EUVIMEDEUVIMED entdecken
Crossref

Disentangling the Impacts of Air Pollution on Vegetation Photosynthesis Over China Using an Explainable Machine Learning Approach

Lingyan Liu, Haoran Yin, Zhaoyang Zhang, Yunhui Tan, Quan Wang

IEEE Transactions on Geoscience and Remote Sensing · 2026 · 64 · 4419512-4419512

DOI: 10.1109/tgrs.2026.3743776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2026. Verfasst von Lingyan Liu und 4 weiteren Autor:innen. Die Arbeit nennt 77 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid industrialization in China has severely influenced the atmospheric composition. Many models were developed to investigate the impacts of air pollution on vegetation photosynthesis. However, current models show large uncertainties in estimating the impacts of air pollution on vegetation photosynthesis. To accurately estimate the influence of air pollution on vegetation photosynthesis, we established an explainable data-driven model using the eXtreme Gradient Boosting (XGBoost) algorithm by utilizing Tropospheric Monitoring Instrument (TROPOMI)-derived solar-induced chlorophyll fluorescence (SIF) coupled with ERA5-Land meteorology, Clouds and the Earth’s Radiant Energy System (CERES) radiation, and High-resolution and High-quality Air Pollutants Dataset for China (CHAP) atmospheric pollutant data. The model can well capture the variability of SIF, with a coefficient of determination (R ${}^{2}$ ) of 0.87. Results showed that air pollutants reduced terrestrial photosynthesis by approximately 15%–20% in eastern China. Ozone (O ${}_{3}$ ) is the dominant stressor across 67.4% of the region, with its maximum spatial suppression approaching −0.06 mW $\cdot $ m ${}^{-2}\cdot $ sr ${}^{-1}\cdot $ nm ${}^{\mathrm {-1~ }}$ in northeastern and southwestern regions. Aerosol radiative effects further suppressed SIF, with a maximum monthly mean of approximately −0.028 mW $\cdot $ m ${}^{-2}\cdot $ sr ${}^{-1}\cdot $ nm−1 during summer, with the most pronounced impacts observed over southern and eastern regions. Nitrogen dioxide (NO ${}_{2}$ ) exhibited a weak negative effect. The negative effects of air pollution increased over the study period, largely due to the growing influence of O3. This data-driven approach provides a crucial framework for quantifying the impacts of air pollution on terrestrial carbon sinks.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, L., Yin, H., Zhang, Z., Tan, Y., & Wang, Q. (2026). Disentangling the Impacts of Air Pollution on Vegetation Photosynthesis Over China Using an Explainable Machine Learning Approach. IEEE Transactions on Geoscience and Remote Sensing, 64, 4419512-4419512. https://doi.org/10.1109/tgrs.2026.3743776

Vancouver

Liu L, Yin H, Zhang Z, Tan Y, Wang Q. Disentangling the Impacts of Air Pollution on Vegetation Photosynthesis Over China Using an Explainable Machine Learning Approach. IEEE Transactions on Geoscience and Remote Sensing. 2026;64:4419512-4419512. doi:10.1109/tgrs.2026.3743776

BibTeX
@article{Liu2026,
  author = {Liu, Lingyan and Yin, Haoran and Zhang, Zhaoyang and Tan, Yunhui and Wang, Quan},
  title = {Disentangling the Impacts of Air Pollution on Vegetation Photosynthesis Over China Using an Explainable Machine Learning Approach},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  volume = {64},
  pages = {4419512--4419512},
  doi = {10.1109/tgrs.2026.3743776}
}
Kostenlos starten →