Towards Science Autonomy for Planetary Missions: Data Science and Machine Learning to Support Future Missions to Mars, Titan, and Ocean Worlds | Victoria Da Poian
About This Video
Victoria Da Poian, Data Scientist, NASA Goddard Space Flight Center presents a Technical Talk at the 2024 WiDS Worldwide, Stanford conference.
Future planetary exploration missions, such as those targeting habitability and potential life on distant bodies like Titan and Enceladus, face communication constraints with limited transfer rates and short windows. Traditional ground-in-the-loop operations are impractical for such remote targets, necessitating additional autonomy for mission success. Leveraging machine learning and data science, our research aims to enable science autonomy onboard space missions. This autonomy allows spacecraft to make scientific decisions independently, optimizing exploration efficiency and maximizing scientific returns by streamlining data collection and analysis processes, particularly in mass spectrometry data analysis. Ultimately, this approach promises to revolutionize planetary science missions by enhancing exploration capabilities and scientific outcomes.
In This Video
Data Scientist, NASA Goddard Space Flight Center
Talk Title: Towards Science Autonomy for Planetary Missions: Data Science and Machine Learning to support future missions to Mars, Titan, and Ocean Worlds
Abstract: Future planetary exploration missions investigating habitability and potential life on distant bodies (e.g., Titan, Enceladus) will face communication constraints with limited transfer rates and short communication windows. The current space mission operations plans relying on ground-in-the-loop interactions are not suitable for such remote targets. To address this, new missions require additional autonomy to achieve their desired science return. Our research leverages machine learning and data science to enable science autonomy onboard space missions. Science autonomy would enable a spacecraft to make closed-loop scientific decisions without the need for constant communication with Earth’s science and operations teams. It has the potential to greatly enhance planetary science missions by enabling far more efficient exploration of planetary bodies, while optimizing the science data returned to Earth. We focus on methods for mass spectrometry data to support scientists’ decision-making process, make science operations faster and more efficient, and ultimately maximize space missions’ scientific returns.
Bio: Victoria Da Poian is a data scientist at NASA Goddard Space Flight Center who specializes in developing machine learning and data science tools for planetary science instruments. Her work centers on advancing science autonomy for space missions, allowing spacecraft to make independent scientific decisions without constant communication with teams on Earth. This innovation promises more efficient exploration of other planetary bodies and maximizes data returned to Earth.