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

Alpine lakes on the Qinghai-Tibet Plateau are important regions for studies of the regional carbon cycle and are highly sensitive to climate change. However, the variation patterns of lake surface greenhouse gases and their environmental regulation mechanisms remain unclear. In this study, Bird Island of Qinghai Lake was selected as the study area. Based on the measured concentrations of lake surface CO 2 , CH 4 , and H 2 O corresponding to Sentinel-2 satellite overpass periods throughout 2021, combined with Sentinel-2 remote sensing imagery and ERA5-Land meteorological data, Random Forest (RF) and Extreme Gradient Boosting (XGBoost) models, together with the SHAP method, were used to identify and predict the influencing factors and their contribution characteristics to the variations in lake surface CO 2 , CH 4 , and H 2 O. The results showed that CO 2 , CH 4 , and H 2 O exhibited distinct seasonal variations. The annual variation in CO 2 concentration generally showed a “V”-shaped pattern, with concentrations during the growing season being lower than those during the non-growing season. The annual variation in CH 4 concentration was relatively small and exhibited a “wave”-shaped pattern. The H 2 O concentration showed a distinct unimodal pattern, and its high-value period was generally consistent with the low-value period of CO 2 . Temperature and MNDWI were the main predictive factors affecting the variations in CO 2 , CH 4 , and H 2 O concentrations, while H 2 O concentration was also affected by Radiation. This study combined observational data, remote sensing imagery, and machine learning, providing new insights into the environmental predictive factors of greenhouse gas concentrations in lakes under climate change.