基于多源数据的像元尺度东北三省夜间PM2.5估算OA北大核心CSTPCD

Climate change and forest vegetation affect the distribution of PM2.5 concentrations,and PM2.5 as an important air pol-lutant can also affect forest vegetation growth directly or indirectly.Currently,the technique of inverting daytime PM2.5 based on opti-cal aerosol thickness(AOD)data is relatively mature,and as a complement to daytime PM2.5,nighttime PM2.5 is of great significance for the all-day PM2.5 monitoring.Based on the radiation transmission theory,the machine learning estimation model of nighttime PM2.5 concentration in the three northeastern provinces was established with nighttime light brightness,enhanced vegetation index and seven meteorological factors(2 m dewpoint temperature,2 m temperature,u component of wind speed,v component of wind speed,atmo-spheric surface pressure,evaporation,precipitation)as input variables,and nighttime PM2.5 concentration as response variable,aim-ing to provide a reference for monitoring nighttime PM2.5 concentration in the three northeastern provinces.The results show that the model constructed based on the integration tree has high estimation accuracy,with a goodness of fit(R2)of 0.68,a mean absolute error(MAE)of 7.05 μg/m3,and a root mean square error(RMSE)of 11.62 μg/m3.In addition,the model is found to have certain spatial and temporal sensitivity by analyzing the errors between the estimated and true PM2.5 values at each monitoring station in the three northeastern provinces.It can provide a reference for the forest vegetation conservation work by timely and accurately controlling the distribution of nighttime PM2.5 concentration.