Description

ExoMiner is a new deep neural network we have recently developed and used to validate hundreds of new exoplanets from the Kepler mission. ExoMiner utilizes most unique elements of Kepler SOC/TESS SPOC data validation summary report in their original format in order to classify transit signals. This is unlike the existing machine classifiers that either do not use a comprehensive list of diagnostic tests required for the correct classification of transit signals or use a simplified version of these tests in the form of a few scalar values. In this talk, I will present ExoMiner, its unique characteristics, and what makes it highly accurate and suitable for exoplanet validation. We also introduce ExoMiner++, a more powerful version of ExoMiner, that addresses the existing shortcomings of the ExoMiner and is more suitable to handle Transiting Exoplanet Survey Satellite (TESS) mission data.

****************

Speaker Bio

Holder of a PhD in computer science with focus on machine learning and data mining, Hamed Valizadegan joined NASA Ames Research Center (USRA) as a machine learning research scientist in 2013. At Ames, he has been involved with multiple projects including Automatic Planet Discovery (Kepler and TESS missions), Vascular Image Segmentation (Space Biology), Display Verification (Orion mission), and data driven prognostics (Hubble Space Telescope). Before joining NASA Ames, he spent three years at University of Pittsburgh conducting research in Medical Informatics. He has published more than 25 peer reviewed papers and been invited to many industrial and academic level conferences as speaker and keynote speaker.”

*************

Zoom Link

Time: Sep 14, 2022 06:00 PM Pacific Time (US and Canada)

Join Zoom Meeting

https://us02web.zoom.us/j/87641056824?pwd=ckI5K0trcE5tRnZUMnVtWWx0Y1FtUT09

Meeting ID: 876 4105 6824

Passcode: 060478