Raphael
Pestourie

General Information

Email:
rpestourie3@gatech.edu
Phone:
4048943889
Location - Building:
Coda
Location - Room:
S1319
Roles:
Professor (any rank)
Primary Unit:
School of Computational Science and Engineering
Website URL
Group website

Details

Degrees with subject and Postdoc Experience:
Degree Type
Postdoctoral scholar
Subject
Applied Mathematics
Year
2020-2023
Institution
MIT
Location
Cambridge, MA
Degree Type
PhD
Subject
Applied Mathematics
Year
2020
Institution
Harvard Univeristy
Location
Cambridge, MA
Degree Type
MA
Subject
Statistics
Year
2020
Institution
Harvard University
Location
Cambridge, MA
Degree Type
MBA
Subject
Business Administration
Year
2014
Institution
ESSEC Business School
Location
Cergy, France
Degree Type
Diplome d'ingenieur des arts et manufactures
Subject
Applied Physics
Year
2014
Institution
Ecole Centrale Paris (Now CentraleSupelec)
Location
Chatenay-Malabry, France
Degree Type
Diplome Grande Ecole
Subject
Management
Year
2014
Institution
ESSEC Business School
Location
Cergy, France
Degree Type
Master of Research
Subject
Nanosciences
Year
2013
Institution
Université Paris-Saclay
Location
Saclay, France
Statement of Research Interests:

My group develops solver-informed artificial-intelligence (AI)-enabled methods that enable efficient partial differential equation–constrained optimization (PDE-CO): a unifying mathematical framework for most engineering design problems, from optics and mechanics to transport and materials. Our goal is to make AI and physics co-evolve, so that learning and computation accelerate one another, while removing redundancies of the state of the art. In this Engineering + AI paradigm, we integrate the nonlinear fitting power of neural networks with the generalization capability of numerical solvers to design physical systems more efficiently, interpretably, and at unprecedented scale.

Statement of Teaching Interests:

I train both undergraduate and graduate students. My teaching covers topics in numerical methods and scientific machine learning. 

Selection of recent research, scholarly, and creative activities:

Marzban R, Adibi A, Pestourie R "Inverse Design in Nanophotonics via Representation Learning," Advanced Optical Materials, 2025 

M. R. Peters, D. Mojahed, W. Ma, R. Pestourie, T. Gu, S. G. Johnson, J. Hu "Integrated photonic spectrometers: a critical review." Photonics Insights, 4(4), R10-R10, 2025. 

R. Marzban, H. Abiri, R. Pestourie†, A. Adibi† “HiLAB: A Hybrid Inverse-Design Framework.” Small Methods, 2025

R. Pestourie “Fast approximate solvers for metamaterials design in electromagnetism.” IEEE Antennas and Propagation Magazine, 2025

W. Ma, R. Pestourie, SG Johnson, "Time-reversal-symmetry bounds on electromagnetic fields" Physical Review Applied, 2025

W. Ma, R. Pestourie, et al. "Multiplicative resonant enhancement of chemical detection" Physical Review Applied, 2024

R. Pestourie, et al. "Physics-enhanced deep surrogates for partial differential equations," Nature Machine Intelligence, 2023

Z. Li*, R. Pestourie*, et al. "Inverse design enables large-scale high-performance meta-optics reshaping virtual reality," Nature Communications, 2022

R. Pestourie et al. "Active learning of deep surrogates for PDEs: Application to metasurface design," npj Computational Materials, 2020

R. Pestourie, et al., “Inverse design of large-area metasurfaces,” Optics Express, 2018