Joining the faculty in January 2014 as an associate professor of geoinformatics, Cervone has a joint appointment in the Department of Geography, and in the newly formed Institute for Cyberscience. He is an affiliate scientist with the Research Application Laboratory (RAL) at the National Center for Atmospheric Research (NCAR) in Boulder, CO.
My big passion is sailing. I am a volunteer instructor at the US Naval
Academy (USNA), in the Offshore Sailing Training Squadron (OSTS)
program. I race on the Chesapeake bay about once a week, and I have
done several offshore passages in the Atlantic Ocean and in the
Mediterranean Sea. I own a 28' keel sailboat, a 14' 420 dinghy, and a
My research revolves around:
a) Using Geoinformatics as the framework that provides geospatial analysis tools to solve problems, primarily based on machine learning and statistics.
b) Remote sensing, numerical simulations, and social media to provide the big data that I need for my research.
c) Environmental Hazards as the main theme of the problems that I work on.
Currently, I work on three projects:
• The first concerns the fusion of remote sensing and social media data for disaster management. My plan is to use social media data, and other non-autoritative sources, to build a human terrain during and after a major disasters, and to use this extracted knowledge to fill in the gaps in remote sensing observations to to satellite orbits, clouds, and other sensor and carrier limitations. This project is currently being funded by DOT and by ONR.
• The second project relates to the source characterization of unknown and potentially toxic pollutants. I have recently applied my methodology to reconstruct the non-steady release rate for the radioactive leak at the Fukushima nuclear power plant. The methodology I developed uses machine learning rule induction (my forte) to guide a reasoning process that iteratively generates and evaluates candidate solutions. This work is currently being supported by NCAR.
• The third and newest project relates to the use of geoinformatics for the optimization of numerical model forecasts for wind energy power production. This project is also partially supported by NCAR.
- remote sensing
- environmental hazards
- social media