With the acceleration of urbanization in China, haze is becoming a growing threat to human health. However, comprehensive research on the diffusion and evolution of PM2.5 is still lacking. Therefore, this study proposes an improved Gaussian smoke plume model considering the influence of multiple factors such as rain wash, gravity sedimentation, and surface rebound on PM2.5. Additionally, the evolution of PM2.5 was predicted by selecting 9 factors that had large influences on PM2.5. In the prediction, support vector machine and Radial Basis Function kernel function were adopted to construct classifiers and obtain the maximum distinction degree, respectively. Finally, the diffusion simulation and experimental evolution prediction were verified using data obtained from nine PM2.5 monitoring stations in Wuhan. The experimental results showed that the algorithm could obtain considerably accurate simulation results of PM2.5 diffusion, had low error with measured values, and has significance in government plans for formulating planning strategies of controlling and reducing environment pollution.