Carbon dioxide (CO₂) is a key driver of global climate change. Since the Industrial Revolution, the rapid rise in atmospheric CO₂ levels has significantly intensified global warming and climate-related issues. To accurately and promptly monitor changes in CO₂ concentrations and to support the development of climate policies, this study proposes a method based on random forest models to generate a continuous monthly dataset of CO₂ column concentration (XCO₂) across the entire Chinese region from 2004 to 2023. The study integrates XCO₂ satellite observations from SCIAMACHY, GOSAT, OCO-2, and GF-5B, alongside nighttime light remote sensing data, meteorological parameters, vegetation indices, and CO₂ profile data. Using the random forest algorithm, a complex relationship model was established between XCO₂ concentrations and various environmental variables. The goal of this model is to provide XCO₂ estimates with enhanced spatial coverage and accuracy. The XCO₂ concentrations predicted by the model show a high level of consistency with satellite observations, achieving a correlation coefficient (R-value) of 0.9959 and a root mean square error (RMSE) of 1.1631 ppm. This indicates that the model offers strong predictive accuracy and generalization ability. Additionally, ground-based validation further confirmed the model’s effectiveness, with a correlation coefficient (R-value) of 0.956 when compared with TCCON site observation data.

The use of satellite data to estimate PM_2.5 is an appropriate approach for long-term, substantial monitoring and assessment. To estimate PM_2.5, the majority of the algorithms now in use utilize the top-of-atmosphere (TOA) reflectance or aerosol optical depth (AOD) derived from scalar satellite data. However, there is relatively little research on the retrieval of PM_2.5 using multi-angle polarized data. With its directional polarimetric camera (DPC), the Chinese new-generation satellite Gaofen 5B (henceforth referred to as GF-5B) offers a unique opportunity to close this gap in multi-angle polarized observation data. In this research, we utilized TOA data from the DPC payload and applied the gradient boosting machine method to simulate the impact of the observation angle, wavelength, and polarization information on the accuracy of PM_2.5 retrieval. We identified the optimal conditions for the effective estimation of PM_2.5. The quantitative results indicated that, under these optimal conditions, the PM_2.5 concentrations retrieved by GF-5B showed a strong correlation with the ground-based data, achieving an R² of 0.9272 and an RMSE of 7.38 µg·m⁻³. By contrast, Himawari-8’s retrieval accuracy under similar data conditions consisted of an R² of 0.9099 and RMSE of 7.42 µg·m⁻³, indicating that GF-5B offers higher accuracy. Furthermore, the retrieval results in this study demonstrated an R² of 0.81 when compared to the CHAP dataset, confirming the feasibility and effectiveness of the use of GF-5B for PM_2.5 retrieval and providing support for PM_2.5 estimation through multi-angle polarized data.

The Wide-Swath Imaging (WSI) sensor is a Chinese satellite launched in 2022, capable of providing data at resolutions ranging from 75 to 600 m for monitoring aerosols, fire points, and dust, among other uses. In this study, we developed a Dark Dense Vegetation method to retrieve the Aerosol Optical Depth (AOD) quickly from WSI 600 m data. First, after splitting into three types according to the Normalized Difference Vegetation Index (NDVI), we calculated the empirical parameters of land reflectance between the red (0.65 μm) and blue (0.47 μm) channels using Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance products over the Beijing area. Second, the decrease in the NDVI was simulated and analyzed under different AODs and solar zenith angles, and we introduced an iterative inversion approach to account for it. The simulation retrievals demonstrated that the iterative inversion produced accurate results after less than four iterations. Thirdly, we utilized the atmospherically corrected NDVI for dark target identification and output the AOD result. Finally, retrieval experiments were conducted using WSI 600 m data collected over Beijing in 2023. The retrieved AOD images highlighted two air pollution events occurring during 3–8 March and 27–31 October 2023. The inversion results in 2023 showed a strong correlation with Aerosol Robotic Network station data (the correlation coefficient was greater than 0.9). Our method exhibited greater accuracy than the MODIS aerosol product, though it was less accurate than the Multi-Angle Implementation of Atmospheric Correction product.