PREDICTION OF ENVIRONMENTAL POLLUTION USING NEURAL NETWORK

In general environmental pollution is one of the most considerable one as challenges in a smart megacity terrain. In denitrifying of pollution data enables the metropolitans to dissect the current business situation of the megacity and take their opinions consequently. Deployment of Big data Analytical Tool grounded detectors has vastly changed the dynamics of prognosticating air quality. This project performed the pollution prediction using sarima regression technique and also classification using neural network approach with a comparative study to analyze the best model for accurately predicting the air quality with reference to data size and processing time. Current research has used different machine learning tools for pollution prediction; however, comparative analysis of these techniques is often required to have a better understanding of their processing time for multiple datasets. In analyzing the standard of atmospheric terrain is an important condition for the much longer survival of living people on environment. A pure suitable atmospheric terrain is needed for the healthy development of mortal beings. Now the problem of haze, photochemical problems in the air, and global warming is formerly a crucial issue of global concern. Current implementations of country’s frugality, transportation and assiduity with the enhancement of urbanization, environmental pollution problems have gradationally come prominent, but this is contrary to people’s vision of pursuing a high- quality life. The project is designed using R Studio. The coding language used is R 3.4.4.