Machine learning structure preserving brackets for forecasting irreversible processes
arXiv:2106.12619
Abstract
Forecasting of time-series data requires imposition of inductive biases to obtain predictive extrapolation, and recent works have imposed Hamiltonian/Lagrangian form to preserve structure for systems with reversible dynamics. In this work we present a novel parameterization of dissipative brackets from metriplectic dynamical systems appropriate for learning irreversible dynamics with unknown a priori model form. The process learns generalized Casimirs for energy and entropy guaranteed to be conserved and nondecreasing, respectively. Furthermore, for the case of added thermal noise, we guarantee exact preservation of a fluctuation-dissipation theorem, ensuring thermodynamic consistency. We provide benchmarks for dissipative systems demonstrating learned dynamics are more robust and generalize better than either "black-box" or penalty-based approaches.
References in corpus (6)
- Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling
- ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
- Hamiltonian Graph Networks with ODE Integrators
- Turbulence forecasting via Neural ODE
- MALI: A memory efficient and reverse accurate integrator for Neural ODEs
- Enforcing exact physics in scientific machine learning: a data-driven exterior calculus on graphs