A micro-pulse lidar system incorporating differential absorption lidar (DIAL) and coherent Doppler wind lidar (CDWL) is proposed and demonstrated. Due to the high signal-to-noise ratio (SNR) of the superconducting nanowire single-photon detector (SNSPD), the DIAL channel achieves high sensitivity in CO2 measurement. Meanwhile, the CDWL channel is used to obtain the horizontal wind field. In the process of the optimization and calibration of the DIAL receiver, specifically, mode scrambling and temperature control of the connecting fiber between the telescope and the SNSPD enhance the stability and robustness of the system. Horizontal scanning of the CO2 concentration and the wind field is carried out in a 6 km range over a scanning span of 60° with a radial resolution of 150 m and 15 s. The results show that the hybrid lidar system captures the spatial distribution of CO2 concentration and the wind field simultaneously. The horizontal net CO2 flux in a radius of 6 km is estimated by integrating the CO2 concentration and the wind transport vector, indicating different characteristics of horizontal net CO2 fluxes in an industrial area, a university campus, and a park. During most of the experiment, CO2 flux remained positive in the industrial area, but balances fell to nearly zero on the campus and in the park. The horizontal net fluxes averaged over 24 h in the three areas are 3.5 × 105 ppm·m2·s−1, 0.7 × 105 ppm·m2·s−1, and 0.1 × 105 ppm·m2·s−1.
Sudden Stratospheric Warmings (SSWs) are extreme polar atmospheric disturbances that significantly impact mid-latitude cold surges, but their early prediction remains a challenge for conventional numerical models. In this study, we propose a video prediction framework for SSW forecasting and introduce a Decoupled Spatiotemporal Memory Flow Network (DSMF-Net) to more effectively capture the dynamic evolution of stratospheric polar vortices. DSMF-Net separates spatial and temporal dependencies using specialized memory flow modules, enabling fine-grained modeling of vortex morphology and dynamic transitions. Experiments on representative SSW events from 2018 to 2021 show that DSMF-Net can reliably predict SSW occurrences up to 20 days in advance while accurately replicating the evolution of polar vortex structures. Compared to baseline models such as the Predictive Recurrent Neural Network (PredRNN) and Motion Recurrent Neural Network (MotionRNN), our method achieves consistent improvements across various metrics, with average gains of 10.5% in Mean Squared Error (MSE) and 6.4% in Mean Absolute Error (MAE) and a 0.7% increase in the Structural Similarity Index Measure (SSIM). These findings underscore the potential of deep video prediction frameworks to improve medium-range stratospheric forecasts and bridge the gap between data-driven models and atmospheric dynamics.