Scholarlink

<p>Air pollution is a major environmental concern in many Indian cities, with potential negative impacts on public health and the environment. This study aims to assess and forecast air quality in Jabalpur city of Madhya Pradesh, using an artificial neural network (ANN). The study utilised historical air quality data from January 2019 to December 2023, including concentrations of criteria pollutants, particulate matter PM<sub>2.5</sub>, PM<sub>10</sub>, SO<sub>2</sub>, NO<sub>2</sub>, and meteorological parameters collected from the Central Pollution Control Board (CPCB). An ANN model was developed and trained on the historical data to predict future air quality levels and It was observed that PM<sub>10</sub> and PM<sub>2.5</sub> concentrations exceeded the daily and annual CPCB standards, the performance of the ANN model was evaluated using statistical metrics such as RMSE, R<sup>2</sup>, MSE, and MAE. Meteorological parameters and hourly pollutant concentrations were used to train the five-year model, hence the result showed that ANN can predict the air pollutant concentrations with R<sup>2</sup> value of 0.8666 for NO<sub>2</sub> but for SO<sub>2</sub> shows lesser accuracy, with lowest R<sup>2</sup> as 0.6977.</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

Atmospheric Pollution Forecasting Over Jabalpur City of Madhya Pradesh: A Machine Learning Application

  • 期刊论文

  • 发表日期：

    2025年6月12日

查看全文
  • Vineet Kushwaha,
  • Anil Kumar Sharma

摘要

Air pollution is a major environmental concern in many Indian cities, with potential negative impacts on public health and the environment. This study aims to assess and forecast air quality in Jabalpur city of Madhya Pradesh, using an artificial neural network (ANN). The study utilised historical air quality data from January 2019 to December 2023, including concentrations of criteria pollutants, particulate matter PM2.5, PM10, SO2, NO2, and meteorological parameters collected from the Central Pollution Control Board (CPCB). An ANN model was developed and trained on the historical data to predict future air quality levels and It was observed that PM10 and PM2.5 concentrations exceeded the daily and annual CPCB standards, the performance of the ANN model was evaluated using statistical metrics such as RMSE, R2, MSE, and MAE. Meteorological parameters and hourly pollutant concentrations were used to train the five-year model, hence the result showed that ANN can predict the air pollutant concentrations with R2 value of 0.8666 for NO2 but for SO2 shows lesser accuracy, with lowest R2 as 0.6977.