A Review on Analysis and Prediction of Air Quality Using Machine Learning Techniques

A Review on Analysis and Prediction of Air Quality Using Machine Learning Techniques

Surabhi Sharma

Deptt. of Electronics & Communication Engineering

Shriram College of Engineering & Management (SRCEM)

Banmore, Gwalior(M.P)

Prof. Ashish Duvey

Deptt. of Electronics & Communication Engineering

Shriram College of Engineering & Management (SRCEM)

Banmore, Gwalior(M.P)

Abstract— Human health is greatly influenced by air quality. Air pollution causes a variety of health problems, particularly in youngsters. The capacity to anticipate air quality allows the government and other concerned groups to take the required precautions to protect the most vulnerable from being exposed to harmful air quality. To ensure optimum air quality, the air quality measurement system analyses different air contaminants in various areas. It is the most pressing problem in the current situation. The entry of harmful gases into the climate from industry, car emissions, and other sources pollutes the air. Conventional methods to this issue have had extremely little success due to a lack of access to significant longitudinal data for such techniques. Currently, air pollution has reached alarming levels, with several large cities exceeding the government's air quality standards. It has a significant influence on human health. With advances in machine learning techniques, it is now feasible to anticipate contaminants based on historical data. Machine learning methods are used to anticipate air pollution levels so that individuals may take preemptive steps to reduce air pollution. In this research, we provide a variety of ML techniques that can continue can take existing pollutants, however, with the aid of previous pollutants, we are running an algorithm based on machine learning to forecast the future data of pollutants. This approach can continue to take current pollutants.

Keywords— Air pollution., Air Quality prediction, Artificial Intelligence, Machine Learning, supervised and unsupervised.