With the rapid development of industrialization and urbanization, air pollution is increasing at an alarming rate in many developing countries. The four air pollutants which are becoming a concerning threat to human health are namely respirable particulate matter, nitrogen oxides, particulate matter and sulphur dioxide. The models which are currently used for air quality prediction by comparing to the AQI indexes do not give satisfactory results, which inspired us to examine the methods of predicting air quality based on deep learning using the K-Mean Clustering algorithm and Image Processing Technique. The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of air computing. A good interpolation helps to estimate the limited air quality monitoring stations whose distribution is uneven in a city; an accurate prediction provides valuable information to protect humans and take necessary measures to reduce the effect of air pollution; a reasonable feature analysis is used to provide a more effective and general model. Overall, finding solutions to these topics can bring out extremely useful information to support air pollution control, and consequently generate great societal and technical impacts.
Paper
Full text
Analysis of Fine Gained Air Quality Using Deep Learning
Semantic Scholar · Environmental Science · 2021
Abstract
With the rapid development of industrialization and urbanization, air pollution is increasing at an alarming rate in many developing countries. The four air pollutants which are becoming a concerning threat to human health are namely respirable particulate matter, nitrogen oxides, particulate matter and sulphur dioxide. The models which are currently used for air quality prediction by comparing to the AQI indexes do not give satisfactory results, which inspired us to examine the methods of predicting air quality based on deep learning using the K-Mean Clustering algorithm and Image Processing Technique. The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of air computing. A good interpolation helps to estimate the limited air quality monitoring stations whose distribution is uneven in a city; an accurate prediction provides valuable information to protect humans and take necessary measures to reduce the effect of air pollution; a reasonable feature analysis is used to provide a more effective and general model. Overall, finding solutions to these topics can bring out extremely useful information to support air pollution control, and consequently generate great societal and technical impacts.