This paper proposes a novel short-term air temperature prediction with three-layer Back Propagation Neural Network (BPNN) for the regional application of next 1-12 hours. With the continuous collection of eight real-time micro-climate parameters in the experimentation and demonstration stations in our university, the Multiple Stepwise Regression (MSR) is employed to screen the original historical data to find the parameter factors with greater contribution rate. On the basis of the Root Mean Square Error (RMSE) value evaluating the optimal fitting degree of the stepwise regression, the Levenberg-Marquardt (LM) and the Resilient Propagation (R-Prop) training algorithm are employed to construct a Combined BPNN (CBPNN) with two MSR inputs. Compared with the known micro-climate data sets, the Mean Absolute Error (MAE) is to evaluate the applicability of CBPNN prediction model. The experimentation shows that the MAE is within 4°C in the next 12 hours. This proposal will be deployed in stations in our university for extreme weather warnings, and could be applied to some regional short-term parameter prediction for the future agricultural production service.

Recently, due to the rapid economic development and the acceleration of urbanization, haze events have occurred frequently in most parts of China, which has attracted widespread attention at home and abroad. This study presents a statistical summary of air pollution concentrations and traffic state indexes from August 2014 to April 2015 in Shanghai, China. We find PM2.5 concentrations show a remarkable seasonal variability with ``winter > spring > autumn > summer'' in Shanghai. Concentrations of PM2.5, CO, NO2, SO2 are generally higher in winter than in summer due to enhanced anthropogenic and biogenic emissions and unsuitable meteorological conditions for pollution diffusion, contrary to concentrations of O3. The weekly changes of NO2 are highly consistent with that of traffic state indexes, suggesting a significant contribution to NO2 concentrations from road traffic emissions. Two moderate peaks are found in the diurnal variability of concentrations of PM2.5, CO and NO2, similar to road traffic indexes, indicating the important contribution of road traffic emissions every day. We find that SO2, NO2, CO are the dominant factors contributing to PM2.5 pollution, where NO2 and CO are mainly from road traffic emissions. The average annual Spearman correlation coefficient is r = 0.689 (p < 0.01), r = 0.564 (p < 0.01), r = 0.812 (p < 0.01), respectively.