• Jun 17] Visual Storytelling Contest videos and materials are updated.
• Apr 14] Workshops (PacificVAST) schedules are updated.
• Mar 7] Conference program and keynote talks are updated.
• Feb] Registration is now available!
• Feb] Accommodation information is updated.

• 2016
  Taipei
  Apr 19 - Apr 22
• 2015
  Hangzhou
  Apr 14 - Apr 17
• 2014
  Yokohama
  Mar 04 - Mar 07
• 2013
  Sydney
  Feb 26 - Mar 01
• 2012
  Songdo
  Feb 28 - Mar 02
• 2011
  Hong Kong
  Mar 01 - Mar 04
• 2010
  Taipei
  Mar 02 - Mar 05
• 2009
  Beijing
  Apr 20 - Apr 23
• 2008
  Kyoto
  Mar 04 - Mar 07

• Facebook Official Facebook Page

• Twitter Official Twitter Account

• WeChat Official WeChat Account (亚太地区可视化会议微信公众号)

Decoupling Ensemble Data Using Subspaces

• Fan Hong
  Peking University, Beijing, China
• Xiaoru Yuan xiaoru.yuan (at) pku.edu.cn
  Peking University, Beijing, China
• Alex Pang pang (at) soe.ucsc.edu
  University of California, Santa Cruz, California, United States
• Chufan Lai chufan.lai (at) pku.edu.cn
  Peking University, Beijing, China
• Brad Hollister behollis (at) soe.ucsc.edu
  University of Utah, Salt Lake City, Utah, United States
• Xiaoguang Ma maxg (at) mail.iap.ac.cn
  State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, China
• Pierre Lermusiaux pierrel (at) mit.edu
  Massachusetts Institute of Technology, Cambridge, Massachusetts, United States

Abstract

Locations and simulations runs are two important aspects of ensemble data. Existing methods either compare regional or locational features extracted from runs, or compare simulation runs over the spatial domain. By decoupling only one aspect and aggregating the other, the coordinated behaviors between run subsets and location subsets are concealed. In this work, we introduce the concept of ensemble subspace inspired by high-dimensional data visualization, and suggest a more informative approach to explore ensemble data, that is to simultaneously decouple the locations and runs. Biclustering-based method is employed for ensemble subspace extraction, thus enables the exploration of coordinated behaviors in ensemble data. We build a system to support extraction and exploration of coordinated behaviors in ensemble subspaces. Our case studies have shown plenty of results about coordinated behaviors, which are difficult to find with existing tools.