arXiv subjects

Beatrice W. Soh

Publications and source records attributed to Beatrice W. Soh.

3 recordsLinked to original sources

arXiv2025

Identifiable learning of dissipative dynamics

Complex dissipative systems appear across science and engineering, from polymers and active matter to learning algorithms. These systems operate far from equilibrium, where energy dissipation and time irreversibility govern their behavior but are difficult to quantify from data. Here, we introduce a universal and identifiable neural framework that learns dissipative stochastic dynamics directly from trajectories while ensuring interpretability, expressiveness, and uniqueness. Our method identifies a unique energy landscape, separates reversible from irreversible motion, and allows direct computation of the entropy production, providing a principled measure of irreversibility and deviations from equilibrium. Applications to polymer stretching in elongational flow and to stochastic gradient Langevin dynamics reveal new insights, including super-linear scaling of barrier heights and sub-linear scaling of entropy production rates with the strain rate, and the suppression of irreversibility with increasing batch size. Our methodology thus establishes a general, data-driven framework for discovering and interpreting non-equilibrium dynamics.

cs.LG↗

arXiv2023

Constructing Custom Thermodynamics Using Deep Learning

One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetries and conservation laws. Such automated hypothesis creation and verification can assist scientists in studying complex phenomena, where traditional physical intuition may fail. Here we develop a platform based on a generalized Onsager principle to learn macroscopic dynamical descriptions of arbitrary stochastic dissipative systems directly from observations of their microscopic trajectories. Our method simultaneously constructs reduced thermodynamic coordinates and interprets the dynamics on these coordinates. We demonstrate its effectiveness by studying theoretically and validating experimentally the stretching of long polymer chains in an externally applied field. Specifically, we learn three interpretable thermodynamic coordinates and build a dynamical landscape of polymer stretching, including the identification of stable and transition states and the control of the stretching rate. Our general methodology can be used to address a wide range of scientific and technological applications.

cond-mat.soft↗

arXiv2023

Automated Electrokinetic Stretcher for Manipulating Nanomaterials

In this work, we present an automated platform for trapping and stretching individual micro- and nanoscale objects in solution using electrokinetic forces. The platform can trap objects at the stagnation point of a planar elongational electrokinetic field for long time scales, as demonstrated by the trapping of ~100 nanometer polystyrene beads and DNA molecules for minutes, with a standard deviation in displacement from the trap center < 1 micrometer. This capability enables the stretching of deformable nanoscale objects in a high-throughput fashion, as illustrated by the stretching of more than 400 DNA molecules within ~4 hours. The flexibility of the electrokinetic stretcher opens up numerous possibilities for contact-free manipulation, with size-based sorting of DNA molecules performed as an example. The platform described provides an automated, high-throughput method to track and manipulate objects for real-time studies of micro- and nanoscale systems.

physics.ins-det↗