Ambient Air Quality Estimation using Supervised Learning Techniques

Abstract

The exponential increase of population in the urban areas has led to deforestation and industrialization that greatly affects the air quality. The polluted air affects the human health. Due to this concern, the prediction of air quality has become a potential research area. For the assessment of air quality an important indicator is Air Quality Index (AQI). The objective of this paper is to build prediction models using supervised learning. Supervised Learning is broadly classified into: classification, regression and ensemble techniques. This study has been carried out using various techniques of classification, regression and ensemble learning. It has been observed from experimental work that Decision Trees from classification, Support Vector Regression from regression and Stacking Ensemble from ensemble techniques work more effectively and efficiently than the rest of the other techniques that fall under these categories.

Enhancing risk communication and environmental crisis management through satellite imagery and AI for air quality index estimation

“…In this first experiment, following up from our previous work (in which we predicted only the class of air quality according to the Pollution Control Department, Ministry of Natural Resources and Environment of Thailand standards: Very good, Good, Satisfactory, Unhealthy, and Very Unhealthy [ 12 ]–not the actual AQI values), we re-test our model in the classfification part (the first part of the proposed hybrid model) to see if the same model and accuracy performance still holds in the classification part of the model. In our previous paper [ 24 ], we reported that Random Forest model performed the best with an averaged accuracy of 0.914, averaged precision of 0.89, averaged recall of 0.814, and an averaged F-1 score of 0.84825.…”

“…In 2019, Zamani Joharestani et al [ 11 ] used spatial data collected in Tehran, Iran to predict PM2.5 by using machine learning techniques: Random Forest, Extreme Gradient Boosting, and Deep Learning. Sethi and Mittal [ 12 ] predicted air quality of Faridabad, India by using AOD data with several machine learning techniques. Wang et al [ 13 ] estimated PM2.5 in China by using AOD data using Neural Networks.…”

Prediction of Air Quality Index Using Machine Learning Techniques: A Comparative Analysis

“…Experiments have shown that decision trees (classifcation), SVR, and stacking ensembles work much better than the other methods in their category. Mathematical models, learning, and regression techniques were recommended for developed areas and cities [27].…”

Artificial Neural Network in the Field of Environment

“…), and some non-ferrous metal ore smelting process, it is a colorless, stimulating odour gas can and PM2.5 combined with formation of aerosols in the air, is a threat to human respiratory tract, serious when can make people breathing difficulties, cause a variety of respiratory diseases and even deadly. In addition, SO2 can also combine with water vapor in the atmosphere and dissolve in water to form sulfuric acid and sulfite, leading to the formation of acid rain [16]. NO2 is the main form of nitrogen oxide pollutants in the air, which is generated by the combustion of fossil fuels, the use of nitric acid, the manufacture of nitrogen-containing fertilizers, metal smelting and other processes.…”