Raphaël Pestourie, PhD
Welcome where Artificial Intelligence (AI) meets scientific computing for engineering applications!
The goal of my group is to extend the horizon of accurate models for the optimization of engineering solutions. For example, we introduce models where trial and error and heuristics are the state of the art for practitioners. We formulate engineering questions as computational optimization problems and develop techniques to find optimal answers with an efficient combination of data and computing resources. To that end, my group develops fast approximate PDE models and scientific machine learning models that combine AI models and scientific models, end to end. These new models enable the ressource-efficient and large-scale optimization of engineering solutions in the following areas:
Large-scale inverse design in electromagnetism (up to one billion design parameters),
Co-design of physical hardware and software (aka End-to-end optimization),
AI-enhanced optimization methodologies via surrogate models, and via topology or shape optimization.
My PhD and postdoctoral research have been generously supported by MIT-IBM Watson AI Lab, IBM, the Simons Foundation, DARPA, the Army Research Office, arpa-e, the Institute for Soldier Nanotechnologies, and the French Fulbright Commission. I have published in journals like Nature Communications, npj Computational Materials, the SIAM Journal on Scientific Computing, Optics Express, ACS Photonics, Nanophotonics, Advanced Optical Materials, Physical Review Research, Physical Review A, to name a few. I am also a regular reviewer for these journals and for (scientific) machine learning conferences.
Keywords: inverse design, artificial intelligence, scientific machine learning, PDEs, electromagnetism, statistical optics, scientific computing, interpolation, large-scale optimization, Photonics, metasurfaces, end-to-end optimization, AI, active learning, Bayesian statistics, surrogate models.
Information about my group
My group is hiring! If you are interested in collaborating with me, please don't hesitate to reach out. I strongly support the Georgia Tech value that "We thrive on diversity."
I am very fortunate to advise the following students:
PhD student in my group
Xian Mae Hadia (currently MSc in CS at Georgia Tech, PhD expected to start Fall 2024)
MIT PhD student that I mentor scientifically
Lorenzo Xavier van Muñoz (MIT Physics, NSF Graduate Research Fellow and a Dean of Science Fellow, former Mellon Mays Undergraduate Fellow at Caltech)
Past students thatI advised or mentored
Sophie Fisher (PhD at MIT EECS)
Jerrell Cockerham from Colorado College through MIT Summer Research Program 2020 (now PhD candidate in Mathematics at Rice university)
Before joining the faculty at Georgia Tech, I earned five masters, a PhD, and completed my postdoctoral studies:
Diplôme grande école from ESSEC
Ingénieur des Arts et Manufactures specialized in Physics from École Centrale Paris (now CentraleSupelec)
Master of research in Nanosciences from Université Paris Saclay
MBA from ESSEC
AM in Statistics from Harvard University
PhD in Applied Mathematics with a secondary field in Computational Science and Engineering from Harvard John A. Paulson School of Engineering and Applied Sciences
Postdoctoral studies in the Mathematics department at MIT (3 years).
During my PhD, I was an Arthur Sachs Fellow selected by the French Fulbright Commission, and a Jean Gaillard fellow selected by the Board of Directors of the École Centrale des Arts et Manufactures in Paris. In addition, I was awarded membership into the Harvard Graduate School Leadership Institute through the Harvard Kennedy School’s Center for Public Leadership.
I am a strong believer that research should result in innovation and commercialization. I have working experience in a quantitative trading hedge fund and in startups both as an employee and as a founder. I have published many peer-reviewed articles and am a patent inventor.
I am originally from France, and I have studied languages and cultures of other people through pursuing internships and advanced degrees in several countries. Outside work, I play music with/for my bicultural, multilingual family.
Selected videos of invited talks
Invited talk at SciMLCon on March 23rd 2022 Physics-enhanced deep surrogates trained end to end
Invited seminar at IBM on February 24th 2022 Scientific machine learning: from optics to deep surrogates
Invited seminar at MERL on February 8th 2022 Extreme optics design as a large-scale optimization problem