CISL Seminar Series - "Stochastic Evolutionary Algorithms Guided by Machine Learning for Atmospheric Source Detection"

Stochastic Evolutionary Algorithms Guided by Machine Learning for Atmospheric Source Detection

Guido Cervone
Pennsylavania State University

In this talk I will present a methodology based on evolutionary algorithms guided by machine learning for the characterization of atmospheric sources.  In traditional evolutionary (a.k.a. genetic) algorithms, a problem is optimized in parallel by maintaining a population of candidate solutions, which are evaluated according to an objective function, and evolved through selection operators and pseudo-random change operators.  In this talk, I will present a variant for evolutionary algorithms where the changes to candidate solutions are made through machine learning rule generation and instantiation.

Dr. Guido Cervone was born in Italy.  He received the B.S. in Computer Science from the Catholic University of America in Washington D.C in 1998., the M.S. in Computer Science and Ph.D. in Computational Sciences and Informatics with specialization in Knowledge Mining from George Mason University in Fairfax VA in 2000 and 2005 respectively.  

He is Associate Professor of Geoinformatics, Meteorology and Atmospheric Science at the Pennsylvania State University, University Park, PA. At Penn State, he serves as the Associate Director of the Institute for CyberScience, Director of the Geoinformatics and Earth Observation laboratory, and faculty affiliate of the Environmental and Energy Study Institute (EESI).  He is also Affiliate Scientist with the Research Application Laboratories (RAL) at the National Center for Atmospheric Research (NCAR) in Boulder, CO, and Adjunct Professor at the Lamont Doherty Earth Observatory (LDEO), Columbia University, in Palisades, NY. 
His expertise is in geoinformatics, machine learning and remote sensing, and his research focuses on the development and application of computational algorithms for the analysis of remote sensing, numerical modeling and social media spatio-temporal Big Data. The main problem domains are related to environmental hazards and renewable energy forecasting.
Refreshments will be served at 9:45am outside of the MSR!
Wednesday, July 11, 2018
10:00 a.m. - 11:00 a.m.
Mesa Lab, Main Seminar Room


Room Number: 
Main Seminar Room

Type of event:

Will this event be webcast to the public by NCAR|UCAR?: 
Announcement Timing: 
Monday, July 2, 2018 to Wednesday, July 11, 2018
Calendar Timing: 
Wednesday, July 11, 2018 - 10:00pm to 11:00pm

Random Profile


Recent & Upcoming Visitors