Atmospheric particulate matter is regarded as one of the most serious air pollutants that endanger human health. Lidar detection is a viable method for achieving high-precision particle distribution measurements. To some extent, the aerosol extinction coefficient reflects the relative size of aerosol mass concentration. Meteorological elements, such as temperature, relative humidity, wind speed, and surface pressure, have a significant impact on the extinction coefficient and mass concentration. In this study, a dataset of PM_2.5 and PM₁₀ was created by combining the extinction coefficient obtained from lidar and surface meteorological elements such as temperature, relative humidity, wind speed, and surface pressure. The data characteristics were calculated using principal component analysis. The mass concentration of PM_2.5 and PM₁₀ were estimated using the generalized regression neural network (GRNN) model. The results show that the correlation coefficients between the estimated mass concentrations obtained by the GRNN model and the true values collected from environmental monitoring stations for PM_2.5 and PM₁₀ were 0.86 and 0.85, respectively. Moreover, the root mean square errors (RMSEs) were 2.58 μm/cm³ and 10.84 μm/cm³, and the mean absolute deviations (MAEs) were 0.81 μg/m³ and 1.53 μg/m³ for PM_2.5 and PM_10,respectively. The GRNN model was applied to lidar scanning mode to evaluate the horizontal distribution characteristics of particle over Pukou District of Nanjing. The estimated mass concentrations of PM_2.5 and PM₁₀ were consistent with the measured values, demonstrating the GRNN model’s effectiveness in particle mass concentration evaluation.

The aerosol extinction coefficient, wind speed, temperature, relative humidity, and surface pressure were used as input variables in the GRNN, and the PM_2.5 and PM₁₀ mass concentrations were used as output variables for model training and verification. First, principal component analysis was used to calculate the characteristics of sample data, and the effects of various meteorological factors on aerosol mass concentration were fully considered. Furthermore, the better evaluation model was continuously trained by adjusting parameters. The GRNN evaluation model was used to evaluate the temporal and spatial changes of particulate matter mass concentration in the Pukou District of Nanjing. Simultaneously, it was verified and analyzed in conjunction with ground meteorological elements and data from environmental monitoring stations.

The GRNN model was used to establish and validate an evaluation model of PM_2.5 and PM₁₀ mass concentrations based on the extinction coefficient obtained from lidar and surface meteorological factors. The correlation coefficients between the estimated mass concentrations obtained by the GRNN model and the measured values were 0.86 and 0.85, the RMSE were 2.58 μg/m³ and 10.84 μg/m³, and the mean absolute errors (MAE) were 0.81 μg/m³ and 1.53 μg/m³ for PM_2.5 and PM_10,respectively. The GRNN model was also used to estimate and analyze particulate matter mass concentration using lidar horizontal scanning. The trend of the model’s evaluation values were consistent with the measured values from the environmental monitoring station.

The aerosol extinction coefficient was calculated using the GRNN model and the lidar inversion result. The correlation model was constructed using the hourly mean value of mass concentration. The model variables were screened using principal component analysis, and K-fold cross-validation was performed on the training data. The optimal sliding factor was chosen using the minimum mean square error index. The output model’s results were reliable, with correlation coefficients between predicted and actual values of 0.86 and 0.85 for PM_2.5 and PM₁₀ mass concentrations, respectively. Moreover, the RMSEs were 2.58 μg/m³ and 10.84 μg/m³ and the average absolute errors were 0.81 μg/m³ and 1.53 μg/m³, for PM_2.5 and PM₁₀ mass concentration, respectively. The Pukou District in Nanjing was observed horizontally using lidar, combined with local temperature, relative humidity, wind speed, surface pressure, extinction coefficient, the GRNN model was employed to estimate the mass concentrations of PM_2.5 and PM₁₀. The correlation analysis results between the estimated mass concentration of PM_2.5 and PM₁₀ and the measured values collected from the environmental monitoring station further validated the GRNN model’s accuracy. The results demonstrated that the model could be used to monitor PM_2.5 and PM₁₀ mass concentrations using lidar, and it provided a new method of monitoring particulate matter pollution over a wide range with high temporal and spatial resolutions.