Air Pollution Source Identification by Using Neural Network with Bayesian Optimization

To accurately locate pollution sources, in this research, we first create an air-pollution identification system, called Air Pollution Source Identification System (APSIS), which adopts tensorflow to establish three neural-network based analytical models with which to find the sources of air pollution. The APSIS collects environmental data in a relatively smaller grid area. Next, collected data are tuned when necessary to prevent the APSIS built by collected data from being seriously affected by outlier and other unstable factors, like wind direction. The purpose is to identify possible distribution of pollution and then more accurately find out the sources. After that, the APSIS is applied to identify the sources of air pollution in a wide area. Source identification accuracies of these neural networks are compared with other air diffusion models, aiming to develop one which is suitable for identifying the air pollution sources.