The widespread availability of machine learning (ML) technologies promises to disrupt scientific disciplines.
Popular open source ML frameworks are not only useful for data-driven model fitting, but also for efficient computation of physics-based models. This COSPAR 2021 workshop is dedicated to showcasing use cases of ML technologies to observational and simulation data.
This includes applications to:
Dr. Guhathakurta is the Lead Program Scientist for NASA's initiative called "Living With a Star" (LWS) which focuses on understanding and ultimately predicting solar variability and its diverse effects on Earth, human technology and astronauts in space. The systems science behind this new kind of weather outside of Earth's terrestrial atmosphere is known as "Space Weather". Read more.
She is also the Program Scientist for the recently launched twin satellites "Solar TErrestrial RElations Observatory" (STEREO). STEREO is a two-year mission which will employ two nearly identical space-based observatories - one ahead of Earth in its orbit, the other trailing behind - to provide the first-ever stereoscopic measurements to study the Sun and the nature of its coronal mass ejections, or CMEs and their impact on space-weather. In addition to leading science missions for the LWS program, Dr Guhathakurta also manages a theory, modeling and data analysis program to integrate scientific output, data and models to generate a comprehensive, systems understanding of Sun-Heliosphere-Planets coupling. She is the discipline scientist of this new discipline titled "Heliophysics".
Shirley Ho's research interests have ranged from using machine learning and statistics to tackle fundamental challenges in cosmology to finding new structures in our own Milky Way. Ho has broad expertise in theoretical astrophysics, observational astronomy and data science. Ho’s recent interest has been on understanding and developing novel tools in machine learning techniques and applying them to astrophysical challenges. Read more.
Her goal is to understand the universe’s beginning, evolution and its ultimate fate. Ho earned her Ph.D. in astrophysical sciences from Princeton University in 2008 and her bachelor’s degrees in computer science and physics from the University of California, Berkeley in 2004. She was a Chamberlain fellow and a Seaborg fellow at Lawrence Berkeley National Laboratory before joining Carnegie Mellon University in 2011 as an assistant professor. She became the Cooper Siegel Career Chair Professor and was appointed associate professor with tenure in 2016. She moved to Lawrence Berkeley Lab as a Senior Scientist in 2016 and to the Center of Computational Astrophysics (Simons Foundation) in 2018 as the group leader in Cosmology X Data Science.
Technical Organising Committee
The rise of machine learning (ML) and artificial intelligence (AI) techniques is creating opportunities for space science missions with unprecedented capabilities. By augmenting traditional rule-based decision making with AI techniques (such as decision policies in deep reinforcement learning), robotic missions may become highly autonomous. Furthermore, ML advances will augment the capabilities of crews serving in extended space missions.
Questions to be explored in this COSPAR 2021 workshop include:
Michael Seablom is the Chief Technologist for the Science Mission Directorate at NASA Headquarters. He has the responsibility for surveying and assessing technology needs for the Heliophysics, Astrophysics, Earth Science and Planetary Science Divisions and is the primary liaison to the NASA Office of Chief Technologist and the Space Technology Mission Directorate.
Salah Sukkarieh is the Professor of Robotics and Intelligent Systems at the University of Sydney and is the CEO of Agerris, a new Agtech startup company from the ACFR developing autonomous robotic solutions to improve agricultural productivity and environmental sustainability. He was the Director Research and Innovation at the Australian Centre for Field Robotics from 2007-2018, where he led the strategic research and industry engagement program in the world's largest field robotics institute. Read more.
He is an international expert in the research, development and commercialisation of field robotic systems and has led a number of robotics and intelligent systems R&D projects in logistics, commercial aviation, aerospace, education, environment monitoring, agriculture and mining. Salah was awarded the NSW Science and Engineering Award for Excellence in Engineering and Information and Communications Technologies in 2014, the 2017 CSIRO Eureka Prize for Leadership in Innovation and Science and the 2019 NSW Australian of the Year nominee. Salah is a Fellow of Australian Academy of Technological Sciences and Engineering (ATSE) and has over 500 academic and industry publications in robotics and intelligent systems.
Pierre-Philippe Mathieu is heading the Φ-lab Explore Office at the European Space Agency in ESRIN (Frascati, Italy), aiming to connect people, ideas and digital technologies to help shape the future of Earth Observation. He spent 20+ years working in the field of environmental and ocean modelling, weather risk management and remote sensing. He has a degree in mechanical engineering and M.Sc from University of Liege (Belgium), a Ph.D. in oceanography from the University of Louvain (Belgium), and a Management Degree from the University of Reading Business School (UK).
Prior to this, Animesh earned a Ph.D. from UC Berkeley and was a postdoc at the Stanford AI Lab. His research focuses on machine learning algorithms for perception and control in robotics. His work aims to build Generalizable Autonomy in robotics which involves a confluence of representations and algorithms for reinforcement learning, control and perception. His work has received multiple Best Paper Awards (ICRA, IROS, Hamlyn Symposium, Neurips Workshop, ICML Workshop) and has been covered in the press (New York Times, IEEE Spectrum, VentureBeat, Nature, BBC).
Technical Organizing Committee
As space becomes increasingly accessible due to the burgeoning global space industry, the volume of data produced by space research missions is expected to continue rising exponentially.
Opportunities for accelerating scientific discovery come with challenges in scaling traditional scientific processing workflows. A possible model for addressing such needs is the adoption of cloud compute technologies and open source software. At the same time, the deployment of cloud compute technologies can allow researchers to address calls for scientific reproducibility.
This COSPAR 2021 workshop will include tutorials and case studies addressing the following questions:
*Science, Technology, Engineering, the Arts and Mathematics (STEAM)
Richard is the Data Manager for the Frontier Development Lab, a family of research challenges across the US, Europe and Oceania, representing a +$1 million USD processing budget for compute-intensive remote sensing AI research. Outside of FDL, he is the CTO for an Oxford-based satellite Agritech DaaS start-up. He is finishing a DPhil at the University of Oxford, using Big Data and AI to forecast volcanic eruptions better.
Hsin-Fang Chiang has a PhD in Astronomy from the University of Illinois at Urbana-Champaign and is a data management developer at the Vera C. Rubin Observatory since 2015. The goal of the Rubin Observatory is to survey the entire sky continuously for 10 years and produce 500 petabytes of images to help us address a wide range of fundamental astrophysical questions. Hsin-Fang implements end-to-end data processing workflow, executes production and prepares data access for the observatory. Recently, she co-leads experiments to explore portable and scalable solutions in cloud environments for data hosting and processing.
A former exoplanet researcher, Grant is now Project Manager of the Zooniverse citizen science platform based at the University of Oxford. His job involves managing an international community of researchers, volunteers and web developers with the goal of enabling and progressing research across multiple diverse disciplines such as astronomy, ecology, biomedical sciences and the humanities.
Ryan P. Abernathey is an Associate Professor of Earth And Environmental Science at Columbia University and Lamont Doherty Earth Observatory. He received his Ph.D. from MIT in 2012 and a B.A. from Middlebury College. He joined Columbia in 2013 after a postdoc at Scripps Institution of Oceanography. Read more.
Ryan is a physical oceanographer who studies the large-scale ocean circulation and its relationship with Earth's climate. A central theme is how ocean mesoscale turbulence, i.e. eddies, waves and jets on scales of tens to hundreds of kilometers, contributes to the transport of momentum, heat and geochemically relevant tracers. Regionally, his main focus is the Southern Ocean, which surrounds Antarctica and links the three main ocean basins. High-resolution numerical modeling and satellite remote sensing are key tools in this research, which has led to an interest in high performance computing and big data. Prof. Abernathey helps lead the Pangeo project, an international collaboration aimed at accelerating data-intensive geoscience research through open source software and open infrastructure. He is a core developer of several open source scientific python libraries, including Xarray, Zarr and Xgcm.
Technical Organizing Committee
You will want to grab the official t-shirt of the first ever Virtual Assembly in the history of COSPAR.
Missed the Space Agency Leaders’ Round Table live? You can now download and view the recording.
See the whole weeks’ program at a glance. Commencing Friday 28th January 2021.
View the extended interview videos of all Awardees here.
COSPAR's objectives are to promote on an international level scientific research in space, with emphasis on the exchange of results, information and opinions and to provide a forum, open to all scientists, for the discussion of problems that may affect scientific space research.
These objectives are achieved through the organization of Scientific Assemblies, publications and other means.
COSPAR-K
