Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning

Chi Huan Tung; Meng Zhe Chen; Hsin Lung Chen; Guan Rong Huang; Lionel Porcar; Ming Ching Chang; Jan Michael Carrillo; Yangyang Wang; Bobby G. Sumpter; Yuya Shinohara; Changwoo Do; Wei Ren Chen

doi:10.1107/S1600576724004515

Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning

Chi Huan Tung
, Meng Zhe Chen
, Hsin Lung Chen
, Guan Rong Huang
, Lionel Porcar
, Ming Ching Chang
, Jan Michael Carrillo
, Yangyang Wang
, Bobby G. Sumpter
, Yuya Shinohara
, Changwoo Do
, Wei Ren Chen

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

4 Scopus citations

Abstract

An innovative strategy is presented that incorporates deep auto-encoder networks into a least-squares fitting framework to address the potential inversion problem in small-angle scattering. To evaluate the performance of the proposed approach, a detailed case study focusing on charged colloidal suspensions was carried out. The results clearly indicate that a deep learning solution offers a reliable and quantitative method for studying molecular interactions. The approach surpasses existing deterministic approaches with respect to both numerical accuracy and computational efficiency. Overall, this work demonstrates the potential of deep learning techniques in tackling complex problems in soft-matter structures and beyond.

Original language	English
Pages (from-to)	1047-1058
Number of pages	12
Journal	Journal of Applied Crystallography
Volume	57
Issue number	Pt 4
DOIs	https://doi.org/10.1107/S1600576724004515
State	Published - Aug 1 2024

Funding

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 (DOE). Molecular dynamics simulations used resources of the Oak Ridge Leadership Computing Facility, which is supported by the DOE Office of Science under contract DE-AC05-00OR22725. Application of machine learning to soft matter was 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. G.-R. Huang is supported by the National Science and Technology Council (NSTC) in Taiwan (grant No. NSTC 111-2112-M-110-021-MY3). M.-C. Chang is grateful for the support provided by the University at Albany – SUNY. Y. Shinohara is supported by the US Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Science and Engineering Division. Y. Wang acknowledges support from the US Department of Energy, Office of Science, Office of Basic Energy Sciences, Early Career Research Program award KC0402010 under contract DE-AC05-00OR22725.

Keywords

charge-stabilized colloids
deep learning
potential inversion
small-angle scattering
structure factors

Access to Document

10.1107/S1600576724004515

Cite this

Tung, C. H., Chen, M. Z., Chen, H. L., Huang, G. R., Porcar, L., Chang, M. C., Carrillo, J. M., Wang, Y., Sumpter, B. G., Shinohara, Y., Do, C., & Chen, W. R. (2024). Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning. Journal of Applied Crystallography, 57(Pt 4), 1047-1058. https://doi.org/10.1107/S1600576724004515

@article{aba697a992af4a19b6b2d3cd1de206be,

title = "Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning",

abstract = "An innovative strategy is presented that incorporates deep auto-encoder networks into a least-squares fitting framework to address the potential inversion problem in small-angle scattering. To evaluate the performance of the proposed approach, a detailed case study focusing on charged colloidal suspensions was carried out. The results clearly indicate that a deep learning solution offers a reliable and quantitative method for studying molecular interactions. The approach surpasses existing deterministic approaches with respect to both numerical accuracy and computational efficiency. Overall, this work demonstrates the potential of deep learning techniques in tackling complex problems in soft-matter structures and beyond.",

keywords = "charge-stabilized colloids, deep learning, potential inversion, small-angle scattering, structure factors",

author = "Tung, \{Chi Huan\} and Chen, \{Meng Zhe\} and Chen, \{Hsin Lung\} and Huang, \{Guan Rong\} and Lionel Porcar and Chang, \{Ming Ching\} and Carrillo, \{Jan Michael\} and Yangyang Wang and Sumpter, \{Bobby G.\} and Yuya Shinohara and Changwoo Do and Chen, \{Wei Ren\}",

year = "2024",

month = aug,

day = "1",

doi = "10.1107/S1600576724004515",

language = "English",

volume = "57",

pages = "1047--1058",

journal = "Journal of Applied Crystallography",

issn = "0021-8898",

publisher = "International Union of Crystallography",

number = "Pt 4",

}

TY - JOUR

T1 - Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning

AU - Tung, Chi Huan

AU - Chen, Meng Zhe

AU - Chen, Hsin Lung

AU - Huang, Guan Rong

AU - Porcar, Lionel

AU - Chang, Ming Ching

AU - Carrillo, Jan Michael

AU - Wang, Yangyang

AU - Sumpter, Bobby G.

AU - Shinohara, Yuya

AU - Do, Changwoo

AU - Chen, Wei Ren

PY - 2024/8/1

Y1 - 2024/8/1

N2 - An innovative strategy is presented that incorporates deep auto-encoder networks into a least-squares fitting framework to address the potential inversion problem in small-angle scattering. To evaluate the performance of the proposed approach, a detailed case study focusing on charged colloidal suspensions was carried out. The results clearly indicate that a deep learning solution offers a reliable and quantitative method for studying molecular interactions. The approach surpasses existing deterministic approaches with respect to both numerical accuracy and computational efficiency. Overall, this work demonstrates the potential of deep learning techniques in tackling complex problems in soft-matter structures and beyond.

AB - An innovative strategy is presented that incorporates deep auto-encoder networks into a least-squares fitting framework to address the potential inversion problem in small-angle scattering. To evaluate the performance of the proposed approach, a detailed case study focusing on charged colloidal suspensions was carried out. The results clearly indicate that a deep learning solution offers a reliable and quantitative method for studying molecular interactions. The approach surpasses existing deterministic approaches with respect to both numerical accuracy and computational efficiency. Overall, this work demonstrates the potential of deep learning techniques in tackling complex problems in soft-matter structures and beyond.

KW - charge-stabilized colloids

KW - deep learning

KW - potential inversion

KW - small-angle scattering

KW - structure factors

UR - https://www.scopus.com/pages/publications/85200648524

U2 - 10.1107/S1600576724004515

DO - 10.1107/S1600576724004515

M3 - Article

AN - SCOPUS:85200648524

SN - 0021-8898

VL - 57

SP - 1047

EP - 1058

JO - Journal of Applied Crystallography

JF - Journal of Applied Crystallography

IS - Pt 4

ER -

Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this