Empowering metasurfaces with inverse design: principles and applications

Z Li, R Pestourie, Z Lin, SG Johnson, F Capasso - Acs Photonics, 2022 - ACS Publications
Conventional human-driven methods face limitations in designing complex functional
metasurfaces. Inverse design is poised to empower metasurface research by embracing fast …

Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport

L Lu, R Pestourie, SG Johnson, G Romano - Physical Review Research, 2022 - APS
Deep neural operators can learn operators mapping between infinite-dimensional function
spaces via deep neural networks and have become an emerging paradigm of scientific …

[HTML][HTML] Inverse design enables large-scale high-performance meta-optics reshaping virtual reality

Z Li, R Pestourie, JS Park, YW Huang… - Nature …, 2022 - nature.com
Meta-optics has achieved major breakthroughs in the past decade; however, conventional
forward design faces challenges as functionality complexity and device size scale up …

Neural operator-based surrogate solver for free-form electromagnetic inverse design

Y Augenstein, T Repan, C Rockstuhl - ACS Photonics, 2023 - ACS Publications
Neural operators have emerged as a powerful tool for solving partial differential equations in
the context of scientific machine learning. Here, we implement and train a modified Fourier …

[HTML][HTML] Prediction of solar energetic events impacting space weather conditions

MK Georgoulis, SL Yardley, JA Guerra… - Advances in Space …, 2024 - Elsevier
Aiming to assess the progress and current challenges on the formidable problem of the
prediction of solar energetic events since the COSPAR/International Living With a Star …

Learning continuous models for continuous physics

AS Krishnapriyan, AF Queiruga, NB Erichson… - Communications …, 2023 - nature.com
Dynamical systems that evolve continuously over time are ubiquitous throughout science
and engineering. Machine learning (ML) provides data-driven approaches to model and …

Diffeomorphism Neural Operator for various domains and parameters of partial differential equations

Z Zhao, C Liu, Y Li, Z Chen, X Liu - Communications Physics, 2025 - nature.com
Solving partial differential equations (PDEs) across varying geometric domains and
parameters represents a significant challenge in fields such as materials science …

Physics‐Informed Machine Learning for Inverse Design of Optical Metamaterials

S Sarkar, A Ji, Z Jermain, R Lipton… - Advanced Photonics …, 2023 - Wiley Online Library
Optical metamaterials manipulate light through various confinement and scattering
processes, offering unique advantages like high performance, small form factor and easy …

Rapid prediction of indoor airflow field using operator neural network with small dataset

H Gao, W Qian, J Dong, J Liu - Building and Environment, 2024 - Elsevier
Indoor airflow is one of the most critical factors affecting room comfort. The accurate
prediction of indoor airflow fields is essential for efficient environmental control. However …

Active Learning for Neural PDE Solvers

D Musekamp, M Kalimuthu, D Holzmüller… - arXiv preprint arXiv …, 2024 - arxiv.org
Solving partial differential equations (PDEs) is a fundamental problem in engineering and
science. While neural PDE solvers can be more efficient than established numerical solvers …