Attaining entropy production and dissipation maps from Brownian movies via neural networks

Abstract

Quantifying entropy production (EP) is essential to understand stochastic systems at mesoscopic scales, such as living organisms or biological assemblies. However, without tracking the relevant variables, it is challenging to figure out where and to what extent EP occurs from recorded time-series image data from experiments. Here, applying a convolutional neural network (CNN), a powerful tool for image processing, we develop an estimation method for EP through an unsupervised learning algorithm that calculates only from movies. Together with an attention map of the CNN's last layer, our method can not only quantify stochastic EP but also produce the spatiotemporal pattern of the EP (dissipation map). We show that our method accurately measures the EP and creates a dissipation map in two nonequilibrium systems, the bead-spring model and a network of elastic filaments. We further confirm high performance even with noisy, low spatial resolution data, and partially observed situations. Our method will provide a practical way to obtain dissipation maps and ultimately contribute to uncovering the nonequilibrium nature of complex systems.

arXiv comment15 pages, 8 figures

References in corpus (43)

• Adam: A Method for Stochastic Optimization
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• Stochastic thermodynamics, fluctuation theorems, and molecular machines
• Thermodynamic uncertainty relation for biomolecular processes
• Meso-scale turbulence in living fluids
• Estimating divergence functionals and the likelihood ratio by convex risk minimization
• Dissipation: The phase-space perspective
• Diffusive transport without detailed balance in motile bacteria: Does microbiology need statistical physics?
• Stochastic thermodynamics under coarse-graining
• Classical and Quantum Fluctuation Theorems for Heat Exchange
• Equality connecting energy dissipation with violation of fluctuation-response relation
• Broken detailed balance and non-equilibrium dynamics in living systems
• Nonequilibrium Physics in Biology
• Estimating dissipation from single stationary trajectories
• Hydrodynamic flow patterns and synchronization of beating cilia
• Entropy production and the arrow of time
• Irreversibility in active matter systems: Fluctuation theorem and mutual information
• Quantifying dissipation using fluctuating currents
• Entropy production in field theories without time reversal symmetry: Quantifying the non-equilibrium character of active matter
• Inferring entropy production from short experiments
• Fluctuation Theorem for Partially-masked Nonequilibrium Dynamics
• Lower bounds on dissipation upon coarse graining
• Inferring broken detailed balance in the absence of observable currents
• Estimating entropy production by machine learning of short-time fluctuating currents
• Oscillatory surface rheotaxis of swimming E. coli bacteria
• Entropy production estimation with optimal current
• Improved bounds on entropy production in living systems
• Human sperm steer with second harmonics of the flagellar beat
• Effective thermodynamics for a marginal observer
• Broken Detailed Balance of Filament Dynamics in Active Networks
• Learning force fields from stochastic trajectories
• Entropy Production Rate is Maximized in Non-Contractile Actomyosin
• Stationary and transient Fluctuation Theorems for effective heat flux between hydrodynamically coupled particles in optical traps
• Learning entropy production via neural networks
• Self-organization of stress patterns drives state transitions in actin cortices
• Estimating time-dependent entropy production from non-equilibrium trajectories
• Noninvasive Measurement of Dissipation in Colloidal Systems
• Non-equilibrium scaling behaviour in driven soft biological assemblies
• Learning the Non-Equilibrium Dynamics of Brownian Movies
• Hidden entropy production by fast variables
• Inertial effects on the Brownian gyrator
• Higher-order Efficiency Bound and Its Application to Nonlinear Nano-thermoelectrics
• Scaling behavior of non-equilibrium measures in internally driven elastic assemblies