Dataset Information

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.

SUBMITTER: Xie M

PROVIDER: S-EPMC10485062 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

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

Scientific data 20230907 1

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<sup>2</sup>), Euclidean distance, and remote sensing (RS), to simulate the daily net ecosystem carbon dioxide exchange (NEE) and water flux (WF) of the Eurasian ...[more]

PMID: 37679357

Similar Datasets

Project description:Countries have pledged to different national and international environmental agreements, most prominently the climate change mitigation targets of the Paris Agreement. Accounting for carbon stocks and flows (fluxes) is essential for countries that have recently adopted the United Nations System of Environmental-Economic Accounting - ecosystem accounting framework (UNSEEA) as a global statistical standard. In this paper, we analyze how spatial carbon fluxes can be used in support of the UNSEEA carbon accounts in five case countries with available in-situ data. Using global multi-date biomass map products and other remotely sensed data, we mapped the 2010-2018 carbon fluxes in Brazil, the Netherlands, the Philippines, Sweden and the USA using National Forest Inventory (NFI) and local biomass maps from airborne LiDAR as reference data. We identified areas that are unsupported by the reference data within environmental feature space (6-47% of vegetated country area); cross-validated an ensemble machine learning (RMSE=9-39 Mg C [Formula: see text] and [Formula: see text]=0.16-0.71) used to map carbon fluxes with prediction intervals; and assessed spatially correlated residuals (<5 km) before aggregating carbon fluxes from 1-ha pixels to UNSEEA forest classes. The resulting carbon accounting tables revealed the net carbon sequestration in natural broadleaved forests. Both in plantations and in other woody vegetation ecosystems, emissions exceeded sequestration. Overall, our estimates align with FAO-Forest Resource Assessment and national studies with the largest deviations in Brazil and USA. These two countries used highly clustered reference data, where clustering caused uncertainty given the need to extrapolate to under-sampled areas. We finally provide recommendations to mitigate the effect of under-sampling and to better account for the uncertainties once carbon stocks and flows need to be aggregated in relatively smaller countries. These actions are timely given the global initiatives that aim to upscale UNSEEA carbon accounting.

Project description:Nature-based climate solutions are a vital component of many climate mitigation strategies, including California's, which aims to achieve carbon neutrality by 2045. Most carbon offsets in California's cap-and-trade program come from improved forest management (IFM) projects. Since 2012, various landowners have set up IFM projects following the California Air Resources Board's IFM protocol. As many of these projects approach their 10th year, we now have the opportunity to assess their effectiveness, identify best practices, and suggest improvements toward future protocol revisions. In this study, we used remote sensing-based datasets to evaluate the carbon trends and harvest histories of 37 IFM projects in California. Despite some current limitations and biases, these datasets can be used to quantify carbon accumulation and harvest rates in offset project lands relative to nearby similar "control" lands before and after the projects began. Five lines of evidence suggest that the carbon accumulated in offset projects to date has generally not been additional to what might have otherwise occurred: (1) most forests in northwestern California have been accumulating carbon since at least the mid-1980s and continue to accumulate carbon, whether enrolled in offset projects or not; (2) harvest rates were high in large timber company project lands before IFM initiation, suggesting they are earning carbon credits for forests in recovery; (3) projects are often located on lands with higher densities of low-timber-value species; (4) carbon accumulation rates have not yet increased on lands that enroll as offset projects, relative to their pre-enrollment levels; and (5) harvest rates have not decreased on most project lands since offset project initiation. These patterns suggest that the current protocol should be improved to robustly measure and reward additionality. In general, our framework of geospatial analyses offers an important and independent means to evaluate the effectiveness of the carbon offsets program, especially as these data products continue improving and as offsets receive attention as a climate mitigation strategy.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets