Machine learning inversion from scattering for mechanically driven polymers

Lijie Ding; Chi Huan Tung; Bobby G. Sumpter; Wei Ren Chen; Changwoo Do

doi:10.1107/S160057672500634X

Machine learning inversion from scattering for mechanically driven polymers

Research output: Contribution to journal › Article › peer-review

Abstract

A machine learning inversion method is developed for analyzing scattering functions of mechanically driven polymers and extracting the corresponding feature parameters, which include energy parameters and conformation variables. The polymer is modeled as a chain of fixed-length bonds constrained by bending energy, and it is subject to external forces such as stretching and shear. We generate a data set consisting of random combinations of energy parameters, including bending modulus, stretching and shear force, along with Monte Carlo-calculated scattering functions and conformation variables such as end-to-end distance, radius of gyration and off-diagonal component of the gyration tensor. The effects of the energy parameters on the polymer are captured by the scattering function, and principal component analysis ensures the feasibility of the machine learning inversion. Finally, we train a Gaussian process regressor using part of the data set as a training set and validate the trained regressor for inversion using the rest of the data. The regressor successfully extracts the feature parameters.

Original language	English
Pages (from-to)	1526-1532
Number of pages	7
Journal	Journal of Applied Crystallography
Volume	58
DOIs	https://doi.org/10.1107/S160057672500634X
State	Published - Oct 1 2025

Funding

We thank Jan-Michael Carrillo for fruitful discussions. This research was performed at the Spallation Neutron Source and the Center for Nanophase Materials Sciences, which are DOE Office of Science User Facilities operated by Oak Ridge National Laboratory. This research was sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy. The ML aspects were supported by the US Department of Energy Office of Science, Office of Basic Energy Sciences, Data, Artificial Intelligence and Machine Learning at DOE Scientific User Facilities Program under award No. 34532. Monte Carlo simulations and computations used resources of the Oak Ridge Leadership Computing Facility, which is supported by the DOE Office of Science under contract DE-AC05-00OR22725.

Keywords

Gaussian process regressors
Monte Carlo methods
machine learning
polymers
small-angle scattering

Access to Document

10.1107/S160057672500634X

Cite this

@article{f49405382f8e45d49cdc5230a17676f2,

title = "Machine learning inversion from scattering for mechanically driven polymers",

abstract = "A machine learning inversion method is developed for analyzing scattering functions of mechanically driven polymers and extracting the corresponding feature parameters, which include energy parameters and conformation variables. The polymer is modeled as a chain of fixed-length bonds constrained by bending energy, and it is subject to external forces such as stretching and shear. We generate a data set consisting of random combinations of energy parameters, including bending modulus, stretching and shear force, along with Monte Carlo-calculated scattering functions and conformation variables such as end-to-end distance, radius of gyration and off-diagonal component of the gyration tensor. The effects of the energy parameters on the polymer are captured by the scattering function, and principal component analysis ensures the feasibility of the machine learning inversion. Finally, we train a Gaussian process regressor using part of the data set as a training set and validate the trained regressor for inversion using the rest of the data. The regressor successfully extracts the feature parameters.",

keywords = "Gaussian process regressors, Monte Carlo methods, machine learning, polymers, small-angle scattering",

author = "Lijie Ding and Tung, \{Chi Huan\} and Sumpter, \{Bobby G.\} and Chen, \{Wei Ren\} and Changwoo Do",

year = "2025",

month = oct,

day = "1",

doi = "10.1107/S160057672500634X",

language = "English",

volume = "58",

pages = "1526--1532",

journal = "Journal of Applied Crystallography",

issn = "0021-8898",

publisher = "International Union of Crystallography",

}

TY - JOUR

T1 - Machine learning inversion from scattering for mechanically driven polymers

AU - Ding, Lijie

AU - Tung, Chi Huan

AU - Sumpter, Bobby G.

AU - Chen, Wei Ren

AU - Do, Changwoo

PY - 2025/10/1

Y1 - 2025/10/1

N2 - A machine learning inversion method is developed for analyzing scattering functions of mechanically driven polymers and extracting the corresponding feature parameters, which include energy parameters and conformation variables. The polymer is modeled as a chain of fixed-length bonds constrained by bending energy, and it is subject to external forces such as stretching and shear. We generate a data set consisting of random combinations of energy parameters, including bending modulus, stretching and shear force, along with Monte Carlo-calculated scattering functions and conformation variables such as end-to-end distance, radius of gyration and off-diagonal component of the gyration tensor. The effects of the energy parameters on the polymer are captured by the scattering function, and principal component analysis ensures the feasibility of the machine learning inversion. Finally, we train a Gaussian process regressor using part of the data set as a training set and validate the trained regressor for inversion using the rest of the data. The regressor successfully extracts the feature parameters.

AB - A machine learning inversion method is developed for analyzing scattering functions of mechanically driven polymers and extracting the corresponding feature parameters, which include energy parameters and conformation variables. The polymer is modeled as a chain of fixed-length bonds constrained by bending energy, and it is subject to external forces such as stretching and shear. We generate a data set consisting of random combinations of energy parameters, including bending modulus, stretching and shear force, along with Monte Carlo-calculated scattering functions and conformation variables such as end-to-end distance, radius of gyration and off-diagonal component of the gyration tensor. The effects of the energy parameters on the polymer are captured by the scattering function, and principal component analysis ensures the feasibility of the machine learning inversion. Finally, we train a Gaussian process regressor using part of the data set as a training set and validate the trained regressor for inversion using the rest of the data. The regressor successfully extracts the feature parameters.

KW - Gaussian process regressors

KW - Monte Carlo methods

KW - machine learning

KW - polymers

KW - small-angle scattering

UR - https://www.scopus.com/pages/publications/105020255979

U2 - 10.1107/S160057672500634X

DO - 10.1107/S160057672500634X

M3 - Article

AN - SCOPUS:105020255979

SN - 0021-8898

VL - 58

SP - 1526

EP - 1532

JO - Journal of Applied Crystallography

JF - Journal of Applied Crystallography

ER -

Machine learning inversion from scattering for mechanically driven polymers

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this