TECIS-CASNet: atmospheric hierarchy identification and application of the terrestrial ecosystem carbon inventory satellite

The TECIS (Terrestrial Ecosystem Carbon Inventory Satellite), launched in August 2022, achieves high-resolution stereo monitoring of atmospheric clouds and aerosols through multibeamLiDAR and multispectral cameras. Traditional algorithms struggle with accuracy and robustness in vertical layer retrieval under complex conditions. Here, we propose TECIS-CASNet, a universal framework for atmospheric layer identification, integrating TECIS and CALIOP with deep learning transformer theories. To demonstrate its advantage, we applied it to analyze the spatiotemporal distribution of cloud, aerosol, and dust in the Beijing–Tianjin–Hebei (BTH) region of China, where cloud-aerosol variability is high due to topography, climate, and human activity. The TECIS-CASNet improved classification by approximately 15% compared with traditional algorithms, especially under low signal-to-noise ratio and other complex situations. Furthermore, it achieved 95%accuracy with absolute accuracy of 0.01 in optical depth inversion. The framework identified dust transport from central Inner Mongolia (linked to potential deforestation), significantly affecting near-ground air quality. The TECIS-CASNet has great potential for satellite LiDAR data processing and climate change.