PICL: Physics informed contrastive learning for partial differential equations
Neural operators have recently grown in popularity as Partial Differential Equation (PDE) surrogate models. Learning solution functionals, rather than functions, has proven to be a powerful approach to calculate fast, accurate solutions to complex PDEs. While much work has been performed evaluating...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2024-12-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0223651 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850057617898995712 |
|---|---|
| author | Cooper Lorsung Amir Barati Farimani |
| author_facet | Cooper Lorsung Amir Barati Farimani |
| author_sort | Cooper Lorsung |
| collection | DOAJ |
| description | Neural operators have recently grown in popularity as Partial Differential Equation (PDE) surrogate models. Learning solution functionals, rather than functions, has proven to be a powerful approach to calculate fast, accurate solutions to complex PDEs. While much work has been performed evaluating neural operator performance on a wide variety of surrogate modeling tasks, these works normally evaluate performance on a single equation at a time. In this work, we develop a novel contrastive pretraining framework utilizing generalized contrastive loss that improves neural operator generalization across multiple governing equations simultaneously. Governing equation coefficients are used to measure ground-truth similarity between systems. A combination of physics-informed system evolution and latent-space model output is anchored to input data and used in our distance function. We find that physics-informed contrastive pretraining improves accuracy for the Fourier neural operator in fixed-future and autoregressive rollout tasks for the 1D and 2D heat, Burgers’, and linear advection equations. |
| format | Article |
| id | doaj-art-2a80d49283ef451f83aeb5e2cf973df4 |
| institution | DOAJ |
| issn | 2770-9019 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Machine Learning |
| spelling | doaj-art-2a80d49283ef451f83aeb5e2cf973df42025-08-20T02:51:23ZengAIP Publishing LLCAPL Machine Learning2770-90192024-12-0124046107046107-1210.1063/5.0223651PICL: Physics informed contrastive learning for partial differential equationsCooper Lorsung0Amir Barati Farimani1Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, Pennsylvania 15213, USADepartment of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, Pennsylvania 15213, USANeural operators have recently grown in popularity as Partial Differential Equation (PDE) surrogate models. Learning solution functionals, rather than functions, has proven to be a powerful approach to calculate fast, accurate solutions to complex PDEs. While much work has been performed evaluating neural operator performance on a wide variety of surrogate modeling tasks, these works normally evaluate performance on a single equation at a time. In this work, we develop a novel contrastive pretraining framework utilizing generalized contrastive loss that improves neural operator generalization across multiple governing equations simultaneously. Governing equation coefficients are used to measure ground-truth similarity between systems. A combination of physics-informed system evolution and latent-space model output is anchored to input data and used in our distance function. We find that physics-informed contrastive pretraining improves accuracy for the Fourier neural operator in fixed-future and autoregressive rollout tasks for the 1D and 2D heat, Burgers’, and linear advection equations.http://dx.doi.org/10.1063/5.0223651 |
| spellingShingle | Cooper Lorsung Amir Barati Farimani PICL: Physics informed contrastive learning for partial differential equations APL Machine Learning |
| title | PICL: Physics informed contrastive learning for partial differential equations |
| title_full | PICL: Physics informed contrastive learning for partial differential equations |
| title_fullStr | PICL: Physics informed contrastive learning for partial differential equations |
| title_full_unstemmed | PICL: Physics informed contrastive learning for partial differential equations |
| title_short | PICL: Physics informed contrastive learning for partial differential equations |
| title_sort | picl physics informed contrastive learning for partial differential equations |
| url | http://dx.doi.org/10.1063/5.0223651 |
| work_keys_str_mv | AT cooperlorsung piclphysicsinformedcontrastivelearningforpartialdifferentialequations AT amirbaratifarimani piclphysicsinformedcontrastivelearningforpartialdifferentialequations |