Li et al. (2026) Identifying the influencing factors of lake surface greenhouse gas concentrations using sentinel-2 remote sensing and machine learning: A case study of bird Island, Qinghai Lake

Identification

• Journal: Scientific Reports
• Year: 2026
• Date: 2026-09-07
• Authors: Xingyue Li, Zhen Chen, Lei Li, Dong Han, Kelong Chen
• DOI: 10.1038/s41598-026-67206-5

Research Groups

• Qinghai University
• Institute of Hydroecology, Chinese Academy of Sciences

Short Summary

This study used Sentinel-2 remote sensing imagery and machine learning to identify the influencing factors of lake surface greenhouse gas concentrations in Qinghai Lake. The results showed that temperature and MNDWI were the main predictive factors affecting the variations in CO2, CH4, and H2O concentrations.

Objective

• Identify the key environmental drivers controlling variations in lake surface CO2, CH4, and H2O concentrations in Qinghai Lake

Study Configuration

• Spatial Scale: Bird Island of Qinghai Lake (36°32′−37°15′N, 99°36′−100°16′E)
• Temporal Scale: 2021

Methodology and Data

• Models used: Random Forest (RF), Extreme Gradient Boosting (XGBoost)
• Data sources: Sentinel-2 remote sensing imagery, ERA5-Land hourly time-series data, greenhouse gas concentration measurements

Main Results

• CO2 concentrations remained relatively stable with a small fluctuation range, exhibiting a ‘V’-shaped trend.
• CH4 concentrations were more stable with smaller fluctuations, showing a ‘wave-like’ pattern.
• H2O exhibited substantial fluctuations and had the largest variation amplitude among the three gases.

Contributions

• This study combined observational data, remote sensing imagery, and machine learning to provide new insights into the environmental predictive factors of greenhouse gas concentrations in lakes under climate change.
• The results showed that temperature and MNDWI were the main predictive factors affecting the variations in CO2, CH4, and H2O concentrations.

Funding

• This study was supported by the National Natural Science Foundation of China (Grant No. 52179215)

Citation

@article{Li2026Identifying,
  author = {Li, Xingyue and Chen, Yarong and Chen, Zhen and Li, Lei and Han, Dong and Chen, Kelong},
  title = {Identifying the influencing factors of lake surface greenhouse gas concentrations using sentinel-2 remote sensing and machine learning: A case study of bird Island, Qinghai Lake},
  journal = {Scientific Reports},
  year = {2026},
  doi = {10.1038/s41598-026-67206-5},
  url = {https://doi.org/10.1038/s41598-026-67206-5}
}