Frontier Development Laboratory (FDL) entering its sixth year, with teams of researchers who will use AI and machine learning to tackle seven challenges in heliophysics, astronaut health, lunar resources, and earth sciences. FDL applies AI technologies to science to push the boundaries of research and develop new tools to help solve some of humanity’s greatest challenges. For the second year in a row, the FDL, which typically brings together researchers, mentors and faculty from around the world at the SETI Institute in Mountain View, Calif., Will take place virtually.
“In an impressive pivot, our 2020 FDL participants demonstrated that interdisciplinary researchers can achieve extraordinary results in an intense sprinting environment and do so virtually, across approximately nine time zones,” said Bill Diamond, President and CEO of the SETI Institute. “We FDL AI / ML Research Accelerator will be a virtual program again this year, but we anticipate extraordinary results! ”
FDL is a public-private partnership with NASA in the USA and ESA in Europe. It brings together some of the brightest minds in space science, AI, and business, including Google Cloud, Lockheed Martin, Luxembourg Space Agency, Intel, Microsoft, MIT Portugal, Mayo Clinic, USGS, and NVIDIA. New partners this year include the Lawrence Berkeley National Laboratory. Other partners include IBM and Planet. FDL is hosted by the SETI Institute and the NASA Ames Research Center.
FDL’s goal is to apply the powerful synergies between physics, simulation and machine learning – many of which are emerging in the commercial sector – to issues important to space exploration and humanity.
Over the past six years, FDL has successfully demonstrated the potential of interdisciplinary AI approaches to address the challenges of planetary defense, space weather and lunar prospecting. FDL researchers have helped advance the state of the art in the use of AI to predict solar activity, map lunar resources, build 3D shape models of potentially dangerous asteroids, discover unclassified meteor showers and determine the effectiveness of asteroid mitigation strategies.
FDL fills knowledge gaps in space science by pairing experts in machine learning with researchers in astronomy, astrophysics, astrobiology and planetary sciences. They work together for an intensive eight-week research sprint, held during the summer vacation of the academic year – although the journey from the definition of the challenge to the end result (technical memo and trained algorithm and data products) takes 12 months.
Interdisciplinary teams of four composed of doctoral and postdoctoral researchers and a faculty of three experts in the field and machine learning tackle narrowly defined scientific challenges, informed by knowledge of “what is possible in ML”. The professors, experts in the field, support the teams, steer the quality of research and push for more ambitious solutions. External and partner experts, special guests and stakeholder reviewers from space agencies help understand the problem and provide a community of expertise that fosters excellence.
FDL 6.0 will build on the work, processes, and learning developed over the previous five cycles, with the potential to deepen the impact of work and advance science in new ways.