Scholarlink

This study presents an autoregression model developed in python platform for time-series prediction of PM2.5 at Anand Vihar location in New Delhi, India. The study analysed both fixed and rolling autoregression models for predictions. The hourly PM2.5 concentration data of the region has been collected and used for training of proposed model. The performance of the proposed model has been analysed in terms of mean absolute error (MAE), root mean squared error (RMSE) and mean absolute percentage error (MAPE). The outcomes specify superior performance of rolling autoregression model developed in python thereby giving lower error responses compared to fixed autoregression model. The MAE, RMSE and MAPE obtained for rolling autoregression model for a maximum multistep ahead prediction of 7 h’ duration was 7.09 µg/m3, 8.10 µg/m3 and 1.88% respectively.

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

Soft Computing Applications for Time-Series Prediction of PM2.5 Concentration Using Python

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tarun Kumar Dhiman,
  • Ashwani Kharola,
  • Amir Shaikh,
  • Kiran Sharma,
  • Sunil Kumar Lal,
  • Vinayak Sharma

摘要

This study presents an autoregression model developed in python platform for time-series prediction of PM2.5 at Anand Vihar location in New Delhi, India. The study analysed both fixed and rolling autoregression models for predictions. The hourly PM2.5 concentration data of the region has been collected and used for training of proposed model. The performance of the proposed model has been analysed in terms of mean absolute error (MAE), root mean squared error (RMSE) and mean absolute percentage error (MAPE). The outcomes specify superior performance of rolling autoregression model developed in python thereby giving lower error responses compared to fixed autoregression model. The MAE, RMSE and MAPE obtained for rolling autoregression model for a maximum multistep ahead prediction of 7 h’ duration was 7.09 µg/m3, 8.10 µg/m3 and 1.88% respectively.