David Fleming [EMAIL]

Graduate Student, Astronomy
University of Washington eScience Institute
University of Washington

Research Expertise: Exoplanet habitability assessment, machine learning

VPL Focus: Task C: The Habitable Planet



As a member of the UW eScience Institute’s Integrative Graduate Education and Research Traineeship (IGERT) in Big Data and Data Science, I work on dealing with the large parameter space required to accurately model exoplanet systems using the code VPLANET (see Barnes et al. 2016).  The massive parameter space afforded by VPLANET’s inclusion of numerous physical modules ranging from atmospheric escape to orbital dynamics necessitates the use machine learning techniques to analyze the output of a large number of simulations and to intelligently traverse this parameter space.  I am particularly interested in the application of machine learning techniques to wrangle this large parameter space to draw inferences about exoplanet habitability and understand the underlying physical processes that influence habitability.