Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport
Deep neural operators can learn operators mapping between infinite-dimensional function spaces via deep neural networks and have become an emerging paradigm of scientific machine learning. However, training neural operators usually requires a large amount of high-fidelity data, which is often diffic...
Main Authors: | Lu Lu, Raphaël Pestourie, Steven G. Johnson, Giuseppe Romano |
---|---|
Format: | Article |
Language: | English |
Published: |
American Physical Society
2022-06-01
|
Series: | Physical Review Research |
Online Access: | http://doi.org/10.1103/PhysRevResearch.4.023210 |
Similar Items
-
Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport
by: Lu, Lu, et al.
Published: (2022) -
Inverse design in nanoscale heat transport via interpolating interfacial phonon transmission
by: Johnson, Steven G., et al.
Published: (2022) -
Multifidelity importance sampling
by: Peherstorfer, Benjamin, et al.
Published: (2018) -
Physics-Informed Neural Networks with Hard Constraints for Inverse Design
by: Lu, Lu, et al.
Published: (2021) -
Multifidelity approximate Bayesian computation
by: Prescott, T, et al.
Published: (2020)