Prediction algorithm of PM2.5 mass concentration based on adaptive BP neural network

• Published in: Computing Vol. 100; no. 8; pp. 825 - 838
• Main Author: Chen, Yegang
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.08.2018; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computer Appl. in Administrative Data Processing; Computer Communication Networks; Computer Science; Impact analysis; Information Systems Applications (incl.Internet); Machine learning; Mathematical models; Neural networks; Remote sensing; Software Engineering; Pulmonary particulate matter; BP neural network; 65Y05; 62H12; PM2.5 mass concentration; Prediction
• ISSN: 0010-485X; 1436-5057
• DOI: 10.1007/s00607-018-0628-3

PM2.5 hadn’t received much attention until 2013 when people started to understand its dreadful impacts to human health. According to the meteorological monitoring data of PM2.5 from September 9, 2016 to September 9, 2017 in Fuling district, Chongqing, this paper analyzed the impact of temperature, humidity and the power of wind on PM2.5. Using the mathematical model of BP neural networks, a prediction model based on satellite remote sensing data for the pollutant concentration in regional scale was explored, and the forecast for Fuling 3-h PM2.5 concentration was realized. The algorithm effectively establishes the correlation between AOD and PM2.5 concentration, and it suppresses the overfitting phenomenon very well, as well as it makes up the limitation of machine learning for single site prediction.