Laboratory: Interaction,Discovery, Exploration, and Adaptation lab
Phone: (405) 325-5427 | Office: DEH 251
PhD, University of Massachusetts Amherst
MS, University of Massachusetts Amherst
BS, Carnegie Mellon University (with honors)
Associate Professor, University of Oklahoma
Assistant Professor, University of Oklahoma
Senior Postdoctoral Research Associate, University of Massachusetts Amherst
Machine learning and data mining, particularly spatiotemporal relational data mining, for real-world applications with a special interest in severe weather and in space. Issues of automatically learning and growing appropriate forms of knowledge representations to enable improved agent autonomy.
Dr. Amy McGovern is an associate professor in the School of Computer Science at the University of Oklahoma. Dr. McGovern is an NSF CAREER award winner and her research focuses on developing novel spatiotemporal data mining method for real-world applications, particularly focusing on severe weather. Dr. McGovern received her PhD in Computer Science from the University of Massachusetts Amherst in 2002 and was a senior postdoctoral research associate at the University of Massachusetts until joining the University of Oklahoma in January, 2005. She received her MS from the University of Massachusetts Amherst (1998) and her BS (honors) from Carnegie Mellon University (1996).
AWARDS, HONORS AND PROFESSIONAL ACTIVITIES
Chair-elect, American Meteorological Society’s Committee on Artificial Intelligence Applications to Environmental Science
NSF CAREER Awardee, 2008-2013. Chair, EPSCOR Oklahoma Women in Science Day, 2008, 2009,
2010, 2011. Faculty Advisor, the University of Oklahoma’s Association for
Computing Machinery’s Women’s Chapter (ACM-W), Spring
2007-2010. Faculty Advisor, Alpha Sigma Kappa, Sorority for Women in
Technical Studies, 2008-present. Member Association, Computing Machinery (ACM) and American
Meteorological Society (AMS). Editor, Machine Learning Journal. Program committee and reviewer: International Conference on
Machine Learning, Neural Information Processing Systems, American Association for Artificial Intelligence, International Conference on Autonomous Agents, Journal of Machine Learning, International Conference on Data Mining.
NSF CAREER AWARD
Title: Developing Spatiotemporal Relational Models to Anticipate Tornado Formation
NSF CAREER AWARD SUMMARY
The goal of this research is to revolutionize the ability to anticipate tornadoes by developing advanced techniques for statistical pattern discovery in spatially and temporally varying relational data. These models are applied to complete fields of meteorological quantities obtained through data assimilation and simulation. Doppler radar data is limited and, while modern data assimilation techniques allow the unobserved quantities to be estimated, the resulting four-dimensional fields are too complicated for the extraction of meaningful, repeatable patterns by either humans or current data mining techniques. By studying a full field of variables, the models can identify critical interactions among high level features. The models are developed and verified in close collaboration with domain experts. The interdisciplinary nature of the research is used to improve retention and recruitment in computer science (CS). Introducing authentic projects into both early CS and meteorology classes will improve the number of technically trained students in both majors.
NSF, “CSR: Small: Learning-Assisted Parellization,” Co-PI, $500K, Aug. 2010-July 2013.
IBM through DARPA, “Learning to Guide Search in Large State Spaces,” PI, $95K, Jan. 2010-Dec. 2010.
NSF CAREER, “Developing Spatiotemporal Relational Models to Anticipate Tornado Formation,” PI, $500K, July 2008-June 2013.
Defense Advanced Research Projects Agency, subcontract to the University of California Berkeley, “Using Go as a Platform for Knowledge Guided Exploration,”, PI, $400K, Aug 2008-Sept 2009.
“Identifying Predictive Multi-Dimensional Time Series Motifs: an Application to Severe Weather Prediction,” Data Mining and Knowledge Discovery, Vol. 22, No. 1, pp. 232-258, 2011 (with D.H. Rosendahl, R.A. Brown and K.K. Droegemeier).
“Understanding Severe Weather Processes through Spatiotemporal Relational Random Forests,” Proceedings of the NASA Conference on Intelligent Data Understanding (CIDU 2010), 2010 (with T. Supine, D.J. Gagne II, N. Troutman, M, Collier, R.A. Brown, J. Basara and J. Williams).
“Spatiotemporal Relational Random Forests,” Proceedings of the 2009 IEEE International Conference on Data Mining (ICDM), workshop on Spatiotemporal Data Mining, electronically published, 2009 (with T. Supine, J. Williams and J. Abernathy).
“Spatio-temporal Multi-Dimensional Relational Framework Trees,” Proceedings of the 2009 IEEE International Conference on Data Mining (ICDM), workshop on Spatiotemporal Data Mining, electronically published, 2009 (with M. Bodenhamer, S. Bleckley, D. Fennelly and A.H. Fagg).
“Classification of Convective Areas Using Decision Trees,” Journal of Atmospheric and Oceanic Technology, Vol. 26, No. 7, pp. 1341-1353, 2009 (with D.J. Gagne II and J. Brotzge).