Scholarlink

Air pollution poses a severe global threat to public health, the environment, and societal wellbeing. This survey paper undertakes an extensive examination of the diverse methods employed for predicting air pollution levels, from sophisticated computational methods like machine learning and deep learning techniques to conventional statistical models like multiple linear regression. The paper elucidates the strengths, limitations, and comparative performance of the various methods, aiming to provide insights into their efficacy and potential for advancing air quality forecasting capabilities. Moreover, it also focuses on the future directions outlined in the survey, such as enhancing model interpretability, integrating advanced technologies, implementing real-time monitoring systems, fostering cross-disciplinary collaboration, and emphasizing the health impacts of air pollution. By addressing these challenges and embracing the suggested future directions, advancements in air pollution prediction methods can lead to more accurate forecasts, informed decision-making, and improved public health outcomes.

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

Forecasting Air Quality: A Comprehensive Survey of Air Pollution Prediction Methods and Applications

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Md. Sanwarul Islam,
  • Ramisa Hossain Arna,
  • Tasnimul Hassan Shad,
  • Tahamina Akter Mim,
  • Ismail Mahmud Nur,
  • Mahedi Masnad Ether,
  • Sabit Al Alfi,
  • Anindita Sutradhar,
  • Nafisa Hossain Arpa,
  • Sayed Abdul Mokit,
  • Abu Talha,
  • Md. Jakir Hossain

摘要

Air pollution poses a severe global threat to public health, the environment, and societal wellbeing. This survey paper undertakes an extensive examination of the diverse methods employed for predicting air pollution levels, from sophisticated computational methods like machine learning and deep learning techniques to conventional statistical models like multiple linear regression. The paper elucidates the strengths, limitations, and comparative performance of the various methods, aiming to provide insights into their efficacy and potential for advancing air quality forecasting capabilities. Moreover, it also focuses on the future directions outlined in the survey, such as enhancing model interpretability, integrating advanced technologies, implementing real-time monitoring systems, fostering cross-disciplinary collaboration, and emphasizing the health impacts of air pollution. By addressing these challenges and embracing the suggested future directions, advancements in air pollution prediction methods can lead to more accurate forecasts, informed decision-making, and improved public health outcomes.