PREDICTION OF OZONE FORMATION BASED ON NEURAL NETWORK

The atmospheric ozone concentration in Seoul, Korea, was forecasted using an artificial neural network (ANN) and spatiotemporal analysis. The ANN was trained by using hourly pollutant and meteorological data that resulted in complex patterns of ozone formation. The finite-volume method was employed in the spatiotemporal analysis in order to take into account the effects of wind. Time horizons in the forecasts were 1-6 hours and 16-21 hours. The resulting predictions of ozone formation were compared with measured data. From the comparison, it was found that the ANN method gave reliable accuracy within a limited prediction.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/8675387
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Sohn, S H
  • Oh, S C
  • Jo, B W
  • Yeo, Y-K
• Publication Date: 2000-8

Language

• English

Media Info

• Features: Appendices; Figures; References; Tables;
• Pagination: p. 688-696
• Serial:
  • Journal of Environmental Engineering
  • Volume: 126
  • Issue Number: 8
  • Publisher: American Society of Civil Engineers
  • ISSN: 0733-9372
  • Serial URL: http://ojps.aip.org/eeo

Subject/Index Terms

• TRT Terms: Accuracy; Air pollution; Atmospheric diffusion; Forecasting; Mathematical models; Mathematical prediction; Meteorology; Neural networks; Ozone; Pollutants; Wind
• Uncontrolled Terms: Advection; Finite volume method
• Geographic Terms: Seoul (Korea)
• Subject Areas: Data and Information Technology; Geotechnology; Highways; Planning and Forecasting; I10: Economics and Administration;

Filing Info

• Accession Number: 00795823
• Record Type: Publication
• Files: TRIS
• Created Date: Aug 1 2000 12:00AM