Forest Soil Carbon Efflux Evaluation Across China: A New Estimate With Machine Learning

Forest soil respiration (Rs) plays an important role in the carbon balance of terrestrial ecosystems. China's forest occupies a large part of the world's forest. However, due to the lack of integrated observation data and appropriate upscaling methodologies, substantial uncertainties exist in the Rs evaluation, which limits our understanding of the carbon balance. Here, we re-evaluated the total soil carbon effluxes across China by combining field observations from 634 published annual Rs with a machine learning technique (i.e., Random Forest (RF)). Our results revealed that the combination of systematic measurements with the RF model allowed a definite estimate. The average annual Rs was 776.9 g C m(-2) yr(-1), ranging from 411.5 to 1,770.7 g C m(-2) yr(-1). Total forest soil carbon effluxes amounted to 1.17 Pg C yr(-1) in China. Geographically, annual Rs showed a clear spatially increasing trend from northeast to southwest. Forest type is an important factor in determining the soil respiration rate. Bamboo and Evergreen broadleaf forests were higher than other types of forests. These results provide a unique insight into the magnitudes and mechanisms of soil CO(2 )emissions in China's forest ecosystems. Soil respiration refers to the soil-to-atmosphere flux of CO2, primarily generated by root and microbial respiration. Accurate assessment of forest soil respiration in China is a significant part of global-scale carbon cycles. However, due to the lack of integrated observation data and appropriate upscaling methodologies, substantial uncertainties exist in soil respiration evaluation. Here, we assembled a new database and used a random forest approach to re-explore the total forest soil respiration and obtained reliable annual forest soil carbon efflux in China. These results contribute to a better understanding and quantification of the national and global carbon cycle.

Automated summary

Forest soil respiration (Rs) is crucial for the carbon balance of terrestrial ecosystems, but uncertainties exist in its evaluation in China due to the lack of integrated observation data and appropriate upscaling methodologies. This study used a machine learning technique (Random Forest) to re-evaluate the total forest soil carbon effluxes in China, providing reliable estimates and insights into soil CO2 emissions in China's forest ecosystems. The average annual Rs was 776.9 g C m(-2) yr(-1), with a total of 1.17 Pg C yr(-1).