Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale

Accurate estimation and forecasting of Reference Evapotranspiration (ET0) is critical for almost all agricultural activities and water resource management. However, the most commonly used Penman-Monteith model (FAO56-PM) requires a large amount of input data and it is difficult to compute for genera...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Ye, Aurora González-Vidal, Miguel A. Zamora-Izquierdo, Antonio F. Skarmeta
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525001194
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850221338966360064
author Yu Ye
Aurora González-Vidal
Miguel A. Zamora-Izquierdo
Antonio F. Skarmeta
author_facet Yu Ye
Aurora González-Vidal
Miguel A. Zamora-Izquierdo
Antonio F. Skarmeta
author_sort Yu Ye
collection DOAJ
description Accurate estimation and forecasting of Reference Evapotranspiration (ET0) is critical for almost all agricultural activities and water resource management. However, the most commonly used Penman-Monteith model (FAO56-PM) requires a large amount of input data and it is difficult to compute for general users. Machine Learning (ML) techniques can be used to address this shortcoming. Nevertheless, most studies are site-specific and lack generalizability. This study compares standard ML and Deep Learning (DL) algorithms for estimating and forecasting daily ET0 at different spatial scales in Spain. While Transfer Learning (TL) is a well-established ML technique, its application in ET0 computation remains largely unexplored. We applied TL in a novel approach to retrain DL models, enabling adaptation to diverse local climatic conditions, which is particularly important in this domain. All possible combinations of FAO56-PM inputs were evaluated. The results showed that with three or more climatic variables, the TL process can consistently reduce errors by using an appropriate amount of new data to retrain the models. In estimation, with 20% (120 days) of new data, TL models can provide the same performance as if they were trained with local data, both regionally and nationally (improvement of MAE from 26.4% to 99.5%). During forecasting, we used predicted weather data as input, and despite inherent biases in some variables, the TL models successfully adapted using 9-36 days of new data, significantly improving predictive performance (reducing MAE from -1.1% to 134.3%). Thus, the TL process is highly recommended as a promising methodology for increasing the generalization capability of DL models in both daily ET0 estimation and forecasting under diverse climatic conditions with limited local data.
format Article
id doaj-art-78918686dcc04013a970a5cb33c79e71
institution OA Journals
issn 2772-3755
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-78918686dcc04013a970a5cb33c79e712025-08-20T02:06:44ZengElsevierSmart Agricultural Technology2772-37552025-08-011110088610.1016/j.atech.2025.100886Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scaleYu Ye0Aurora González-Vidal1Miguel A. Zamora-Izquierdo2Antonio F. Skarmeta3Department of Information and Communication Engineering, University of Murcia, Murcia, SpainDepartment of Information and Communication Engineering, University of Murcia, Murcia, SpainCorresponding author.; Department of Information and Communication Engineering, University of Murcia, Murcia, SpainDepartment of Information and Communication Engineering, University of Murcia, Murcia, SpainAccurate estimation and forecasting of Reference Evapotranspiration (ET0) is critical for almost all agricultural activities and water resource management. However, the most commonly used Penman-Monteith model (FAO56-PM) requires a large amount of input data and it is difficult to compute for general users. Machine Learning (ML) techniques can be used to address this shortcoming. Nevertheless, most studies are site-specific and lack generalizability. This study compares standard ML and Deep Learning (DL) algorithms for estimating and forecasting daily ET0 at different spatial scales in Spain. While Transfer Learning (TL) is a well-established ML technique, its application in ET0 computation remains largely unexplored. We applied TL in a novel approach to retrain DL models, enabling adaptation to diverse local climatic conditions, which is particularly important in this domain. All possible combinations of FAO56-PM inputs were evaluated. The results showed that with three or more climatic variables, the TL process can consistently reduce errors by using an appropriate amount of new data to retrain the models. In estimation, with 20% (120 days) of new data, TL models can provide the same performance as if they were trained with local data, both regionally and nationally (improvement of MAE from 26.4% to 99.5%). During forecasting, we used predicted weather data as input, and despite inherent biases in some variables, the TL models successfully adapted using 9-36 days of new data, significantly improving predictive performance (reducing MAE from -1.1% to 134.3%). Thus, the TL process is highly recommended as a promising methodology for increasing the generalization capability of DL models in both daily ET0 estimation and forecasting under diverse climatic conditions with limited local data.http://www.sciencedirect.com/science/article/pii/S2772375525001194Reference evapotranspirationTransfer learningLong short-term memoryGeneralizabilitySpain/Mediterranean climate
spellingShingle Yu Ye
Aurora González-Vidal
Miguel A. Zamora-Izquierdo
Antonio F. Skarmeta
Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
Smart Agricultural Technology
Reference evapotranspiration
Transfer learning
Long short-term memory
Generalizability
Spain/Mediterranean climate
title Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
title_full Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
title_fullStr Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
title_full_unstemmed Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
title_short Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
title_sort transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in spain from local to national scale
topic Reference evapotranspiration
Transfer learning
Long short-term memory
Generalizability
Spain/Mediterranean climate
url http://www.sciencedirect.com/science/article/pii/S2772375525001194
work_keys_str_mv AT yuye transferanddeeplearningmodelsfordailyreferenceevapotranspirationestimationandforecastinginspainfromlocaltonationalscale
AT auroragonzalezvidal transferanddeeplearningmodelsfordailyreferenceevapotranspirationestimationandforecastinginspainfromlocaltonationalscale
AT miguelazamoraizquierdo transferanddeeplearningmodelsfordailyreferenceevapotranspirationestimationandforecastinginspainfromlocaltonationalscale
AT antoniofskarmeta transferanddeeplearningmodelsfordailyreferenceevapotranspirationestimationandforecastinginspainfromlocaltonationalscale