2023/02/28 by Jinghong Zeng, Zeng, Jinghong
Environmental Science · Mathematics · #Air Quality Monitoring and Forecasting #Air Quality and Health Impacts #Econometrics #Environmental science #Forecast error #Forecast verification #Geography #Global Forecast System #Interval (graph theory) #Mathematics #Meteorology #Nonlinear system #Numerical weather prediction #Precipitation #Quantitative precipitation forecast #Water Quality Monitoring and Analysis
paper · pdf · doi:10.48550/arxiv.2302.14505
openalex publication_date 2023/02/28 · openalex created_date 2023/03/03 · openalex updated_date 2026/07/28
Forecasting PM2.5 concentration is important to solving air pollution problems in Wuhan. This paper proposes a PM2.5 concentration forecast model based on nonlinear regression, including a single-value forecast model and an interval forecast model. The single-value forecast model can precisely forecast PM2.5 concentration for the next day, with forecast bias about 6 μg/m3 in goodness of fit analysis. The interval forecast model can efficiently forecast high-concentration and low-concentration days, which covers 60%-80% observed samples in model validation. Moreover, this paper combines the PM2.5 concentration forecast model with NCEP Climate Forecast System Version 2 to realize its forecast application, then develops NCEP CFS2's PM2.5 concentration forecast model to enhance forecast accuracy. The results indicate that the PM2.5 concentration forecast model has good capacity for independent forecasting.