Dr. Lukas Mandrake is a senior researcher and group supervisor of the Machine Learning (ML) and Instrument Autonomy group at JPL since 2002. His group brings ML techniques to bear against a wide range of applied problems in space, science, technology, and medicine. Our products have empowered flight missions (MSL Curiosity rover, MER Opportunity/Spirit rovers, EO-1, OCO-2/3…), advanced the state of the art for commercial customers like Kaiser, Statoil, and Chevron, were infused into numerous university settings, and addressed governmental agency needs (USDA, DOE, and DOD). Specifically, Mandrake specializes on scoping a question to make it answerable given available data, followed by creating ML-based solutions that are explainable and scientifically defensible (e.g. no “black box”).

Lukas is also an ML liaison to the Information and Data Science program office at JPL, bringing a “trench-view” perspective on data science to the highest levels of strategy. He is passionate about bringing Data Science and especially ML to the JPL science community as well as the Ops and On-board autonomy systems. Oftentimes, these low-hanging fruits remain untouched due to cultural and perception differences between siloed areas of specialization; Lukas has been functioning as a liaison to ease the technological transfer of ML into these high-impact areas with significant success and over twenty major publications in applied ML application.

While working on the Orbiting Carbon Observatory (OCO-2) mission, he invented a unique system for estimating the uncertainty of observations called the Data Ordering Genetic Optimization (DOGO). DOGO went on to place 2nd for the prestigious, NASA-wide Software of the Year award. Mandrake is also an enthusiastic and award-winning speaker & educator, bringing the promise of ML to new fields and applications as well as science education in general. He passionately works to educate children in science literacy and critical thinking, and has hosted hundreds of school children on interactive tours of JPL.

Prior to his work at JPL and during his educational training, Mandrake built models of rental income vs. apartment amenities for real estate, coded and wrote dialog for several major computer games, and constructed a unique plasma simulator for auroral investigations.

Mandrake entered college at the age of thirteen and spent his “high school” years exploring college topics in mathematics, chemistry, and physics. He received a bachelor’s degree (BSE) in Engineering Physics from the University of Arizona in 1995. He went on to receive a Masters in Theoretical Plasma Physics and a PhD in Computational Plasma Physics from the University of California, Los Angeles in 2002. While there, he also implemented and oversaw new, computerized physics labs for undergraduates, receiving several outstanding teaching awards.

View my recent Caltech seminar on how machine learning can support scientific discovery.

Find my publications on Google Scholar

Contact

Education

• Physics (PhD) - University of California Los Angeles
• Physics (MS) - University of California Los Angeles
• Engineering Physics (BS) - University of Arizona

Research Interests

• Interpretable Machine Learning
• Genetic Algorithms
• Data-Driven Science
• Data Quality Estimation
• Compute-constrained Machine Learning