SmartSat Distinguished Speaker – Prof Ashish Mahabal

Astronomer and Lead Computational and Data Scientist, CalTech

Near-Earth and Deep-Space Computing: Opportunities and the Future

The exploration of space and the resulting science that humans have managed over the last several decades has been limited by on-board processing, and possible data transfer to Earth. Given the high costs involved the emphasis has been on doing a few things, but doing them well. Recent developments in processor technology combined with machine learning advances has opened up many new possibilities for extended scientific missions as well as possible ways to take advantage of serendipitous observations. Implementation of some such technologies has already taken place near-Earth. Over the last year the Keck Institute for Space Studies (KISS) at Caltech brought together researchers and industry experts to brainstorm how best to take advantage of the much larger data-taking and processing capabilities we can now incorporate on individual spacecraft and on small internetworked components like landers, rovers, and orbiters. We will elaborate the possibilities that came up through a few use cases, both near-Earth and in deep space. Besides Earth science missions and those targeted towards satellites of planets, more general astrophysical ones studying extragalactic space also stand to benefit.

Prof Ashish Mahabal is an astronomer (Division of Physics, Mathematics, and Astronomy) and Lead Computational and Data Scientist (Center for Data Driven Discovery) at the California Institute of Technology, Pasadena, USA, and an adjunct faculty at the Inter-University Center for Astronomy and Astrophysics, Pune, India. His interests include Large Sky Surveys, Classification, Deep Learning, and Methodology Transfer to other complex-data fields like medicine.

He leads the ML for the Zwicky Transient Facility, a large sky survey covering the entire Northern Sky every few nights. He also works with the Data Science group at the Jet Propulsion Laboratory (JPL) and is part of the Consortium for Molecular and Cellular Characterization of Screen-Detected Lesions (MCL), and the Early Detection Research Network (EDRN) for cancer.