TY - GEN
T1 - Accelerated Optimization of Robust Nanophotonic Devices via Deep Learning
AU - Campbell, Sawyer D.
AU - Jenkins, Ronald P.
AU - Werner, Pingjuan Li
AU - Werner, Douglas Henry
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The potential for nanophotonic devices to disrupt existing and create new commercial applications has led to a surge in design and manufacturing research in recent years. Yet, new technologies must not only demonstrate performance advantages over legacy solutions, but also improved fabrication cost and reliability. Therefore, inverse-design techniques which optimize guaranteed performance in the presence of fabrication uncertainties are needed to maximize the yield achievable within a given process window. However, simulating a nominal structure and all potential perturbations caused by a variety of highly complex and coupled fabrication uncertainties results in a combinatorial explosion of solutions that ultimately makes direct optimization intractable. To overcome this, we exploit deep learning and demonstrate a neural network that accurately predicts the performance of a representative metasurface supercell in the presence of fabrication uncertainties. The trained neural network is subsequently paired with a modified multi-objective optimization procedure which enables one to study the tradeoffs between nominal performance and guaranteed performance.
AB - The potential for nanophotonic devices to disrupt existing and create new commercial applications has led to a surge in design and manufacturing research in recent years. Yet, new technologies must not only demonstrate performance advantages over legacy solutions, but also improved fabrication cost and reliability. Therefore, inverse-design techniques which optimize guaranteed performance in the presence of fabrication uncertainties are needed to maximize the yield achievable within a given process window. However, simulating a nominal structure and all potential perturbations caused by a variety of highly complex and coupled fabrication uncertainties results in a combinatorial explosion of solutions that ultimately makes direct optimization intractable. To overcome this, we exploit deep learning and demonstrate a neural network that accurately predicts the performance of a representative metasurface supercell in the presence of fabrication uncertainties. The trained neural network is subsequently paired with a modified multi-objective optimization procedure which enables one to study the tradeoffs between nominal performance and guaranteed performance.
UR - http://www.scopus.com/inward/record.url?scp=85202350063&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85202350063&partnerID=8YFLogxK
U2 - 10.1109/PN62551.2024.10621788
DO - 10.1109/PN62551.2024.10621788
M3 - Conference contribution
AN - SCOPUS:85202350063
T3 - 2024 Photonics North, PN 2024
BT - 2024 Photonics North, PN 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 Photonics North, PN 2024
Y2 - 28 May 2024 through 30 May 2024
ER -