglesias, Domingo J.
López, Ernesto
Martínez, Juan J.
author_facet García-Rodríguez, David
Catret, Pablo
Iglesias, Domingo J.
Martínez, Juan J.
López, Ernesto
García, Antonio
author_sort García-Rodríguez, David
collection ReDivia
description Monitoring tools are needed to maximise living systems' ability to mitigate emissions and adapt to changing environmental conditions. Therefore, it is important to be able to predict the fundamental fluxes in crops, in this case vineyards, such as sensible heat flux (H), latent heat flux (LE) and carbon dioxide flux (CO2), in order to know their capacity to adapt to the environmental effects of climate change. In this study, Linear Regression (LR), Elastic Net (EN) regression, K-Nearest Neighbours (KNN), Gaussian-Process (GP), Decision Tree (TREE) Regression, Random Forest (RF) Regression, XGBoost (XGB) Regression, Support Vector Regression (SVR) and Multi-layer Perceptron (MLP) models have been applied to predict fundamental fluxes of an eddy-covariance station from conventional meteorological parameters. These models reproduced well the estimations of three output parameters from the eddy-covariance station. The performance of each predictive model was evaluated using Root-Mean-Squared Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Scaled Error (MASE) and the coefficient of determination (R2). The findings indicate that for the variable H, the GP model outperformed the SVR and all other models, achieving an R2 value of 0.99. Conversely, the SVR demonstrated superior performance for the variables LE and CO2, with R2 values of 0.96 for both. In summary, these findings suggest that the three models proposed show a robust performance in the prediction of the studied fluxes, underlining their versatility and adaptability to the various environmental conditions of the vineyard.
format article
id ReDivia8965
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling ReDivia89652025-04-25T14:49:40Z Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods García-Rodríguez, David Catret, Pablo Iglesias, Domingo J. Martínez, Juan J. López, Ernesto García, Antonio Eddy covariance fluxes Deep learning Agricultural crops Surface energy balance N01 Agricultural engineering machine learning Monitoring tools are needed to maximise living systems' ability to mitigate emissions and adapt to changing environmental conditions. Therefore, it is important to be able to predict the fundamental fluxes in crops, in this case vineyards, such as sensible heat flux (H), latent heat flux (LE) and carbon dioxide flux (CO2), in order to know their capacity to adapt to the environmental effects of climate change. In this study, Linear Regression (LR), Elastic Net (EN) regression, K-Nearest Neighbours (KNN), Gaussian-Process (GP), Decision Tree (TREE) Regression, Random Forest (RF) Regression, XGBoost (XGB) Regression, Support Vector Regression (SVR) and Multi-layer Perceptron (MLP) models have been applied to predict fundamental fluxes of an eddy-covariance station from conventional meteorological parameters. These models reproduced well the estimations of three output parameters from the eddy-covariance station. The performance of each predictive model was evaluated using Root-Mean-Squared Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Scaled Error (MASE) and the coefficient of determination (R2). The findings indicate that for the variable H, the GP model outperformed the SVR and all other models, achieving an R2 value of 0.99. Conversely, the SVR demonstrated superior performance for the variables LE and CO2, with R2 values of 0.96 for both. In summary, these findings suggest that the three models proposed show a robust performance in the prediction of the studied fluxes, underlining their versatility and adaptability to the various environmental conditions of the vineyard. 2024-08-30T11:48:23Z 2024-08-30T11:48:23Z 2024 article publishedVersion Garcia-Rodriguez, D., Ruber, P. C., Fuente, D. J. I., Durá, J. J. M., Baeza, E. L., & Celda, A. G. (2024). Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods. Ecological Informatics, 81, 102638. 1574-9541 https://hdl.handle.net/20.500.11939/8965 10.1016/j.ecoinf.2024.102638 https://www.sciencedirect.com/science/article/pii/S1574954124001808 en info:eu-repo/grantAgreement/AEI/Programa Estatal de I+D+i Orientada a los Retos de la Sociedad/PID2020-120438RB-I00/ES/INTELIGENCIA ARTIFICIAL Y SEMANTICA DE DATOS DE OBSERVACION DE LA TIERRA PARA EL ESTABLECIMIENTO DE LA VALENCIA ANCHOR STATION COMO SUPERSITE DEL PROGRAMA CEOS LPV Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ openAccess Elsevier electronico
spellingShingle Eddy covariance fluxes
Deep learning
Agricultural crops
Surface energy balance
N01 Agricultural engineering
machine learning
García-Rodríguez, David
Catret, Pablo
Iglesias, Domingo J.
Martínez, Juan J.
López, Ernesto
García, Antonio
Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods
title Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods
title_full Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods
title_fullStr Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods
title_full_unstemmed Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods
title_short Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods
title_sort predicting the fundamental fluxes of an eddy covariance station using machine learning methods
topic Eddy covariance fluxes
Deep learning
Agricultural crops
Surface energy balance
N01 Agricultural engineering
machine learning
url https://hdl.handle.net/20.500.11939/8965
https://www.sciencedirect.com/science/article/pii/S1574954124001808
work_keys_str_mv AT garciarodriguezdavid predictingthefundamentalfluxesofaneddycovariancestationusingmachinelearningmethods
AT catretpablo predictingthefundamentalfluxesofaneddycovariancestationusingmachinelearningmethods
AT iglesiasdomingoj predictingthefundamentalfluxesofaneddycovariancestationusingmachinelearningmethods
AT martinezjuanj predictingthefundamentalfluxesofaneddycovariancestationusingmachinelearningmethods
AT lopezernesto predictingthefundamentalfluxesofaneddycovariancestationusingmachinelearningmethods
AT garciaantonio predictingthefundamentalfluxesofaneddycovariancestationusingmachinelearningmethods