The workshop includes an invited talk regarding challenges in pandemic preparedness by Madhav Marathe, presentations of five papers addressing spatial data mining challenges in the pandemic preparedness context and two papers addressing general issues in spatial data mining, and a discussion period for comparing, contrasting, identifying emergent themes, and so forth.

Pandemic diseases such as the avian influenza are extreme infectious disease outbreaks. Pandemic influenza viruses have demonstrated their ability to spread worldwide within months, or weeks, and to cause infections in all age groups.

Traditional epidemiological modeling techniques for planning and responding during such events have focused on rate-based differential-equation models on completely mixing populations. Although these models are attractive from the standpoint of obtaining analytical results, they do not capture the complexity of human and/or vector interactions that serve as a mechanism for disease transmission. In addition, their use in formulating and implementing public policies in the event of epidemics is rather limited.

The talk will outline an interaction based approach based on a combination of network theory and discrete-event simulations to study epidemics in large urban areas. The approach is highly scalable and overcomes several weaknesses inherent in the traditional models. Moreover, it naturally yields a scalable computer assisted decision support system for pandemic planning and response.

I will conclude by discussing new research questions in spatial data mining suggested by the approach.