Computing non-equilibrium trajectories by a deep learning approach

Abstract

Predicting the occurence of rare and extreme events in complex systems is a well-known problem in non-equilibrium physics. These events can have huge impacts on human societies. New approaches have emerged in the last ten years, which better estimate tail distributions. They often use large deviation concepts without the need to perform heavy direct ensemble simulations. In particular, a well-known approach is to derive a minimum action principle and to find its minimizers. The analysis of rare reactive events in non-equilibrium systems without detailed balance is notoriously difficult either theoretically and computationally. They are described in the limit of small noise by the Freidlin-Wentzell action. We propose here a new method which minimizes the geometrical action instead using neural networks: it is called deep gMAM. It relies on a natural and simple machine-learning formulation of the classical gMAM approach. We give a detailed description of the method as well as many examples. These include bimodal switches in complex stochastic (partial) differential equations, quasi-potential estimates, and extreme events in Burgers turbulence.

References in corpus (26)

• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• The large deviation approach to statistical mechanics
• Burgers Turbulence
• Computation of extreme heat waves in climate models using a large deviation algorithm
• Instantons in Burgers Equation
• A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks
• Deep splitting method for parabolic PDEs
• Intermittency of Burgers' Turbulence
• Viscous Instanton for Burgers' Turbulence
• The instanton method and its numerical implementation in fluid mechanics
• A rare event algorithm links transitions in turbulent flows with activated nucleations
• A multiple replica approach to simulate reactive trajectories
• Chaotic magnetic field reversals in turbulent dynamos
• Computing transition rates for the 1-D stochastic Ginzburg--Landau--Allen--Cahn equation for finite-amplitude noise with a rare event algorithm
• Instanton filtering for the stochastic Burgers equation
• Learning nonequilibrium control forces to characterize dynamical phase transitions
• Statistical behavior of adaptive multilevel splitting algorithms in simple models
• Ohta-Jasnow-Kawasaki Approximation for Nonconserved Coarsening under Shear
• Fluctuational transitions through a fractal basin boundary
• Multistability and rare spontaneous transitions in barotropic $\beta$-plane turbulence
• Escaping from nonhyperbolic chaotic attractors
• Relevance of instantons in Burgers turbulence
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• Gel'fand-Yaglom type equations for calculating fluctuations around Instantons in stochastic systems
• Trace formula for activated escape in noisy maps