A fast Bayesian method for updating and forecasting hourly ozone levels

Sahu, Sujit K., Yip, Stan and Holland, David M. (2009) A fast Bayesian method for updating and forecasting hourly ozone levels Environmental and Ecological Statistics, 18, (1), pp. 185-207. (doi:10.1007/s10651-009-0127-y).


[img] PDF sahuyipholland_env_eco_09.pdf - Other
Restricted to Repository staff only

Download (1MB)


A Bayesian hierarchical space-time model is proposed by combining information from real-time ambient AIRNow air monitoring data, and output from a computer simulation model known as the Community Multi-scale Air Quality (Eta-CMAQ) forecast model. A model validation analysis shows that the model predicted maps are more accurate than the maps based solely on the Eta-CMAQ forecast data for a 2 week test period. These out-of sample spatial predictions and temporal forecasts also outperform those from regression models with independent Gaussian errors. The method is fully Bayesian and is able to instantly update the map for the current hour (upon receiving monitor data for the current hour) and forecast the map for several hours ahead. In particular, the 8 h average map which is the average of the past 4 h, current hour and 3 h ahead is instantly obtained at the current hour. Based on our validation, the exact Bayesian method is preferable to more complex models in a real-time updating and forecasting environment.

Item Type: Article
Digital Object Identifier (DOI): doi:10.1007/s10651-009-0127-y
ISSNs: 1352-8505 (print)
Keywords: bayesian inference, eta-cmaq model, space-time forecasting, hierarchical model, separable models, spatial interpolation
Organisations: Statistics
ePrint ID: 147821
Date :
Date Event
9 November 2009Published
Date Deposited: 26 Apr 2010 13:41
Last Modified: 18 Apr 2017 14:35
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/147821

Actions (login required)

View Item View Item