Machine learning on neutron and x-ray scattering and spectroscopies

2021/02/05 by Zhantao Chen, Nina Andrejevic, Nathan Drucker +12
Materials Science · Physics and Astronomy · #Artificial intelligence #Characterization (materials science) #Computer science #Machine Learning in Materials Science #Machine learning #Materials science #Nanotechnology #Neutron #Neutron scattering #Nuclear Physics and Applications #Nuclear physics #Optics #Physics #Scattering #Variety (cybernetics) #Workflow #X-ray Diffraction in Crystallography #cond-mat.mtrl-sci

paper · pdf · doi:10.1063/5.0049111

published as Chem. Phys. Rev. 2, 031301 (2021) · 56 pages, 12 figures. Feedback most welcome

arxiv created 2021/02/05 · openalex created_date 2021/02/15 · openalex publication_date 2021/07/08 · arxiv updated 2021/07/13 · openalex updated_date 2026/08/06

Abstract

Neutron and x-ray scattering represent two classes of state-of-the-art materials characterization techniques that measure materials structural and dynamical properties with high precision. These techniques play critical roles in understanding a wide variety of materials systems from catalysts to polymers, nanomaterials to macromolecules, and energy materials to quantum materials. In recent years, neutron and x-ray scattering have received a significant boost due to the development and increased application of machine learning to materials problems. This article reviews the recent progress in applying machine learning techniques to augment various neutron and x-ray techniques, including neutron scattering, x-ray absorption, x-ray scattering, and photoemission. We highlight the integration of machine learning methods into the typical workflow of scattering experiments, focusing on problems that challenge traditional analysis approaches but are addressable through machine learning, including leveraging the knowledge of simple materials to model more complicated systems, learning with limited data or incomplete labels, identifying meaningful spectra and materials representations, mitigating spectral noise, and others. We present an outlook on a few emerging roles machine learning may play in broad types of scattering and spectroscopic problems in the foreseeable future.

Citations

• Dynamical Theory of Crystal Lattices
• The effect of collective spin-1 excitations on electronic spectra in high-Tcsuperconductors
• Spin Dynamics of the Spin-1/2Kagome Lattice AntiferromagnetZnCu3(OH)6Cl2
• X-ray photon correlation spectroscopy
• On representing chemical environments
• Emergent excitations in a geometrically frustrated magnet
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Crystal structure representations for machine learning models of formation energies
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum-chemical insights from deep tensor neural networks
• Automatic chemical design using a data-driven continuous representation of molecules
• Visualizing dispersive features in 2D image via minimum gradient method
• Neural Message Passing for Quantum Chemistry
• Multimodal Machine Learning: A Survey and Taxonomy
• SchNet – A deep learning architecture for molecules and materials
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• A high-bias, low-variance introduction to Machine Learning for physicists
• Learn to Combine Modalities in Multimodal Deep Learning
• Neural Ordinary Differential Equations
• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network
• Machine learning and the physical sciences
• Machine-learning-assisted insight into spin ice Dy2Ti2O7
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
• Data-driven approach for synchrotron X-ray Laue microdiffraction scan analysis
• Learning Discrepancy Models From Experimental Data
• Iterative Retraining of Quantum Spin Models Using Recurrent Neural Networks
• Physics-informed multi-LSTM networks for metamodeling of nonlinear structures
• Finding symmetry breaking order parameters with Euclidean neural networks
• More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
• Deep learning for tomographic image reconstruction
• LDA+DMFTapproach to resonant inelastic x-ray scattering in correlated materials