GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data

Gross primary productivity (GPP) plays a crucial role in the carbon exchange between the atmosphere and terrestrial ecosystems. Eddy covariance (EC) method can obtain accurate GPP at the site level, but the sparse distribution limits representativeness. Satellite solar-induced chlorophyll fluorescen...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongming Ma, Xiaobin Guan, Yuchen Wang, Yuyu Li, Dekun Lin, Huanfeng Shen
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225001505
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850135795835338752
author Yongming Ma
Xiaobin Guan
Yuchen Wang
Yuyu Li
Dekun Lin
Huanfeng Shen
author_facet Yongming Ma
Xiaobin Guan
Yuchen Wang
Yuyu Li
Dekun Lin
Huanfeng Shen
author_sort Yongming Ma
collection DOAJ
description Gross primary productivity (GPP) plays a crucial role in the carbon exchange between the atmosphere and terrestrial ecosystems. Eddy covariance (EC) method can obtain accurate GPP at the site level, but the sparse distribution limits representativeness. Satellite solar-induced chlorophyll fluorescence (SIF) serves as emerging data of large-scale GPP, yet there are still limitations in its conversion to GPP and spatiotemporal coverage. This study proposes a transfer learning (SIFEC-TL) method to estimate long-term global GPP with high accuracy by combining constraints from SIF and EC data. SIF data are taken as the source domain that provides the spatial information for pre-training, and EC GPP in the target domain provides precise GPP for the machine learning model fine-tuning. To verify the performance of SIFEC-TL, the results are compared with those from machine learning models that use only SIF or EC GPP alone (SIFML and ECML). The results indicate that the SIFEC-TL model demonstrates stronger spatial scalability compared to the SIFML and ECML models, with R2 increasing by 0.132 and 0.036. The SIFEC-TL more effectively captures inter-annual GPP dynamics with underestimation/overestimation over high/low values in the SIFML and ECML models being well corrected. Furthermore, three different SIF-based GPP are also used as source domains, and the results showed that they only affect pre-training but the final accuracy after fine-tuning remains similar, which indicates SIFEC-TL can obtain stable GPP estimation accuracy regardless of the spatiotemporal coverage of SIF data and its conversion to GPP.
format Article
id doaj-art-a1b9af74dabc4f2e8e7afb3f66191d1e
institution OA Journals
issn 1569-8432
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-a1b9af74dabc4f2e8e7afb3f66191d1e2025-08-20T02:31:17ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-05-0113910450310.1016/j.jag.2025.104503GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance dataYongming Ma0Xiaobin Guan1Yuchen Wang2Yuyu Li3Dekun Lin4Huanfeng Shen5School of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, China; Collaborative Innovation Center of Geospatial Technology, Wuhan 430079, China; Corresponding author at: School of Resource and Environmental Sciences, Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, China.Gross primary productivity (GPP) plays a crucial role in the carbon exchange between the atmosphere and terrestrial ecosystems. Eddy covariance (EC) method can obtain accurate GPP at the site level, but the sparse distribution limits representativeness. Satellite solar-induced chlorophyll fluorescence (SIF) serves as emerging data of large-scale GPP, yet there are still limitations in its conversion to GPP and spatiotemporal coverage. This study proposes a transfer learning (SIFEC-TL) method to estimate long-term global GPP with high accuracy by combining constraints from SIF and EC data. SIF data are taken as the source domain that provides the spatial information for pre-training, and EC GPP in the target domain provides precise GPP for the machine learning model fine-tuning. To verify the performance of SIFEC-TL, the results are compared with those from machine learning models that use only SIF or EC GPP alone (SIFML and ECML). The results indicate that the SIFEC-TL model demonstrates stronger spatial scalability compared to the SIFML and ECML models, with R2 increasing by 0.132 and 0.036. The SIFEC-TL more effectively captures inter-annual GPP dynamics with underestimation/overestimation over high/low values in the SIFML and ECML models being well corrected. Furthermore, three different SIF-based GPP are also used as source domains, and the results showed that they only affect pre-training but the final accuracy after fine-tuning remains similar, which indicates SIFEC-TL can obtain stable GPP estimation accuracy regardless of the spatiotemporal coverage of SIF data and its conversion to GPP.http://www.sciencedirect.com/science/article/pii/S1569843225001505Gross primary productivityCross-domain transfer learningSolar-induced chlorophyll fluorescenceEddy covarianceLong-term GPP
spellingShingle Yongming Ma
Xiaobin Guan
Yuchen Wang
Yuyu Li
Dekun Lin
Huanfeng Shen
GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data
International Journal of Applied Earth Observations and Geoinformation
Gross primary productivity
Cross-domain transfer learning
Solar-induced chlorophyll fluorescence
Eddy covariance
Long-term GPP
title GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data
title_full GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data
title_fullStr GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data
title_full_unstemmed GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data
title_short GPP estimation by transfer learning with combined solar-induced chlorophyll fluorescence and eddy covariance data
title_sort gpp estimation by transfer learning with combined solar induced chlorophyll fluorescence and eddy covariance data
topic Gross primary productivity
Cross-domain transfer learning
Solar-induced chlorophyll fluorescence
Eddy covariance
Long-term GPP
url http://www.sciencedirect.com/science/article/pii/S1569843225001505
work_keys_str_mv AT yongmingma gppestimationbytransferlearningwithcombinedsolarinducedchlorophyllfluorescenceandeddycovariancedata
AT xiaobinguan gppestimationbytransferlearningwithcombinedsolarinducedchlorophyllfluorescenceandeddycovariancedata
AT yuchenwang gppestimationbytransferlearningwithcombinedsolarinducedchlorophyllfluorescenceandeddycovariancedata
AT yuyuli gppestimationbytransferlearningwithcombinedsolarinducedchlorophyllfluorescenceandeddycovariancedata
AT dekunlin gppestimationbytransferlearningwithcombinedsolarinducedchlorophyllfluorescenceandeddycovariancedata
AT huanfengshen gppestimationbytransferlearningwithcombinedsolarinducedchlorophyllfluorescenceandeddycovariancedata