Spatiotemporal Patterns of Ecosystem Carbon Fluxes in China Estimated by Eddy Covariance Measurements and Machine Learning

- 304242
Poster
Favorite this paper
How to cite this paper?
Abstract

Accurate estimation of regional and global patterns of ecosystem carbon fluxes is crucial to improve the understanding of terrestrial carbon cycles and predictivity of global carbon budget. However, large uncertainties still exist in regional and global carbon budget estimation. Based on eddy covariance measurements from 132 sites in China from 2002 to 2020, we established an intelligent model (IRF) that integrated ecological understanding with machine learning techniques to estimate regional carbon fluxes. The results showed that the IRF models performed better than semiempirical models and machine learning algorithms. The observed data revealed that the optimal models mainly governed by leaf area index, living plant biomass, soil organic carbon, air temperature, and solar radiation matched 70%~93% of the spatiotemporal variation in site-level carbon fluxes. Using the optimal model, we obtained that the annual value of GPP and ER in China ranged from 6.10 PgC yr−1 to 7.66 PgC yr−1, and 5.05 to 5.84 Pg C yr−1 between 2000 and 2020, with an average value of 7.03 ± 0.45 PgC yr−1 and 5.53 ± 0.22 Pg C yr−1, respectively. The interannual trend and variation of carbon fluxes showed a decreasing trend from east to west and from southeast to northwest. Our results provide a methodological support for mapping regional carbon fluxes and suggest that future models should integrate process-based and data-driven approaches for understanding and evaluating regional and global carbon budgets.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences
Track
  • 4-Measuring and modelling carbon on land
Keywords
Carbon dioxide (CO2) fluxes
Bottom up approaches
climate change
eddy covariance