logo
ResearchBunny Logo
Extracting structural motifs from pair distribution function data of nanostructures using explainable machine learning

Chemistry

Extracting structural motifs from pair distribution function data of nanostructures using explainable machine learning

A. S. Anker, E. T. S. Kjær, et al.

Dive into the world of material science with our cutting-edge research! This paper unveils the Machine Learning based Motif Extractor (ML-MotEx), a revolutionary tool that uncovers important features for model quality in X-ray and neutron scattering studies. Conducted by a talented team from the University of Copenhagen and collaborating institutions, this work sheds light on disordered nanomaterials and clusters using advanced machine learning techniques.

00:00
00:00
Playback language: English
Abstract
Characterizing material structure using X-ray or neutron scattering and Pair Distribution Function (PDF) analysis often involves refining a structure model against experimental data. Identifying a suitable model is challenging. This paper introduces a Machine Learning based Motif Extractor (ML-MotEx) that trains a machine learning algorithm on thousands of fits and uses SHAP (SHapley Additive exPlanation) values to identify important model features for fit quality. The method is demonstrated on four chemical systems, including disordered nanomaterials and clusters, assigning importance values to each model feature based on explainable machine learning.
Publisher
npj Computational Materials
Published On
Oct 01, 2022
Authors
Andy S. Anker, Emil T. S. Kjær, Mikkel Juelsholt, Troels Lindahl Christiansen, Susanne Linn Skjærvø, Mads Ry Vogel Jørgensen, Innokenty Kantor, Daniel Risskov Sørensen, Simon J. L. Billinge, Raghavendra Selvan, Kirsten M. Ø. Jensen
Tags
Machine Learning
Motif Extractor
Pair Distribution Function
X-ray scattering
neutron scattering
fit quality
chemical systems

Related Publications

Explore these studies to deepen your understanding of the subject.

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing
Computer Science

Reliability of Supervised Machine Learning Using Synthetic Data in Health Care: Model to Preserve Privacy for Data Sharing

D. Rankin, M. Black, et al.

Machine learning using structural representations for discovery of high temperature superconductors
Physics

Machine learning using structural representations for discovery of high temperature superconductors

L. Novakovic, A. Salamat, et al.

Improved metabolomic data-based prediction of depressive symptoms using nonlinear machine learning with feature selection
Medicine and Health

Improved metabolomic data-based prediction of depressive symptoms using nonlinear machine learning with feature selection

Y. Takahashi, M. Ueki, et al.

Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning
Engineering and Technology

Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning

Y. Zhang, Q. Tang, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny