{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:15:50Z","timestamp":1789172150187,"version":"build-2803163510"},"reference-count":87,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"vor","delay-in-days":10,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2422397"],"award-info":[{"award-number":["2422397"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Global Change Biology"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Gross primary productivity (GPP) is the largest term in the global carbon budget but cannot be directly observed. We present a knowledge\u2010guided machine learning (KGML) framework that partitions eddy covariance\u2010measured net ecosystem exchange (NEE) into gross primary production (GPP) and ecosystem respiration (RECO) with partitioned water vapor fluxes and CO\n                    <jats:sub>2<\/jats:sub>\n                    flux source areas from 36\u2009U.S. National Ecological Observatory Network (NEON) towers. The KGML is guided by hard physical constraints that enforce mass balance and \u2018soft\u2019 theoretical expectations including optimal stomatal response to vapor pressure deficit (VPD) and links between GPP and transpiration (T) through stomatal function. The model achieves strong physical consistency (NEE\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.99) while capturing expected ecophysiological relationships including GPP\u2010T coupling (\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.58) and stomatal responses to light and VPD. Compared to conventional partitioning methods, KGML infers lower GPP and RECO estimates on average, with the largest negative biases occurring at low light levels (0\u2013200\u2009\u03bcmol photons m\n                    <jats:sup>\u22122<\/jats:sup>\n                    \u2009s\n                    <jats:sup>\u22121<\/jats:sup>\n                    ). These differences likely reflect a combination of mechanisms including light\u2010induced respiration suppression consistent with the Kok effect, stomatal\u2010transpiration coupling constraints, and dynamic allocation between respiration components. The flux differences vary across plant functional types (PFTs), where forested ecosystems (deciduous broadleaf, evergreen needleleaf, and mixed), savannas and grasslands show the largest negative annual GPP deviations (\u221210% to \u221218% versus nighttime partitioning), while croplands and open shrublands show moderate negative deviations (\u22125% to \u221210%). The lower GPP estimates by PFT are closer to those inferred by Keenan et\u00a0al. that explicitly considers limitations on RECO from the Kok effect. We discuss implications for our understanding of ecosystem and global carbon cycle processes, as well as ways to further benefit from the full information content of eddy covariance observations by combining physics with knowledge of biological processes.\n                  <\/jats:p>","DOI":"10.1111\/gcb.70886","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T06:45:09Z","timestamp":1778568309000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Constrained Carbon Partitioning: A Self\u2010Trained Physics\u2010Informed Machine Learning Model Refines GPP Estimates From Eddy Covariance Measurements"],"prefix":"10.1111","volume":"32","author":[{"given":"Sadegh","family":"Ranjbar","sequence":"first","affiliation":[{"name":"Department of Biological Systems Engineering University of Wisconsin \u2013 Madison  Madison Wisconsin USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur R.","family":"Desai","sequence":"additional","affiliation":[{"name":"Department of Atmospheric and Oceanic Sciences University of Wisconsin \u2013 Madison  Madison Wisconsin USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophie","family":"Hoffman","sequence":"additional","affiliation":[{"name":"Department of Biological Systems Engineering University of Wisconsin \u2013 Madison  Madison Wisconsin USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Einara","family":"Zahn","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering Princeton University  Princeton New Jersey USA"},{"name":"Department of Earth and Environmental Science University of Pennsylvania  Philadelphia Pennsylvania USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elie","family":"Bou\u2010Zeid","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering Princeton University  Princeton New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul C.","family":"Stoy","sequence":"additional","affiliation":[{"name":"Department of Biological Systems Engineering University of Wisconsin \u2013 Madison  Madison Wisconsin USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-2351-1"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature05038"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1071\/BT07151"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.12649"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2015.03.010"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.14807"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1104\/pp.106.092940"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02531-2"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad5a60"},{"key":"e_1_2_11_11_1","unstructured":"Cuntz M.2020.\u201chesseflux: A Python Library to Process and Post\u2010Process Eddy Covariance Data\u201d."},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.5194\/bg-16-903-2019"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2007.11.012"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs14071722"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1029\/2025MS005102"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.2111\/1551-5028(2007)60[464:EWUEIA]2.0.CO;2"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scienta.2011.12.004"},{"key":"e_1_2_11_18_1","first-page":"1050","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","volume":"48","author":"Gal Y.","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1104\/pp.16.00741"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-9326\/ab22d6"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1029\/2002GB002023"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/nph.16485"},{"issue":"4","key":"e_1_2_11_23_1","article-title":"Heterotrophic Respiration in Disturbed Forests: A Review With Examples From North America","volume":"116","author":"Harmon M. E.","year":"2011","journal-title":"Journal of Geophysical Research: Biogeosciences"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2019.00103"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1890\/ES13-00120.1"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.70798"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.13489"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1175\/JHM-D-10-05034.1"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2486.2001.00412.x"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.70742"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.5194\/essd-17-3009-2025"},{"key":"e_1_2_11_32_1","unstructured":"Karpatne A. X.Jia andV.Kumar.2024.\u201cKnowledge\u2010Guided Machine Learning: Current Trends and Future Prospects. arXiv.\u201dhttps:\/\/doi.org\/10.48550\/arXiv.2403.15989."},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/aob\/mcp292"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-019-0809-2"},{"key":"e_1_2_11_35_1","first-page":"282","author":"Keller M.","year":"2008","journal-title":"Ecological Society of America"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/0006-3002(49)90136-5"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-9326\/ac583e"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2486.2009.02041.x"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.805065"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43860-5"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/ele.13363"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.15548"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2025.114759"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2024.175406"},{"key":"e_1_2_11_45_1","first-page":"4765","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg S. M.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2435.2010.01822.x"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2024.110235"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2486.2010.02375.x"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2486.2010.02243.x"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43017-024-00569-3"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2007.08.002"},{"key":"e_1_2_11_52_1","unstructured":"Novick K.2022.\u201cThe Science Needed for Robust Scalable and Credible Nature\u2010Based Climate Solutions in the United States: Full Report\u201d."},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.16156"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1002\/2015JG002997"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.5194\/bg-3-571-2006"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2486.2003.00609.x"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0534-3"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1890\/08-2176.1"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1029\/2024JH000464"},{"key":"e_1_2_11_60_1","volume-title":"Software: Constrained Carbon Partitioning Using a Self\u2010Trained Physics\u2010Informed Machine Learning +[Computer Software]","author":"Ranjbar S.","year":"2026"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2025.110996"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2486.2005.001002.x"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-2351-1_9"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.06.006"},{"key":"e_1_2_11_65_1","doi-asserted-by":"publisher","DOI":"10.1029\/2021MS002761"},{"key":"e_1_2_11_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2009.09.005"},{"key":"e_1_2_11_67_1","doi-asserted-by":"publisher","DOI":"10.2136\/vzj2012.0025"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1029\/2008WR006932"},{"key":"e_1_2_11_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2019.107732"},{"key":"e_1_2_11_70_1","doi-asserted-by":"crossref","unstructured":"Schuler P. M.Didion\u2010Gency G.Bortolami et\u00a0al.2025.\u201cDecoupling of Stomatal Conductance From Net Assimilation at High Temperature as a Mechanism to Increase Transpiration.bioRxivo\u201d.","DOI":"10.1101\/2025.11.03.686201"},{"key":"e_1_2_11_71_1","doi-asserted-by":"publisher","DOI":"10.1104\/pp.75.1.95"},{"key":"e_1_2_11_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2006.09.001"},{"key":"e_1_2_11_73_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13943"},{"key":"e_1_2_11_74_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.15203"},{"key":"e_1_2_11_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3101129"},{"key":"e_1_2_11_76_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0889.2007.00252.x"},{"key":"e_1_2_11_77_1","doi-asserted-by":"publisher","DOI":"10.1111\/nph.17267"},{"key":"e_1_2_11_78_1","unstructured":"Wang Y. T.Zhang X.Guo andZ.Shen.2024.\u201cGradient Based Feature Attribution in Explainable AI: A Technical Review (arXiv: 2403.10415). arXiv.\u201dhttps:\/\/doi.org\/10.48550\/arXiv.2403.10415."},{"key":"e_1_2_11_79_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature17966"},{"key":"e_1_2_11_80_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1529-8817.2003.00739.x"},{"key":"e_1_2_11_81_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.ady9164"},{"key":"e_1_2_11_82_1","doi-asserted-by":"publisher","DOI":"10.1111\/nph.16638"},{"key":"e_1_2_11_83_1","doi-asserted-by":"publisher","DOI":"10.1111\/gcb.70541"},{"key":"e_1_2_11_84_1","doi-asserted-by":"publisher","DOI":"10.5194\/essd-16-5603-2024"},{"key":"e_1_2_11_85_1","volume-title":"Partitioning of Water and CO2 Fluxes at NEON Sites Into Soil and Plant Components: A Five\u2010Year Dataset for Spatial and Temporal Analysis (Version 1.0) [Dataset]","author":"Zahn E.","year":"2024"},{"key":"e_1_2_11_86_1","doi-asserted-by":"publisher","DOI":"10.1029\/2024JG008025"},{"key":"e_1_2_11_87_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2021.108790"},{"key":"e_1_2_11_88_1","doi-asserted-by":"crossref","unstructured":"Zhang X. N.Chen J.Qiu P.Shi X.Wu andW.Yuan.2024.\u201cImportance\u2010Guided Sequential Training for Physics\u2010Informed Neural Networks. 2024 International Joint Conference on Neural Networks (IJCNN).\u201d1\u20138.","DOI":"10.1109\/IJCNN60899.2024.10651329"}],"container-title":["Global Change Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/gcb.70886","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/gcb.70886","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/gcb.70886","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/gcb.70886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T23:56:57Z","timestamp":1789171017000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/gcb.70886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":87,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1111\/gcb.70886"],"URL":"https:\/\/doi.org\/10.1111\/gcb.70886","archive":["Portico"],"relation":{},"ISSN":["1354-1013","1365-2486"],"issn-type":[{"value":"1354-1013","type":"print"},{"value":"1365-2486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"2025-12-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70886"}}