PM2.5 Concentration Identification Based on Lidar Detection

For the difficulty in measuring the distribution characteristics of PM2.5, concentration in the atmosphere, we used 532 nm lidar to continuously observe the Huainan arca from June 1st to December 31st, 2016. A regression prediction model was established concerning the atmospheric boundary layer height, aerosol optical depth, temperature, relative humidity, wind speed, visibility, and measured PM2.5, concentration to identify the PM2.5, concentration. Since the traditional backpropagation neural network (HP) was prone to the local minimum, we adopted a genetic algorithm-based backpropagation neural network (GA-BP) according to the data characteristics and applied the genetic algorithm to finding the optimal weights and thresholds, balancing global and local contradictions. A comparison of the two regression models demonstrates that the GA-HP method is significantly better than the HP method. The correlation index R-2 of the test set and the mean forecast error arc respectively 0.623 and 21.692 mu g/m(3) for the HP method, and 0.899 and 7.122 mu g/m(3) for the GA-HP method. These results indicate that lidar can effectively monitor the PM2.5, distribution in the atmosphere and provide data support and reference for the monitoring of atmospheric PM2.5, in the Huainan area.