Thermodynamics-informed latent space dynamics identification
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- North Carolina State University, Raleigh, NC (United States)
This software showcases a latent space dynamics identification method, namely tLaSDI, that embeds the first and second principles of thermodynamics. The latent variables are learned through an autoencoder as a nonlinear dimension reduction model. The latent dynamics are constructed by a neural network-based model that precisely preserves certain structures for the thermodynamic laws through the GENERIC formalism. An abstract error estimate is established, which provides a new loss formulation involving the Jacobian computation of autoencoder. The autoencoder and the latent dynamics are simultaneously trained to minimize the new loss. Computational examples demonstrate the effectiveness of tLaSDI, which exhibits robust generalization ability, even in extrapolation. In addition, an intriguing correlation is empirically observed between a quantity from tLaSDI in the latent space and the behaviors of the full-state solution.
- Short Name / Acronym:
- tLaSDI
- Site Accession Number:
- LLNL-CODE-867909
- Software Type:
- Scientific
- License(s):
- MIT License
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)Primary Award/Contract Number:AC52-07NA27344
- DOE Contract Number:
- AC52-07NA27344
- Code ID:
- 142379
- OSTI ID:
- code-142379
- Country of Origin:
- United States
Similar Records
Latent Space Dynamics Identification
Weak-Form Latent Space Dynamics Identification