Climate change and variability: A spatio-temporal data mining perspective

Date: 
Friday, May 3, 2013 - 4:57pm

UCSB COMPUTER SCIENCE DEPARTMENT PRESENTS:

Monday, June 3, 2013
3:30 – 4:30 PM
Room 1132 Harold Frank Hall

HOST: Subhash Suri

SPEAKER: James H. Faghmous
Computer Science, University of Minnesota -Twin Cities

Title: Climate change and variability: A spatio-temporal data mining
perspective

Abstract:

Our planet is experiencing simultaneous changes in global population, urbanization, and climate. These changes, along with the rapid growth of climate data and increasing popularity of data mining techniques may lead to the conclusion that the time is ripe for data mining to spur major innovations in climate science. However, climate data bring forth unique challenges that are unfamiliar to the traditional data mining literature, and unless they are addressed, data mining will not have the same impact that it has had on fields such as biology or e-commerce.

This talk provides a computer science audience with an introduction to mining climate data with an emphasis on the singular characteristics of the datasets and research questions climate science attempts to address. We demonstrate some of the concepts discussed in the earlier parts of the talk with two climate-related applications of relationship and pattern mining to predict Atlantic hurricane activity, and monitor mesoscale ocean eddies, respectively. In both instances, we show that insightfully mining the spatio-temporal context of climate datasets can yield significant improvements in the performance of learning algorithms. We focus on two spatio-temporal data mining applications one predicting Atlantic tropical cyclone (TC) activity and the other on mesoscale ocean eddy monitoring.

Bio:

James H. Faghmous obtained his Ph.D. in computer science from the University of Minnesota -Twin Cities. His doctoral research was part of a 5-year $10M NSF-funded Expeditions in Computing grant to develop novel numerical techniques to study and monitor climate change. James’ research has been funded by an NIH Neuro-Physical-Computational Graduate Fellowship, an NSF Graduate Research Fellowship, an NSF Nordic Research Opportunity Fellowship, and a University of Minnesota Doctoral Dissertation Fellowship. James graduated in 2006 with a B.Sc. in computer science from the City of College of New York where he was a Rhodes and a Gates Scholar nominee.