June 24, 2019, Mountain View, CA – Next week, NASA’s Frontier Development Lab, the SETI Institute, and FDL’s private sector and space agency partners will kick off its fourth annual summer research accelerator, applying the latest techniques in machine learning and artificial intelligence to address important science and exploration research challenges. This year, 24 early career Ph.Ds in AI and interdisciplinary natural science domains will be working in six interdisciplinary teams on challenge questions in the areas of space weather, lunar resources, Earth observation and astronaut health.

Since its inception, FDL has proven the efficacy of interdisciplinary research and the power of public-private partnership,” said Bill Diamond, president and CEO of the SETI Institute. “We are building on the extraordinary accomplishments of the researchers and mentors from the first three years and are excited to welcome another international group of amazing young scientists for this year’s program.  We are also extremely grateful to all our private sector partners and especially to Google Cloud for their leadership role.

Partner organizations support FDL by providing funding, supplying hardware, AI/ML algorithms, datasets, software and cloud-compute resources. They also support working teams with mentors and subject matter experts and hosting key events, such as the first-week AI boot camp and the final public team presentations. This year, FDL is pleased to welcome back partners Google Cloud, Intel, IBM, KX, Lockheed Martin, Luxembourg Space Agency, and NVIDIA. We are also pleased to welcome our new partners Canadian Space Agency, HPE and Element AI.

For the past three years, FDL has demonstrated the potential of applied AI to deliver important results to the space program in a very intense sprint, when supported in this way by a consortium of motivated partners. This approach has proven critical in unlocking meaningful progress in the complex and often systemic nature of AI problems.

"NASA has been at the forefront of machine learning - e.g. robotics,” said Madhulika Guhathakurta, program scientist and heliophysicist on detail at NASA’s Ames Research Center in Silicon Valley. “But we’re now witnessing an inflection point, where AI promises to become a tool for discovery - where the ability to process vast amount of heterogeneous data, as well as massive amount of data collected over decades, allows us to revisit the physics-based models of the past - to better understand underlying principles and radically improve time to insight.”

Each team is comprised of two Ph.D. or postdoc researchers from the space sciences and two data scientists, supported by mentors in each area. This year’s participants come from 13 countries and will be working on these challenges:

• Disaster prevention, progress and response (floods)
• Lunar resource mapping/super resolution
• Expanding the capabilities of NASA’s solar dynamics observatory
• Super-resolution maps of the solar magnetic field covering 40 years of space weather events
• Enhanced Predictability of GNSS Disturbances
• Generation of simulated biosensor data

Additionally, three teams in Europe will be addressing disaster prevention, progress and response (floods), ground station pass scheduling and assessing the changing nature of atmospheric phenomena, in partnership with the European Space Agency (ESA.

FDL 2019 kicks off next week at NVIDIA headquarters in Santa Clara, California, where teams will participate in a one-week intensive boot camp. The program concludes on August 15 at Google in Mountain View, California where teams will present the results of their work. Throughout the summer, teams will be working at the SETI Institute and NASA’s Ames Research Center near Mountain View.

<About the NASA Frontier Development Lab (FDL)

Hosted in Silicon Valley by the SETI Institute, NASA FDL is an applied artificial intelligence research accelerator developed in partnership with NASA's Ames Research Center. Founded in 2016, the NASA FDL aims to apply AI technologies to challenges in space exploration by pairing machine learning expertise with space science and exploration researchers from academia and industry. These interdisciplinary teams address tightly defined problems and the format encourages rapid iteration and prototyping to create outputs with meaningful application to the space program and humanity.

Download the PDF: