Association discovery and outlier detection of air pollution emissions from industrial enterprises driven by big data

Abstract

Air pollution is a major issue related to national economy and people’s livelihood. At present, the researches on air pollution mostly focus on the pollutant emissions in a specific industry or region as a whole, and is a lack of attention to enterprise pollutant emissions from the micro level. Limited by the amount and time granularity of data from enterprises, enterprise pollutant emissions are still understudied. Driven by big data of air pollution emissions of industrial enterprises monitored in Beijing-Tianjin-Hebei, the data mining of enterprises pollution emissions is carried out in the paper, including the association analysis between different features based on grey association, the association mining between different data based on association rule and the outlier detection based on clustering. The results show that: (1) The industries affecting NOx and SO2 mainly are electric power, heat production and supply industry, metal smelting and processing industries in Beijing-Tianjin-Hebei; (2) These districts nearby Hengshui and Shijiazhuang city in Hebei province form strong association rules; (3) The industrial enterprises in Beijing-Tianjin-Hebei are divided into six clusters, of which three categories belong to outliers with excessive emissions of total VOCs, PM and NH3 respectively.