Abstract
This paper develops and empirically compares two Bayesian and empirical Bayes space-time approaches for forecasting next-day hourly ground-level ozone concentrations. The comparison involves the Chicago area in the summer of 2000 and measurements from fourteen monitors as reported in the EPA's AQS database. One of these approaches adapts a multivariate method originally designed for spatial prediction. The second is based on a state-space modeling approach originally developed and used in a case study involving one week in Mexico City with ten monitoring sites. The first method proves superior to the second in the Chicago Case Study, judged by several criteria, notably root mean square predictive accuracy, computing times, and calibration of 95% predictive intervals.
Highlights
This paper compares two methods for temporally forecasting next-day hourly ground-level ozone concentrations over spatial regions
The accumulated body of evidence was so strong that the committee recommended strengthening the air quality standards for this criterion pollutant to meet the requirements of the US Clean Air Act
We describe the general method M1 in terms of the goal of forecasting ozone concentrations at a specific hour on Day 121 and each of g = 14 monitoring sites based on data collected at those sites during the preceding days, that being the objective in the case study described
Summary
This paper compares two methods for temporally forecasting next-day hourly ground-level ozone concentrations over spatial regions. On June 27, 2009 the AIRNow website forecasts a maximum for Chicago of between 0 and 50 ppb, rating that as “Good.” In contrast, for that day in one part of Los Angeles, the rating was “Unhealthy for sensitive groups,” meaning a forecast maximum of between 101 and 150 ppb. These forecasts are needed to forewarn susceptible groups of high ozone concentrations that are associated with acute health effects. This points to a need for enhanced near-term forecasting methods
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have