FDL.AI tackles knowledge gaps in space science by pairing machine learning experts with researchers in Earth science, climate and energy, heliophysics, astrobiology, exploration medicine and planetary science for an intensive research sprint, held from June - August each year.  Although the journey is a year long cycle: from challenge definition through to finished result (Tech Memo and trained algorithm and data products) takes 12 months. 

Interdisciplinary four-person teams of PhD and postdoc level researchers and a faculty of domain and ML experts address tightly defined science challenges which are informed by knowledge of “what’s possible in ML”. The faculty, who are subject matter experts, provide support to the teams and drive research quality and push to more ambitious solutions. External and partner experts, special guests, and reviewers from space agency stakeholders contribute to the understanding of the problem and provide a community of expertise that drives excellence. 

FDL.AI’s format encourages rapid iteration and prototyping to create outputs with meaningful application, with substantial compute resources provided by our commercial partners. This combination of curated challenges, close mentorship, community of expertise and an emphasis on rapid prototyping has ensured a high success rate for research outcomes.  

As such, FDL.AI has demonstrated how structured interdisciplinary problem solving, radical collaboration methods and partnering with commercial organizations with relevant expertise can be useful to the science and technology goals of NASA, the DOE and ESA.