Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation

Abstract We developed a global carbon flux dataset, GloFlux, using a machine learning model that integrates in situ observations from FLUXNET, AmeriFlux, ICOS, JapanFlux2024, and HBRFlux with satellite remote sensing and meteorological data. The dataset covers 2000–2023, has a 0.1∘ × 0. 1∘ spatial r...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiwang Yuan, Xufeng Wang, Tao Che, Jun Li
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05672-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849767178647109632
author Qiwang Yuan
Xufeng Wang
Tao Che
Jun Li
author_facet Qiwang Yuan
Xufeng Wang
Tao Che
Jun Li
author_sort Qiwang Yuan
collection DOAJ
description Abstract We developed a global carbon flux dataset, GloFlux, using a machine learning model that integrates in situ observations from FLUXNET, AmeriFlux, ICOS, JapanFlux2024, and HBRFlux with satellite remote sensing and meteorological data. The dataset covers 2000–2023, has a 0.1∘ × 0. 1∘ spatial resolution, and monthly temporal resolution. It includes three key variables: Gross Primary Productivity (GPP), Net Ecosystem Exchange (NEE), and Ecosystem Respiration (RECO). Validation at independent flux sites not used in model training shows strong performance at the site level, with correlation coefficients of 0.84 for GPP, 0.66 for NEE, and 0.80 for RECO. The spatiotemporal patterns of GloFlux align well with existing datasets such as FLUXCOM and MODIS, supporting the reliability and robustness of the product. GloFlux offers a valuable resource for assessing global vegetation dynamics and understanding ecosystem responses to climate change.
format Article
id doaj-art-f8e0500c3c1944aea4e251f4b758f97c
institution DOAJ
issn 2052-4463
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-f8e0500c3c1944aea4e251f4b758f97c2025-08-20T03:04:18ZengNature PortfolioScientific Data2052-44632025-08-0112111510.1038/s41597-025-05672-8Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observationQiwang Yuan0Xufeng Wang1Tao Che2Jun Li3School of Computer Science, China University of GeosciencesKey Laboratory of Remote Sensing of Gansu Province, Heihe Remote Sensing Experimental Research Station, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of SciencesKey Laboratory of Remote Sensing of Gansu Province, Heihe Remote Sensing Experimental Research Station, State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of SciencesSchool of Computer Science, China University of GeosciencesAbstract We developed a global carbon flux dataset, GloFlux, using a machine learning model that integrates in situ observations from FLUXNET, AmeriFlux, ICOS, JapanFlux2024, and HBRFlux with satellite remote sensing and meteorological data. The dataset covers 2000–2023, has a 0.1∘ × 0. 1∘ spatial resolution, and monthly temporal resolution. It includes three key variables: Gross Primary Productivity (GPP), Net Ecosystem Exchange (NEE), and Ecosystem Respiration (RECO). Validation at independent flux sites not used in model training shows strong performance at the site level, with correlation coefficients of 0.84 for GPP, 0.66 for NEE, and 0.80 for RECO. The spatiotemporal patterns of GloFlux align well with existing datasets such as FLUXCOM and MODIS, supporting the reliability and robustness of the product. GloFlux offers a valuable resource for assessing global vegetation dynamics and understanding ecosystem responses to climate change.https://doi.org/10.1038/s41597-025-05672-8
spellingShingle Qiwang Yuan
Xufeng Wang
Tao Che
Jun Li
Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
Scientific Data
title Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
title_full Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
title_fullStr Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
title_full_unstemmed Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
title_short Global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
title_sort global carbon flux dataset generated by fusing remote sensing and multiple flux networks observation
url https://doi.org/10.1038/s41597-025-05672-8
work_keys_str_mv AT qiwangyuan globalcarbonfluxdatasetgeneratedbyfusingremotesensingandmultiplefluxnetworksobservation
AT xufengwang globalcarbonfluxdatasetgeneratedbyfusingremotesensingandmultiplefluxnetworksobservation
AT taoche globalcarbonfluxdatasetgeneratedbyfusingremotesensingandmultiplefluxnetworksobservation
AT junli globalcarbonfluxdatasetgeneratedbyfusingremotesensingandmultiplefluxnetworksobservation