Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing
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.
Details
| Volume | 10 |
|---|---|
| Tijdschrift nummer | 1 |
| Type | A1: Web of Science-artikel |
| Categorie | Onderzoek |
| Tijdschrift | Scientific Data |
| Issns | 2052-4463 |
| Taal | Engels |
Bibtex
@misc{5f453ae9-8854-4cf3-94ea-5cd3d7e7fc17,
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 Friday Uchenna Ochege and Amaury Frankl and Philippe De Maeyer and Nina Buchmann and Iris Feigenwinter and Jørgen Eivind Olesen 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 Brümmer 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 Šigut and Leif Klemedtsson and Luca Tezza and Lukas Hörtnagl and Marek Urbaniak and Marilyn Roland and Marius Schmidt and Mark A. Sutton 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 Paul G. Leahy 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 Umberto Morra di Cella and Uta Moderow and Yingnian Li and Yongtao He and Yoshiko Kosugi and Geping Luo",
year = "2023",
month = sep,
day = "07",
doi = "https://doi.org/10.1038/s41597-023-02473-9",
language = "Nederlands",
publisher = "Instituut voor Natuur- en Bosonderzoek",
address = "België,
type = "Other"
}
Auteurs
Mingjuan XieXiaofei 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 Eivind 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
