<p>The fast pace of urbanization has resulted in serious environmental issues, primarily air pollution, with highly detrimental effects on the environment and climate as well as public health in general. The most usual cause of poor air through exhaust and combustion of motorized traffic. As being the cause, the Government of India has designed policies and legislation on assumptions of sustainable development so as to prevent such an effect. In the present study, an effort has been made to numerically measure the spatiotemporal variation of air pollution over 2015–2020 from the perspective of seasonal and yearly variation numerically. Seven important air pollutants, i.e., PM<sub>2.5</sub>, PM<sub>10</sub>, SO<sub>2</sub>, NO<sub>2</sub>, NOx, CO, and O<sub>3</sub>, are being analyzed and temporal pattern is being contrasted with latter of meteorological variables based on 270 Indian monitoring stations. Min–max normalization, nearest neighbor imputation to handle missing values, and one-hot encoding to normalize wind speed were implemented as data preprocessing, prior to spatiotemporal pattern identification with the aid of an LSTM model. Findings depict significant decline of major pollutants during the COVID-19 lockdown period owing to lower car emissions and manufacturing.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Temporal variations of major air pollutants: case study in India

  • Usharani Bhimavarapu

摘要

The fast pace of urbanization has resulted in serious environmental issues, primarily air pollution, with highly detrimental effects on the environment and climate as well as public health in general. The most usual cause of poor air through exhaust and combustion of motorized traffic. As being the cause, the Government of India has designed policies and legislation on assumptions of sustainable development so as to prevent such an effect. In the present study, an effort has been made to numerically measure the spatiotemporal variation of air pollution over 2015–2020 from the perspective of seasonal and yearly variation numerically. Seven important air pollutants, i.e., PM2.5, PM10, SO2, NO2, NOx, CO, and O3, are being analyzed and temporal pattern is being contrasted with latter of meteorological variables based on 270 Indian monitoring stations. Min–max normalization, nearest neighbor imputation to handle missing values, and one-hot encoding to normalize wind speed were implemented as data preprocessing, prior to spatiotemporal pattern identification with the aid of an LSTM model. Findings depict significant decline of major pollutants during the COVID-19 lockdown period owing to lower car emissions and manufacturing.