Deep learning probability flows and entropy production rates in active matter

Abstract

Active matter systems, from self-propelled colloids to motile bacteria, are characterized by the conversion of free energy into useful work at the microscopic scale. They involve physics beyond the reach of equilibrium statistical mechanics, and a persistent challenge has been to understand the nature of their nonequilibrium states. The entropy production rate and the probability current provide quantitative ways to do so by measuring the breakdown of time-reversal symmetry. Yet, their efficient computation has remained elusive, as they depend on the system's unknown and high-dimensional probability density. Here, building upon recent advances in generative modeling, we develop a deep learning framework to estimate the score of this density. We show that the score, together with the microscopic equations of motion, gives access to the entropy production rate, the probability current, and their decomposition into local contributions from individual particles. To represent the score, we introduce a novel, spatially-local transformer network architecture that learns high-order interactions between particles while respecting their underlying permutation symmetry. We demonstrate the broad utility and scalability of the method by applying it to several high-dimensional systems of active particles undergoing motility-induced phase separation (MIPS). We show that a single network trained on a system of 4096 particles at one packing fraction can generalize to other regions of the phase diagram, including systems with as many as 32768 particles. We use this observation to quantify the spatial structure of the departure from equilibrium in MIPS as a function of the number of particles and the packing fraction.

References in corpus (21)

• Novel type of phase transition in a system of self-driven particles
• Motility-Induced Phase Separation
• Elucidating the Design Space of Diffusion-Based Generative Models
• A self-propelled particle in an external potential: is there an effective temperature?
• Statistical Mechanics of Active Ornstein Uhlenbeck Particles
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Path-integral analysis of fluctuation theorems for general Langevin processes
• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• Irreversibility and biased ensembles in active matter: Insights from stochastic thermodynamics
• Entropy production of active particles and for particles in active baths
• Fluctuation Relations for Diffusion Processes
• Time-(ir)reversibility in active matter: from micro to macro
• Cumulants and large deviations of the current through non-equilibrium steady states
• Learning hydrodynamic equations for active matter from particle simulations and experiments
• Play. Pause. Rewind. Measuring local entropy production and extractable work in active matter
• The "footprints'' of irreversibility
• Clausius relation for active particles: what can we learn from fluctuations?
• Estimating time-dependent entropy production from non-equilibrium trajectories
• Time-reversal symmetry violations and entropy production in field theories of polar active matter
• A unified, geometric framework for nonequilibrium protocol optimization
• Deep learning probability flows and entropy production rates in active matter

Cited by in corpus (5)

• Deep learning probability flows and entropy production rates in active matter
• Variational time reversal for free energy estimation in nonequilibrium steady states
• Inferring entropy production in many-body systems using nonequilibrium maximum entropy
• Inferring activity from the flow field around active colloidal particles using deep learning
• Effective Energy, Interactions And Out Of Equilibrium Nature Of Scalar Active Matter