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

Monitoring of carbon-water fluxes at Eurasian meteorological stations using random forest and remote sensing. 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., 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., 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., Zhang, J., Klumpp, K., Pilegaard, K., Šigut, L., Klemedtsson, L., Tezza, L., Hörtnagl, L., Urbaniak, M., Roland, M., Schmidt, M., Sutton, M. A., Hehn, M., Saunders, M., Mauder, M., Aurela, M., Korkiakoski, M., Du, M., Vendrame, N., Kowalska, N., Leahy, P. G., Alekseychik, P., Shi, P., Weslien, P., Chen, S., Fares, S., Friborg, T., Tallec, T., Kato, T., Sachs, T., Maximov, T., Di Cella, U. M., Moderow, U., Li, Y., He, Y., Kosugi, Y., & Luo, G. Scientific Data, 10(1):587, September, 2023.

Paper doi abstract bibtex

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 (R 2 ), 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.

@article{xie_monitoring_2023,
	title = {Monitoring of carbon-water fluxes at {Eurasian} meteorological stations using random forest and remote sensing},
	volume = {10},
	issn = {2052-4463},
	url = {https://www.nature.com/articles/s41597-023-02473-9},
	doi = {10.1038/s41597-023-02473-9},
	abstract = {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 (R
              2
              ), 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.},
	language = {en},
	number = {1},
	urldate = {2024-11-15},
	journal = {Scientific Data},
	author = {Xie, Mingjuan and Ma, Xiaofei and Wang, Yuangang and Li, Chaofan and Shi, Haiyang and Yuan, Xiuliang and Hellwich, Olaf and Chen, Chunbo and Zhang, Wenqiang and Zhang, Chen and Ling, Qing and Gao, Ruixiang and Zhang, Yu and Ochege, Friday Uchenna and Frankl, Amaury and De Maeyer, Philippe and Buchmann, Nina and Feigenwinter, Iris and Olesen, Jørgen E. and Juszczak, Radoslaw and Jacotot, Adrien and Korrensalo, Aino and Pitacco, Andrea and Varlagin, Andrej and Shekhar, Ankit and Lohila, Annalea and Carrara, Arnaud and Brut, Aurore and Kruijt, Bart and Loubet, Benjamin and Heinesch, Bernard and Chojnicki, Bogdan and Helfter, Carole and Vincke, Caroline and Shao, Changliang and Bernhofer, Christian and Brümmer, Christian and Wille, Christian and Tuittila, Eeva-Stiina and Nemitz, Eiko and Meggio, Franco and Dong, Gang and Lanigan, Gary and Niedrist, Georg and Wohlfahrt, Georg and Zhou, Guoyi and Goded, Ignacio and Gruenwald, Thomas and Olejnik, Janusz and Jansen, Joachim and Neirynck, Johan and Tuovinen, Juha-Pekka and Zhang, Junhui and Klumpp, Katja and Pilegaard, Kim and Šigut, Ladislav and Klemedtsson, Leif and Tezza, Luca and Hörtnagl, Lukas and Urbaniak, Marek and Roland, Marilyn and Schmidt, Marius and Sutton, Mark A. and Hehn, Markus and Saunders, Matthew and Mauder, Matthias and Aurela, Mika and Korkiakoski, Mika and Du, Mingyuan and Vendrame, Nadia and Kowalska, Natalia and Leahy, Paul G. and Alekseychik, Pavel and Shi, Peili and Weslien, Per and Chen, Shiping and Fares, Silvano and Friborg, Thomas and Tallec, Tiphaine and Kato, Tomomichi and Sachs, Torsten and Maximov, Trofim and Di Cella, Umberto Morra and Moderow, Uta and Li, Yingnian and He, Yongtao and Kosugi, Yoshiko and Luo, Geping},
	month = sep,
	year = {2023},
	pages = {587},
}

Downloads: 0