Interdisciplinary collaboration

I am frequently engaged in research that crosses disciplinary boundaries, combining several research disciplines together. One example is my work at the interface between machine learning and science, combining both algorithmic development and practical applications. In addition to my scientific domain (particle physics), I have collaborated with others in the following scientific and non-scientific domains: planetary science, cosmology, medicine (vaccines) and music.

In planetary science, I have collaborated with researchers from the Johns Hopkins University Applied Physics Laboratory and NASA on a machine learning project analyzing geochemical terrains from MESSENGER mission data. As a proof of concept, we have learned to extract features from lunar elemental composition data and make accurate predictions of features of the Moon, including its albedo map. We are applying similar techniques to data collected by the MESSENGER mission from Mercury, where the relationships among geochemical terrains are much more complex and can shed light on the origin of Mercury. We are applying a similar approach to data from other planetary science missions, including future missions. We have also developed a tool for cosmic-ray imaging studies with mission imagery from space.

I additionally collaborate with theoretical astrophysicists and cosmologists from Brown University Theoretical Physics Center to answer the question what is dark matter by applying deep learning techniques to identify possible dark matter substructure in strong gravitational lensing.

In 2018, I participated in a panel on machine learning for accelerated vaccine and immunotherapy development, focused on machine learning applications and predictive modeling to make more effective vaccines, part of the 2nd World Vaccine and Immunotherapy Congress , which stemmed from my project with Sanofi Pasteur.

In 2016, I have consulted and collaborated with Sanofi Pasteur, a global pharmaceutical company in order to develop better vaccines. We have applied modern machine learning techniques to challenges facing large-scale vaccine production, including making higher-quality antigens and spotting problems before they negatively affect vaccine production. It is my hope that the outcome of this project can help speed up vaccine production, something that would benefit all of us.

I always welcome interesting projects. Please contact me if you are facing a challenging scientific problem where an interdisciplinary approach may lead to a unique solution.