NCAR hosts Sixth International Workshop on Climate Informatics

By Staff
09/28/2016 - 12:00pm

On 22-23 September 2016, CISL's Institute for Mathematics Applied to Geosciences (IMAGe) hosted the sixth yearly meeting for an international group of researchers from statistics, machine learning, data mining, and climate science. The purpose of this workshop series is to build interdisciplinary partnerships between these researchers. The workshop organizers write, "Because climate models and observed datasets are increasing in complexity and volume, and because the nature of our changing climate is an urgent area of discovery, there are many opportunities for such partnerships."

The workshop organizers included Arindam Banerjee, University of Minnesota; Jennifer Dy, Northeastern University; Slava Lyubchich, University of Maryland Center for Environmental Science; Andrew Rhines, Harvard University; Wei Ding, University of Massachusetts Boston; Eniko Szekely, New York University; Imme Ebert-Uphoff, Colorado State University; Claire Monteleoni, George Washington University; and Doug Nychka, National Center for Atmospheric Research.

Participants of the 6th International Workshop on Climate Informatics converse during a poster session. (Photo by Brian Bevirt, CISL.)

The format of the workshop emphasized communication among all the various fields, with a strong emphasis on brainstorming during the breakout sessions and panel discussions. The Climate Informatics website provides a place for interested researchers to interact, share data sets, access materials from past workshops, and learn about upcoming events.

The day preceding the workshop featured an all-day hackathon where the researchers collaborated on solving a big-data problem. This year, the students were tasked to predict the monthly sea ice extent based on historical atmospheric variables that were derived from one of NCAR’s models. The students collectively worked toward their predictions by using the platform RAMP (Rapid Analytics and Model Prototyping), which allows modelers to share pieces of their code with others. As students contributed code to the group, other students were able to modify pieces of the code and apply various statistical methods to make a more accurate prediction. By working alongside others with different backgrounds, students were exposed to new ways to approach the problem, and they learned how to implement new data analysis and coding techniques. Balazs Kégl, a hackathon organizer, says the hackathon provided valuable experience for the students because "the [hackathon] pipeline is what you do in reality."

Data informatics is a discipline for examining large data sets to find patterns and structure that can help in understanding the relationship between different variables or to make predictions. Climate data informatics broadly refers to any research combining climate science with approaches from statistics, machine learning, and data mining. Conferences between researchers from all of these areas stimulate the discussion of new ideas, foster new collaborations, grow the climate informatics community, and accelerate discovery across disciplinary boundaries.

Participants of the 6th International Workshop on Climate Informatics pose for a group photo. The workshop was designed to facilitate partnerships between members of the statistics, machine learning, data mining, and climate science community. (Photo by Brian Bevirt, CISL.)