Prediction of PM2.5 Over Hyderabad Using Deep Learning Technique

• Published in: Nature environment and pollution technology Vol. 21; no. 2; pp. 691 - 696
• Main Authors: Kumar, P. Vinay, Kumar, M. C. Ajay, Kumar, B. Anil, Rao, P. Venkateswara
• Format: Journal Article
• Language: English
• Published: Karad Technoscience Publications 01-06-2022
• Subjects: Air pollution; Air quality; Air quality control; Artificial intelligence; Datasets; Deep learning; Developing countries; Environmental health; Humidity; Industrial development; LDCs; Machine learning; Mathematical models; Meteorological data; Neural networks; Outdoor air quality; Particulate matter; pm2.5, air pollution, deep learning, forecasting; Pollutants; Pollution control; Public health; Rain; Regression; Root-mean-square errors; Scientific papers; Statistical analysis; Statistical models; Time series; Urbanization; India
• ISSN: 2395-3454; 0972-6268; 2395-3454
• DOI: 10.46488/NEPT.2022.v21i02.029

Urbanization and Industrialization during the last few decades have increased air pollution causing harm to human health. Air pollution in metro cities turns out to be a serious environmental problem, especially in developing countries like India. The major environmental challenge is, to predict accurate air quality from pollutants. Envisaging air quality from pollutants like PM2.5, using the latest deep learning technique (LSTM timer series) has turned out to be a significant research area. The primary goal of this research paper is to forecast near-time pollution using the LSTM time series multivariate regression technique. The air quality data from Central Pollution Control Board over Hyderabad station has been used for the present study. All the processing is done in real-time and the system is found to be functionally very stable and works under all conditions. The Root Mean Square Error (RMSE) and R2 have been used as evaluation criteria for this regression technique. Further, the time series regression has been used to find the best fit model in terms of processing time to get the lowest error rate. The statistical model based on machine learning established a relevant prediction of PM2.5 concentrations from meteorological data.