Co-convened by: Forrest M. Hoffman, Jitendra Kumar, J. Walter Larson, Richard Tran Mills, and Miguel D. Mahecha
June 4–6, 2012
Spanning many orders of magnitude in time and space scales, Earth science data are increasingly large and complex, and often represent very long time series, making such data difficult to analyze, visualize, interpret, and understand. Moreover, advanced electronic data storage technologies have enabled the creation of large repositories of observational data, while modern high performance computing capacity has enabled the creation of detailed empirical and process-based models that produce copious output across all these time and space scales. The resulting “explosion” of heterogeneous, multi-disciplinary Earth science data has rendered traditional means of integration and analysis ineffective, necessitating the application of new analysis methods and the development of highly scalable software tools for synthesis, comparison, and visualization. This workshop explores various data mining approaches to understand Earth science data, emphasizing the technological challenges associated with utilizing very large and long time series geospatial data sets. Especially encouraged are original research papers describing applications of data mining methods—including cluster analysis, empirical orthogonal functions (EOFs), genetic algorithms, neural networks, and other machine-learning techniques—that support analysis and discovery in climate, water resources, geology, ecology, and environmental sciences research.
Authors are invited to submit manuscripts of up to 10
(A4) pages reporting unpublished, mature, and original research and recent
developments/theoretical considerations in applications of data mining
to Earth sciences by
January 9, 2012 January 20, 2012 February 10, 2012. Accepted papers will printed
in the conference proceedings published by Elsevier Science in the
open-access Procedia Computer Science series. Submitted papers must
be camera-ready and formatted according to the rules of Procedia
Computer Science. Submission implies the willingness of at
least one of the authors to register and present the paper.
Please submit your paper via the conference website at http://www.iccs-meeting.org/iccs2012/papers/upload.php and select the workshop “Third Data Mining in Earth System Science (DMESS 2012)”.
|Full paper submission:|
|Notification of paper acceptance:|
|Final camera-ready papers due:|
|Early registration opens:||Feburary 15, 2012|
|Early registration closes:||April 15, 2012|
|Tutorials, Welcome reception:||June 3, 2012|
|Conference sessions:||June 4–6, 2012|
|E-mail:||dmess2012 at climatemodeling dot org|
This workshop will contribute to the field of Computational Science by creating a forum for original research papers and presentations from leading computational and earth scientists who are applying data mining techniques on advanced computing platforms (HPC systems, clusters, grids and clouds) to distill knowledge from the massive—and growing—data sets created by the earth science community.
Forrest M. Hoffman has been developing software for data mining using high performance computing (HPC) and apply data mining methods to problems in landscape ecology, remote sensing, and climate analyses for more than a decade. Forrest co-convened the GeoComputation workshop at ICCS 2009 and the previous Second Workshop on Data Mining in Earth System Science at ICCS 2011. Forrest's publication list is available at http://www.climatemodeling.org/~forrest/pubs.
Jitendra Kumar conducts research at the intersection of high performance computing, environmental and earth sciences, and systems analysis and data mining. His research entails data mining, large-scale global optimization, computational hydrology and hydrogeology, and development of parallel algorithms for large-scale supercomputers.
J. Walter Larson is a leader in the development of coupling software for simulation of complex systems, most notably as the co-lead developer of the Model Coupling Toolkit (http://mcs.anl.gov/mct) and as one of the developers of the coupling infrastructure in the Community Climate System Model. He has published papers in the fields of mathematical and plasma physics, climate, data assimilation, and computational science (http://people.physics.anu.edu.au/~jwl105/Pubs).
Richard Tran Mills has conducted research in high performance computing, software for iterative solution of sparse algebraic systems, computational hydrology, geospatiotemporal data mining, computational hydrology, and execution context-aware software. He has contributed to the PETSc PDE-solver framework and is a principal author of the subsurface flow and reactive transport code PFLOTRAN, which is being used on the largest-scale supercomputers in the world to study topics such as radionuclide transport and geologic carbon sequestration.
Miguel D. Mahecha conducts research on ecosystem-atmosphere interactions and related topics. He investigates the potential of novel data mining and time series analysis methods for exploring multidimensional spatiotemporal Earth observations and in situ monitoring data. He is particularly interested in nonlinear dimensionality reduction, multivariate time series analysis, and data assimilation. Publications available at https://www.bgc-jena.mpg.de/bgc-mdi/index.php/Main/MiguelMahecha.