Enhanced force-field calibration via machine learning

TL;DR

This paper presents a machine learning-based toolbox called DeepCalib for calibrating microscopic force fields from Brownian particle trajectories, especially effective for complex, non-conservative, and time-varying forces where standard methods fail.

Contribution

The authors develop a recurrent neural network approach and provide a Python package to improve force field calibration in challenging experimental scenarios.

Findings

Outperforms standard methods with limited data for harmonic potentials

Enables calibration of non-conservative and time-varying force fields

Provides an accessible Python software package for researchers

Abstract

The influence of microscopic force fields on the motion of Brownian particles plays a fundamental role in a broad range of fields, including soft matter, biophysics, and active matter. Often, the experimental calibration of these force fields relies on the analysis of the trajectories of these Brownian particles. However, such an analysis is not always straightforward, especially if the underlying force fields are non-conservative or time-varying, driving the system out of thermodynamic equilibrium. Here, we introduce a toolbox to calibrate microscopic force fields by analyzing the trajectories of a Brownian particle using machine learning, namely recurrent neural networks. We demonstrate that this machine-learning approach outperforms standard methods when characterizing the force fields generated by harmonic potentials if the available data are limited. More importantly, it provides a tool to calibrate force fields in situations for which there are no standard methods, such as non-conservative and time-varying force fields. In order to make this method readily available for other users, we provide a Python software package named DeepCalib, which can be easily personalized and optimized for specific applications.