Mining and reasoning about spatial data is a central challenge in numerous science and engineering domains. The development and application of effective spatial data mining techniques requires sharing ideas and building ties among application researchers, researchers who develop formalisms for spatial modeling, and researchers in (spatial) data mining and methodology. The SIAM-DM 2006 Workshop on Spatial Data Mining aims to provide a forum for such an exchange. Example issues that are of topical interest to the workshop include:

• How can we formally model the behavior of spatial mining algorithms?
• How can we intelligently sample data for `closing-the-loop'?
• What features are pertinent in mining spatial datasets?
• How can we employ spatial reasoning for model inference?
• What software tools aid in robust reasoning about spatial phenomena?

Paper Submission and Review

The workshop seeks to bring together three perspectives on spatial data mining: application domains with significant spatial data mining challenges; mining algorithms for modeling and uncovering structures in spatial data; sampling algorithms for intelligently collecting additional data. In order to focus the discussion at the workshop, we particularly encourage papers responsive to the context of pandemic detection and response, as described in the linked document. Other example application domains include multidisciplinary design optimization, structural bioinformatics, computational fluid dynamics, geographical information systems, experimental algorithmics (e.g., in numerical computing), parameter studies in computational simulation, weather pattern identification, and distributed sensor and actuator networks.

Papers should be 3-5 pages in SIAM-DM conference format (data mining file; general website). A PDF file should be emailed to the program chairs. A paper can present perspectives on how to address the challenge problem issues or completed work that addresses these issues. Novel work that straddles multiple facets of spatial data mining, spatial modeling, and active sampling methodology are especially encouraged. The proceedings will be published as an on-line collection of working papers. Following discussion at the workshop, participants will be invited to contribute to a summary report that will be communicated to a premier data mining magazine or journal.

Important Dates

• Submission: February 27, 2006
• Notification: March 6, 2006
• Workshop: April 22, 2006 (half a day at SIAM-DM 2006)

Organization

The program chairs are Chris Bailey-Kellogg and Naren Ramakrishnan, and can be contacted at cbk@cs.dartmouth.edu and naren@cs.vt.edu. The program committee is as follows:

• Chris Bailey-Kellogg, Dartmouth (co-chair)
• Jochen Garcke, Australian National University
• Carlos Guestrin, Carnegie Mellon University
• Jiawei Han, University of Illinois at Urbana-Champaign
• George Karypis, University of Minnesota
• Tao Li, Florida International University
• Madhav Marathe, Virginia Bioinformatics Institute
• Naren Ramakrishnan, Virginia Tech (co-chair)
• Srinivasan Parthasarathy, The Ohio State University
• Shashi Shekhar, University of Minnesota
• Feng Zhao, Microsoft Research