Sign in Subscribe
Artificial neural networks

Advances in Climate Change Research: Estimating Anthropogenic CO2 Emissions in China

Strategic Insights

— 1 min read

A team of researchers from Tsinghua University in Beijing, China, has made a significant breakthrough in estimating anthropogenic CO2 emissions in the country. Using remote sensing measurements and a neural network approach, they have developed a more accurate method to estimate CO2 emissions, which is crucial for effective climate change mitigation policies. The study aimed to improve CO2 emission estimates in China using a combination of remote sensing and machine learning techniques.

Key Takeaways:

  • The researchers used a neural network approach combined with a partition modeling strategy to estimate CO2 emissions based on column-averaged dry air mole fractions of CO2 (XCO2) anomalies, net primary productivity, and population data.
  • The study evaluated the effectiveness of three background XCO2 concentration approaches: CHN (national median), LAT (10-degree latitudinal median), and NE (N-nearest non-emission grids average).
  • The results showed that the NE method outperformed or was at least comparable to the LAT method, while the CHN method performed the worst.
  • Increasing the number of partitions from 1 to 30 using the NE method resulted in mean absolute error (MAE) values decreasing from 0.254 to 0.122 gC/m²/day.
  • Incorporating population data led to a decrease in MAE values between 0.036 and 0.269 gC/m²/day for different partitions.
  • The study concluded that the present methods and findings offer critical insights for supporting government policy-making and target-setting.
  • The research involves a team of authors from Tsinghua University, including Chen Chen, Kaitong Qin, Songjie Wu, Bellie Sivakumar, Chengxian Zhuang, and Jiaye Li.

Statistics:

  • Mean absolute error (MAE) values decreased from 0.254 to 0.122 gC/m²/day when using the NE method to estimate CO2 emissions.
  • Incorporating population data led to a decrease in MAE values between 0.036 and 0.269 gC/m²/day for different partitions.
  • The number of partitions increased from 1 to 30.
  • The study evaluated the effectiveness of three background XCO2 concentration approaches.

Sources:

  • Estimation of Anthropogenic Carbon Dioxide Emissions in China: Remote Sensing with Generalized Regression Neural Network and Partition Modeling Strategy (2025,16(6):631), published in Atmosphere (http://www.mdpi.com/journal/atmosphere/), a journal by MDPI AG.
  • Free version available at https://doi-org.sdpl.idm.oclc.org/10.3390/atmos16060631.

Read more