Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing

Mingjuan Xie; Xiaofei Ma; Yuangang Wang; Chaofan Li; Haiyang Shi; Xiuliang Yuan; Olaf Hellwich; Chunbo Chen; Wenqiang Zhang; Chen Zhang; Qing Ling; Ruixiang Gao; Yu Zhang; Friday Uchenna Ochege; Amaury Frankl; Philippe De Maeyer; Nina Buchmann; Iris Feigenwinter; Jørgen E. Olesen; Radoslaw Juszczak; Adrien Jacotot; Aino Korrensalo; Andrea Pitacco; Andrej Varlagin; Ankit Shekhar; Annalea Lohila; Arnaud Carrara; Aurore Brut; Bart Kruijt; Benjamin Loubet; Bernard Heinesch; Bogdan Chojnicki; Carole Helfter; Caroline Vincke; Changliang Shao; Christian Bernhofer; Christian Brümmer; Christian Wille; Eeva-Stiina Tuittila; Eiko Nemitz; Franco Meggio; Gang Dong; Gary Lanigan; Georg Niedrist; Georg Wohlfahrt; Guoyi Zhou; Ignacio Goded; Thomas Gruenwald; Janusz Olejnik; Joachim Jansen; Johan Neirynck; Juha-Pekka Tuovinen; Junhui Zhang; Katja Klumpp; Kim Pilegaard; Ladislav Šigut; Leif Klemedtsson; Luca Tezza; Lukas Hörtnagl; Marek Urbaniak; Marilyn Roland; Marius Schmidt; Mark A. Sutton; Markus Hehn; Matthew Saunders; Matthias Mauder; Mika Aurela; Mika Korkiakoski; Mingyuan Du; Nadia Vendrame; Natalia Kowalska; Paul G. Leahy; Pavel Alekseychik; Peili Shi; Per Weslien; Shiping Chen; Silvano Fares; Thomas Friborg; Tiphaine Tallec; Tomomichi Kato; Torsten Sachs; Trofim Maximov; Umberto Morra di Cella; Uta Moderow; Yingnian Li; Yongtao He; Yoshiko Kosugi; Geping Luo

doi:10.1038/s41597-023-02473-9

Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing

Mingjuan Xie, Xiaofei Ma, Yuangang Wang, Chaofan Li, Haiyang Shi, Xiuliang Yuan, Olaf Hellwich, Chunbo Chen, Wenqiang Zhang, Chen Zhang, Qing Ling, Ruixiang Gao, Yu Zhang, Friday Uchenna Ochege, Amaury Frankl, Philippe De Maeyer, Nina Buchmann, Iris Feigenwinter, Jørgen E. Olesen, Radoslaw JuszczakAdrien Jacotot, Aino Korrensalo, Andrea Pitacco, Andrej Varlagin, Ankit Shekhar, Annalea Lohila, Arnaud Carrara, Aurore Brut, Bart Kruijt, Benjamin Loubet, Bernard Heinesch, Bogdan Chojnicki, Carole Helfter, Caroline Vincke, Changliang Shao, Christian Bernhofer, Christian Brümmer, Christian Wille, Eeva-Stiina Tuittila, Eiko Nemitz, Franco Meggio, Gang Dong, Gary Lanigan, Georg Niedrist, Georg Wohlfahrt, Guoyi Zhou, Ignacio Goded, Thomas Gruenwald, Janusz Olejnik, Joachim Jansen, Johan Neirynck, Juha-Pekka Tuovinen, Junhui Zhang, Katja Klumpp, Kim Pilegaard, Ladislav Šigut, Leif Klemedtsson, Luca Tezza, Lukas Hörtnagl, Marek Urbaniak, Marilyn Roland, Marius Schmidt, Mark A. Sutton, Markus Hehn, Matthew Saunders, Matthias Mauder, Mika Aurela, Mika Korkiakoski, Mingyuan Du, Nadia Vendrame, Natalia Kowalska, Paul G. Leahy, Pavel Alekseychik, Peili Shi, Per Weslien, Shiping Chen, Silvano Fares, Thomas Friborg, Tiphaine Tallec, Tomomichi Kato, Torsten Sachs, Trofim Maximov, Umberto Morra di Cella, Uta Moderow, Yingnian Li, Yongtao He, Yoshiko Kosugi, Geping Luo

Environment and Climate

Research output: Contribution to journal › A1: Web of Science-article › peer-review

Abstract

Simulating the carbon-water fluxes at more widely distributed meteorological stations based on the sparsely and unevenly distributed eddy covariance flux stations is needed to accurately understand the carbon-water cycle of terrestrial ecosystems. We established a new framework consisting of machine learning, determination coefficient (R2), Euclidean distance, and remote sensing (RS), to simulate the daily net ecosystem carbon dioxide exchange (NEE) and water flux (WF) of the Eurasian meteorological stations using a random forest model or/and RS. The daily NEE and WF datasets with RS-based information (NEE-RS and WF-RS) for 3774 and 4427 meteorological stations during 2002–2020 were produced, respectively. And the daily NEE and WF datasets without RS-based information (NEE-WRS and WF-WRS) for 4667 and 6763 meteorological stations during 1983–2018 were generated, respectively. For each meteorological station, the carbon-water fluxes meet accuracy requirements and have quasi-observational properties. These four carbon-water flux datasets have great potential to improve the assessments of the ecosystem carbon-water dynamics.

Original language	English
Volume	10
Issue number	1
ISSN	2052-4463
DOIs	https://doi.org/10.1038/s41597-023-02473-9
Publication status	Published - 7-Sept-2023

Thematic List 2020

Soil & air
Climate

Access to Document

10.1038/s41597-023-02473-9Licence: CC BY

Cite this

Xie, M., Ma, X., Wang, Y., Li, C., Shi, H., Yuan, X., Hellwich, O., Chen, C., Zhang, W., Zhang, C., Ling, Q., Gao, R., Zhang, Y., Ochege, F. U., Frankl, A., De Maeyer, P., Buchmann, N., Feigenwinter, I., Olesen, J. E., ... Luo, G. (2023). Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing. Scientific Data, 10(1). https://doi.org/10.1038/s41597-023-02473-9

@article{5f453ae988544cf394ea5cd3d7e7fc17,

title = "Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing",

abstract = "Simulating the carbon-water fluxes at more widely distributed meteorological stations based on the sparsely and unevenly distributed eddy covariance flux stations is needed to accurately understand the carbon-water cycle of terrestrial ecosystems. We established a new framework consisting of machine learning, determination coefficient (R2), Euclidean distance, and remote sensing (RS), to simulate the daily net ecosystem carbon dioxide exchange (NEE) and water flux (WF) of the Eurasian meteorological stations using a random forest model or/and RS. The daily NEE and WF datasets with RS-based information (NEE-RS and WF-RS) for 3774 and 4427 meteorological stations during 2002–2020 were produced, respectively. And the daily NEE and WF datasets without RS-based information (NEE-WRS and WF-WRS) for 4667 and 6763 meteorological stations during 1983–2018 were generated, respectively. For each meteorological station, the carbon-water fluxes meet accuracy requirements and have quasi-observational properties. These four carbon-water flux datasets have great potential to improve the assessments of the ecosystem carbon-water dynamics.",

author = "Mingjuan Xie and Xiaofei Ma and Yuangang Wang and Chaofan Li and Haiyang Shi and Xiuliang Yuan and Olaf Hellwich and Chunbo Chen and Wenqiang Zhang and Chen Zhang and Qing Ling and Ruixiang Gao and Yu Zhang and Ochege, {Friday Uchenna} and Amaury Frankl and {De Maeyer}, Philippe and Nina Buchmann and Iris Feigenwinter and Olesen, {J{\o}rgen E.} and Radoslaw Juszczak and Adrien Jacotot and Aino Korrensalo and Andrea Pitacco and Andrej Varlagin and Ankit Shekhar and Annalea Lohila and Arnaud Carrara and Aurore Brut and Bart Kruijt and Benjamin Loubet and Bernard Heinesch and Bogdan Chojnicki and Carole Helfter and Caroline Vincke and Changliang Shao and Christian Bernhofer and Christian Br{\"u}mmer and Christian Wille and Eeva-Stiina Tuittila and Eiko Nemitz and Franco Meggio and Gang Dong and Gary Lanigan and Georg Niedrist and Georg Wohlfahrt and Guoyi Zhou and Ignacio Goded and Thomas Gruenwald and Janusz Olejnik and Joachim Jansen and Johan Neirynck and Juha-Pekka Tuovinen and Junhui Zhang and Katja Klumpp and Kim Pilegaard and Ladislav {\v S}igut and Leif Klemedtsson and Luca Tezza and Lukas H{\"o}rtnagl and Marek Urbaniak and Marilyn Roland and Marius Schmidt and Sutton, {Mark A.} and Markus Hehn and Matthew Saunders and Matthias Mauder and Mika Aurela and Mika Korkiakoski and Mingyuan Du and Nadia Vendrame and Natalia Kowalska and Leahy, {Paul G.} and Pavel Alekseychik and Peili Shi and Per Weslien and Shiping Chen and Silvano Fares and Thomas Friborg and Tiphaine Tallec and Tomomichi Kato and Torsten Sachs and Trofim Maximov and {di Cella}, {Umberto Morra} and Uta Moderow and Yingnian Li and Yongtao He and Yoshiko Kosugi and Geping Luo",

year = "2023",

month = sep,

day = "7",

doi = "10.1038/s41597-023-02473-9",

language = "English",

volume = "10",

number = "1",

}

Xie, M, Ma, X, Wang, Y, Li, C, Shi, H, Yuan, X, Hellwich, O, Chen, C, Zhang, W, Zhang, C, Ling, Q, Gao, R, Zhang, Y, Ochege, FU, Frankl, A, De Maeyer, P, Buchmann, N, Feigenwinter, I, Olesen, JE, Juszczak, R, Jacotot, A, Korrensalo, A, Pitacco, A, Varlagin, A, Shekhar, A, Lohila, A, Carrara, A, Brut, A, Kruijt, B, Loubet, B, Heinesch, B, Chojnicki, B, Helfter, C, Vincke, C, Shao, C, Bernhofer, C, Brümmer, C, Wille, C, Tuittila, E-S, Nemitz, E, Meggio, F, Dong, G, Lanigan, G, Niedrist, G, Wohlfahrt, G, Zhou, G, Goded, I, Gruenwald, T, Olejnik, J, Jansen, J, Neirynck, J, Tuovinen, J-P, Zhang, J, Klumpp, K, Pilegaard, K, Šigut, L, Klemedtsson, L, Tezza, L, Hörtnagl, L, Urbaniak, M, Roland, M, Schmidt, M, Sutton, MA, Hehn, M, Saunders, M, Mauder, M, Aurela, M, Korkiakoski, M, Du, M, Vendrame, N, Kowalska, N, Leahy, PG, Alekseychik, P, Shi, P, Weslien, P, Chen, S, Fares, S, Friborg, T, Tallec, T, Kato, T, Sachs, T, Maximov, T, di Cella, UM, Moderow, U, Li, Y, He, Y, Kosugi, Y & Luo, G 2023, 'Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing', Scientific Data, vol. 10, no. 1. https://doi.org/10.1038/s41597-023-02473-9

TY - JOUR

T1 - Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing

AU - Xie, Mingjuan

AU - Ma, Xiaofei

AU - Wang, Yuangang

AU - Li, Chaofan

AU - Shi, Haiyang

AU - Yuan, Xiuliang

AU - Hellwich, Olaf

AU - Chen, Chunbo

AU - Zhang, Wenqiang

AU - Zhang, Chen

AU - Ling, Qing

AU - Gao, Ruixiang

AU - Zhang, Yu

AU - Ochege, Friday Uchenna

AU - Frankl, Amaury

AU - De Maeyer, Philippe

AU - Buchmann, Nina

AU - Feigenwinter, Iris

AU - Olesen, Jørgen E.

AU - Juszczak, Radoslaw

AU - Jacotot, Adrien

AU - Korrensalo, Aino

AU - Pitacco, Andrea

AU - Varlagin, Andrej

AU - Shekhar, Ankit

AU - Lohila, Annalea

AU - Carrara, Arnaud

AU - Brut, Aurore

AU - Kruijt, Bart

AU - Loubet, Benjamin

AU - Heinesch, Bernard

AU - Chojnicki, Bogdan

AU - Helfter, Carole

AU - Vincke, Caroline

AU - Shao, Changliang

AU - Bernhofer, Christian

AU - Brümmer, Christian

AU - Wille, Christian

AU - Tuittila, Eeva-Stiina

AU - Nemitz, Eiko

AU - Meggio, Franco

AU - Dong, Gang

AU - Lanigan, Gary

AU - Niedrist, Georg

AU - Wohlfahrt, Georg

AU - Zhou, Guoyi

AU - Goded, Ignacio

AU - Gruenwald, Thomas

AU - Olejnik, Janusz

AU - Jansen, Joachim

AU - Neirynck, Johan

AU - Tuovinen, Juha-Pekka

AU - Zhang, Junhui

AU - Klumpp, Katja

AU - Pilegaard, Kim

AU - Šigut, Ladislav

AU - Klemedtsson, Leif

AU - Tezza, Luca

AU - Hörtnagl, Lukas

AU - Urbaniak, Marek

AU - Roland, Marilyn

AU - Schmidt, Marius

AU - Sutton, Mark A.

AU - Hehn, Markus

AU - Saunders, Matthew

AU - Mauder, Matthias

AU - Aurela, Mika

AU - Korkiakoski, Mika

AU - Du, Mingyuan

AU - Vendrame, Nadia

AU - Kowalska, Natalia

AU - Leahy, Paul G.

AU - Alekseychik, Pavel

AU - Shi, Peili

AU - Weslien, Per

AU - Chen, Shiping

AU - Fares, Silvano

AU - Friborg, Thomas

AU - Tallec, Tiphaine

AU - Kato, Tomomichi

AU - Sachs, Torsten

AU - Maximov, Trofim

AU - di Cella, Umberto Morra

AU - Moderow, Uta

AU - Li, Yingnian

AU - He, Yongtao

AU - Kosugi, Yoshiko

AU - Luo, Geping

PY - 2023/9/7

Y1 - 2023/9/7

N2 - Simulating the carbon-water fluxes at more widely distributed meteorological stations based on the sparsely and unevenly distributed eddy covariance flux stations is needed to accurately understand the carbon-water cycle of terrestrial ecosystems. We established a new framework consisting of machine learning, determination coefficient (R2), Euclidean distance, and remote sensing (RS), to simulate the daily net ecosystem carbon dioxide exchange (NEE) and water flux (WF) of the Eurasian meteorological stations using a random forest model or/and RS. The daily NEE and WF datasets with RS-based information (NEE-RS and WF-RS) for 3774 and 4427 meteorological stations during 2002–2020 were produced, respectively. And the daily NEE and WF datasets without RS-based information (NEE-WRS and WF-WRS) for 4667 and 6763 meteorological stations during 1983–2018 were generated, respectively. For each meteorological station, the carbon-water fluxes meet accuracy requirements and have quasi-observational properties. These four carbon-water flux datasets have great potential to improve the assessments of the ecosystem carbon-water dynamics.

AB - Simulating the carbon-water fluxes at more widely distributed meteorological stations based on the sparsely and unevenly distributed eddy covariance flux stations is needed to accurately understand the carbon-water cycle of terrestrial ecosystems. We established a new framework consisting of machine learning, determination coefficient (R2), Euclidean distance, and remote sensing (RS), to simulate the daily net ecosystem carbon dioxide exchange (NEE) and water flux (WF) of the Eurasian meteorological stations using a random forest model or/and RS. The daily NEE and WF datasets with RS-based information (NEE-RS and WF-RS) for 3774 and 4427 meteorological stations during 2002–2020 were produced, respectively. And the daily NEE and WF datasets without RS-based information (NEE-WRS and WF-WRS) for 4667 and 6763 meteorological stations during 1983–2018 were generated, respectively. For each meteorological station, the carbon-water fluxes meet accuracy requirements and have quasi-observational properties. These four carbon-water flux datasets have great potential to improve the assessments of the ecosystem carbon-water dynamics.

U2 - 10.1038/s41597-023-02473-9

DO - 10.1038/s41597-023-02473-9

M3 - A1: Web of Science-article

SN - 2052-4463

VL - 10

JO - Scientific Data

JF - Scientific Data

IS - 1

ER -