A Multi-Model Sensitivity Analysis Framework for Environmental-Factor-Driven Atmospheric CO2 Variations Based on Ground-Based Raman Lidar Observations

Atmospheric CO2 variations at regional scales reflect boundary-layer mixing, meteorological conditions, and combustion-related emissions, yet their relative contributions remain difficult to separate with single-model analyses. This study develops a multi-model framework for ground-based Raman lidar observations in Nanyang, Henan Province, integrating physically inspired diffusion and mixing proxies, an XGBoost/Ensemble attribution model, a physics-guided gradient-regularized neural network (PG-GRNN), and Granger time-predictability testing. The analysis used 22,942 quality-controlled samples and vertically averaged CO2 concentrations from 210 to 600 m. The multi-model comparison identified pressure, temperature, humidity, NO2, and SO2 as the most consistent factors associated with CO2 variability. Granger analysis further showed significant lagged predictive relationships for NO2, pressure, SO2, temperature, and humidity, with optimal lag orders of 2, 9, 9, 7, and 10, respectively. PG-GRNN reached high prediction accuracy (R2 = 0.9744; MSE = 15.41), while the complete comparison showed that temporal predictability, physics-guided learning, and physically inspired proxies captured complementary aspects of the CO2 response. The framework provides an interpretable route for combining ground-based lidar, environmental monitoring, and time-series analysis to support regional carbon monitoring and remote-sensing product validation.