The Prediction Model of Air Quality in Changsha City Based on Artificial Neural Network

Abstract

The air quality is a hot topic noticed by all the present society. Although modern technology has helped to collect data of the air position, the huge amount of irregular data also makes it hard to detect the pattern of air pollution. Therefore, this research is to apply data mining to the analysis of the air quality. Data mining is a comprehensive mining of information including trends, features and correlations hidden in data. Data mining can extract the value of data which was not known from numerous random data. This research is based on the daily average values of six major pollutants in Changsha from January 1, 2015, to December 31, 2017, and analyzes the relationship between the air quality and socioeconomic factors of Changsha to establish a prediction model using B-P back propagation neural network. The final model of the research fits the actual data well and predicts the future value of API precisely. However, considering the slow convergence rate and the addition of new samples which may affect the previously learnt samples, further exploration on the B-P neural network model can be launched with other mathematical theories.