Prediction and Forecasting of Air Quality Index in Chennai using Regression and ARIMA time series models

Air is one of the most fundamental constituents for sustenance life on earth. The meteorological, traffic factors, consumption non-renewable energy sources, and industrial parameters are steadily increasing air pollution. These factors affect welfare prosperity earth; therefore, nature quality in our environment needs to be monitored continuously. Quality Index (AQI), which indicates quality, influenced by several individual such as accumulation NO2, CO, O3, PM2.5, SO2, PM10. This research paper aims predict forecast AQI with Machine Learning (ML) techniques, namely linear regression time series analysis. Primarily,Multi Linear Regression (MLR) model, supervised machine learning, developed AQI. Ozone(O3), PM 2.5, SO2 sensor output collected from Central Pollution Control Board (CPCB) – Chennai region, India feed input features optimized calculated sensor's set a target train model. obtained model validated new unseen output. Key Performance Indices(KPI) like co-efficient determination, root mean square error absolute were validate accuracy. K-cross-fold validation testing data MLR was around 92%. Secondly, Auto-Regressive Integrated Moving Average (ARIMA) applied timestamp. forecasted value next 15 days lies 95 % confidence interval zone. accuracy test more than 80%.