Inferring colloidal interaction from scattering by machine learning
A machine learning solution for the potential inversion problem in elastic scattering is outlined. The inversion scheme consists of two major components, a generative network featuring a variational autoencoder which extracts the targeted static two-point correlation functions from experimentally me...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Carbon Trends |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266705692300007X |
| _version_ | 1811155489995620352 |
|---|---|
| author | Chi-Huan Tung Shou-Yi Chang Ming-Ching Chang Jan-Michael Carrillo Bobby G Sumpter Changwoo Do Wei-Ren Chen |
| author_facet | Chi-Huan Tung Shou-Yi Chang Ming-Ching Chang Jan-Michael Carrillo Bobby G Sumpter Changwoo Do Wei-Ren Chen |
| author_sort | Chi-Huan Tung |
| collection | DOAJ |
| description | A machine learning solution for the potential inversion problem in elastic scattering is outlined. The inversion scheme consists of two major components, a generative network featuring a variational autoencoder which extracts the targeted static two-point correlation functions from experimentally measured scattering cross sections, and a Gaussian process framework which probabilistically infers the relevant structural parameters from the inverted correlation functions. Via a case study of charged colloidal suspensions, the feasibility of this approach for quantitative study of molecular interaction is critically benchmarked and its merit over existing deterministic approaches, in terms of numerical accuracy and computationally efficiency, is demonstrated. |
| first_indexed | 2024-04-10T04:34:26Z |
| format | Article |
| id | doaj.art-67725bae8e9a426fa58e64c1e1b6cd97 |
| institution | Directory Open Access Journal |
| issn | 2667-0569 |
| language | English |
| last_indexed | 2024-04-10T04:34:26Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Carbon Trends |
| spelling | doaj.art-67725bae8e9a426fa58e64c1e1b6cd972023-03-10T04:36:50ZengElsevierCarbon Trends2667-05692023-03-0110100252Inferring colloidal interaction from scattering by machine learningChi-Huan Tung0Shou-Yi Chang1Ming-Ching Chang2Jan-Michael Carrillo3Bobby G Sumpter4Changwoo Do5Wei-Ren Chen6Department of Materials Science and Engineering, National Tsing Hua University; Hsinchu 300044, TaiwanDepartment of Materials Science and Engineering, National Tsing Hua University; Hsinchu 300044, TaiwanDepartment of Computer Science, University at Albany - State University of New York, Albany, New York 12222, United StatesCenter for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United StatesCorresponding authors.; Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United StatesNeutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United StatesCorresponding authors.; Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United StatesA machine learning solution for the potential inversion problem in elastic scattering is outlined. The inversion scheme consists of two major components, a generative network featuring a variational autoencoder which extracts the targeted static two-point correlation functions from experimentally measured scattering cross sections, and a Gaussian process framework which probabilistically infers the relevant structural parameters from the inverted correlation functions. Via a case study of charged colloidal suspensions, the feasibility of this approach for quantitative study of molecular interaction is critically benchmarked and its merit over existing deterministic approaches, in terms of numerical accuracy and computationally efficiency, is demonstrated.http://www.sciencedirect.com/science/article/pii/S266705692300007XNeutron scatteringMachine learningSoft matterLarge-scale simulations |
| spellingShingle | Chi-Huan Tung Shou-Yi Chang Ming-Ching Chang Jan-Michael Carrillo Bobby G Sumpter Changwoo Do Wei-Ren Chen Inferring colloidal interaction from scattering by machine learning Carbon Trends Neutron scattering Machine learning Soft matter Large-scale simulations |
| title | Inferring colloidal interaction from scattering by machine learning |
| title_full | Inferring colloidal interaction from scattering by machine learning |
| title_fullStr | Inferring colloidal interaction from scattering by machine learning |
| title_full_unstemmed | Inferring colloidal interaction from scattering by machine learning |
| title_short | Inferring colloidal interaction from scattering by machine learning |
| title_sort | inferring colloidal interaction from scattering by machine learning |
| topic | Neutron scattering Machine learning Soft matter Large-scale simulations |
| url | http://www.sciencedirect.com/science/article/pii/S266705692300007X |
| work_keys_str_mv | AT chihuantung inferringcolloidalinteractionfromscatteringbymachinelearning AT shouyichang inferringcolloidalinteractionfromscatteringbymachinelearning AT mingchingchang inferringcolloidalinteractionfromscatteringbymachinelearning AT janmichaelcarrillo inferringcolloidalinteractionfromscatteringbymachinelearning AT bobbygsumpter inferringcolloidalinteractionfromscatteringbymachinelearning AT changwoodo inferringcolloidalinteractionfromscatteringbymachinelearning AT weirenchen inferringcolloidalinteractionfromscatteringbymachinelearning |