Search

In order to survive, mankind needs air. The quality of life depends on the purity of the air we breathe in. Hazardous pollutants are stirred up in our environment by various activities everyday. In a developing country like India, which has huge population, protecting public health is important. In general, air quality is measured using the air quality index, which records the pollutants level in the air. These recordings are to be mentioned across various places, to know about the air quality level. The advancement of the recent artificial intelligence can be replaced by the human efforts and to automate the system in flowless manner. Hence, an effort has been taken in this paper, by proposing a framework of predicting the air quality seasonally using regularized combinational LSTM (REG-CLSTM). For an efficient air quality level prediction with an improved error rate, time, and accuracy, the study has implemented Reg-CLSTM with a large amount of real-time dataset. To improvise the comprehensiveness and the potentiality of the proposed model, the significant feature is extracted by the rough set-wrapper method. The significant challenge is to provide a seasonal limit range for each considered pollutant in place of a generalized range partition. Aiming at this problem, the proposed model is able to identify the highest concerning pollutants occurrence in individual seasons. Through this study, pyramid learning-based hybridized deep learning framework is developed which can play a crucial role in warning the policy maker to reduce the activities that instigate air pollution. [ABSTRACT FROM AUTHOR]

Tackling air pollution has become of utmost importance since the last few decades. Different statistical as well as deep learning methods have been proposed till now, but seldom those have been used to forecast future long-term pollution trends. Forecasting long-term pollution trends into the future is highly important for government bodies around the globe as they help in the framing of efficient environmental policies. This paper presents a comparative study of various statistical and deep learning methods to forecast long-term pollution trends for the two most important categories of particulate matter (PM) which are PM2.5 and PM10. The study is based on Kolkata, a major city on the eastern side of India. The historical pollution data collected from government set-up monitoring stations in Kolkata are used to analyse the underlying patterns with the help of various time-series analysis techniques, which is then used to produce a forecast for the next two years using different statistical and deep learning methods. The findings reflect that statistical methods such as auto-regressive (AR), seasonal auto-regressive integrated moving average (SARIMA) and Holt–Winters outperform deep learning methods such as stacked, bi-directional, auto-encoder and convolution long short-term memory networks based on the limited data available. [ABSTRACT FROM AUTHOR]