Machine Learning on Neutron and X-Ray Scattering

Abstract

Neutron and X-ray scattering represent two 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 catalysis 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 scattering techniques. We highlight the integration of machine learning methods into the typical workflow of scattering experiments. We focus on scattering problems that faced challenge with traditional methods but addressable using machine learning, such as leveraging the knowledge of simple materials to model more complicated systems, learning with limited data or incomplete labels, identifying meaningful spectra and materials' representations for learning tasks, mitigating spectral noise, and many 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.

arXiv comment56 pages, 12 figures. Feedback most welcome

References in corpus (77)

• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Neural Message Passing for Quantum Chemistry
• Automatic chemical design using a data-driven continuous representation of molecules
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Machine learning and the physical sciences
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Deep learning for universal linear embeddings of nonlinear dynamics
• Real time evolution using the density matrix renormalization group
• More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
• A high-bias, low-variance introduction to Machine Learning for physicists
• Data-driven discovery of coordinates and governing equations
• Spin Dynamics of the Spin-1/2 Kagome Lattice Antiferromagnet ZnCu_3(OH)_6Cl_2
• Neutron tomography of magnetic Majorana fermions in a proximate quantum spin liquid
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• First-principles Calculations of the Electronic Structure and Spectra of Strongly Correlated Systems: Dynamical Mean-field Theory
• Resonant Spin Excitation in the High Temperature Superconductor Ba0.6K0.4Fe2As2
• Linear spin wave theory for single-Q incommensurate magnetic structures
• Neural Ordinary Differential Equations
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures
• Emergent excitations in a geometrically frustrated magnet
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Coherence-incoherence crossover in the normal state of iron-oxypnictides and importance of the Hund's rule coupling
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Machine learning modeling of superconducting critical temperature
• Physically-informed artificial neural networks for atomistic modeling of materials
• The effect of collective spin-1 excitations on electronic spectra in high-Tc superconductors
• Finding unprecedentedly low-thermal-conductivity half-Heusler semiconductors via high-throughput materials modeling
• Breakdown of Magnons in a Strongly Spin-Orbital Coupled Magnet
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Numerical evidence of fluctuating stripes in the normal state of high-Tc cuprate superconductors
• Machine-Learning Interatomic Potentials Enable First-Principles Multiscale Modeling of Lattice Thermal Conductivity in Graphene/Borophene Heterostructures
• Low Photon Count Phase Retrieval Using Deep Learning
• Unsupervised machine learning and band topology
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• Learn to Combine Modalities in Multimodal Deep Learning
• Machine Learning and Big Scientific Data
• Hidden magnetic excitation in the pseudogap phase of a model cuprate superconductor
• Machine-Learning X-ray Absorption Spectra to Quantitative Accuracy
• Classification of Local Chemical Environments from X-ray Absorption Spectra using Supervised Machine Learning
• Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations
• The magnetic excitation spectra in BaFe${}_2$As${}_2$: a two-particle approach within DFT+DMFT
• Discovery of Physics from Data: Universal Laws and Discrepancies
• Machine Learning Assisted Insight to Spin Ice Dy${}_2$Ti${}_2$O${}_7$
• Using a machine learning approach to determine the space group of a structure from the atomic pair distribution function (PDF)
• High throughput thermal conductivity of high temperature solid phases: The case of oxide and fluoride perovskites
• Direct prediction of phonon density of states with Euclidean neural networks
• Three-Dimensional Shapes of Spinning Helium Nanodroplets
• LDA+DMFT approach to resonant inelastic x-ray scattering in correlated materials
• Harnessing Interpretable and Unsupervised Machine Learning to Address Big Data from Modern X-ray Diffraction
• Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
• Topological Singularity Induced Chiral Kohn Anomaly in a Weyl Semimetal
• Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging
• Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks
• Three dimensions, two microscopes, one code: automatic differentiation for x-ray nanotomography beyond the depth of focus limit
• Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
• Deep neural networks for classifying complex features in diffraction images
• Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
• Visualizing dispersive features in 2D image via minimum gradient method
• Iterative Retraining of Quantum Spin Models Using Recurrent Neural Networks
• Recurrent Neural Networks in the Eye of Differential Equations
• Magnetic vortex lattice in HgBa2CuO4+x observed by small-angle neutron scattering
• Learning Discrepancy Models From Experimental Data
• Data-driven approach for synchrotron X-ray Laue microdiffraction scan analysis
• Accelerating small-angle scattering experiments with simulation-based machine learning

Cited by in corpus (16)

• Harnessing Interpretable and Unsupervised Machine Learning to Address Big Data from Modern X-ray Diffraction
• Exploring Quantum Materials with Resonant Inelastic X-Ray Scattering
• A perspective on machine learning and data science for strongly correlated electron problems
• Designing Materials Acceleration Platforms for Heterogeneous CO2 Photo(thermal)catalysis
• Robust Machine Learning Inference from X-ray Absorption Near Edge Spectra through Featurization
• Extraction of the interaction parameters for $\alpha -$RuCl${}_3$ from neutron data using machine learning
• Multi-code Benchmark on Simulated Ti K-edge X-ray Absorption Spectra of Ti-O Compounds
• Capturing dynamical correlations using implicit neural representations
• Autonomous Small-Angle Scattering for Accelerated Soft Material Formulation Optimization
• Predicting neutron experiments from first principles: A workflow powered by machine learning
• Human-machine collaboration: ordering mechanism of rank-2 spin liquid on breathing pyrochlore lattice
• Data-Driven Forecasting of Non-Equilibrium Solid-State Dynamics
• Retrieving genuine nonlinear Raman responses in ultrafast spectroscopy via deep learning
• Uncovering Obscured Phonon Dynamics from Powder Inelastic Neutron Scattering using Machine Learning
• Model Calibration of the Liquid Mercury Spallation Target using Evolutionary Neural Networks and Sparse Polynomial Expansions
• Hamiltonian parameter inference from resonant inelastic x-ray scattering with active learning