arXiv subjects

Aileen Luo

Publications and source records attributed to Aileen Luo.

5 recordsLinked to original sources

arXiv2026

AlphaDiffract: Automated Crystallographic Analysis of Powder X-ray Diffraction Data

Materials identification and structural understanding from powder X-ray diffraction (PXRD) data is a long-standing challenge in materials science, fundamental to discovering and characterizing novel materials. A prerequisite for full structure solution is the accurate determination of the crystal lattice, including lattice parameters and crystallographic symmetries. Traditional methods for this are iterative and typically require expert input, and while existing deep learning approaches have shown promise, a robust, single-shot method for comprehensive lattice determination from experimental data remains a key goal. Here, we introduce AlphaDiffract, a deep learning framework that achieves state-of-the-art performance in predicting the crystal system, space group, and lattice parameters directly from PXRD patterns. AlphaDiffract utilizes a 1D adaptation of the ConvNeXt architecture, a modern convolutional neural network that integrates key design principles from transformers, coupled with dedicated prediction heads for each crystallographic property. The model is trained on the largest-to-date physics-based dataset of over 31 million simulated diffraction patterns, generated by augmenting 312,267 curated structures from the ICSD and Materials Project databases. Crucially, it demonstrates strong generalization to experimental data, achieving 81.7% crystal system accuracy and 66.2% space group accuracy on the RRUFF dataset while additionally predicting all six lattice parameters. By providing a unified model for rapid and accurate lattice determination from PXRD data, AlphaDiffract represents a significant step forward in leveraging deep learning for high-throughput materials discovery.

cond-mat.mtrl-sci↗

arXiv2025

DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis

Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample's local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

cs.LG↗

arXiv2024

Deep Learning of Structural Morphology Imaged by Scanning X-ray Diffraction Microscopy

Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving nanoscale structural morphologies by diffraction contrast. One of the critical challenges in experimental nanodiffraction data analysis is posed by the convergence angle of nanoscale focusing optics which creates simultaneous dependency of the far-field scattering data on three independent components of the local strain tensor - corresponding to dilation and two potential rigid body rotations of the unit cell. All three components are in principle resolvable through a spatially mapped sample tilt series however traditional data analysis is computationally expensive and prone to artifacts. In this study, we implement NanobeamNN, a convolutional neural network specifically tailored to the analysis of scanning probe X-ray microscopy data. NanobeamNN learns lattice strain and rotation angles from simulated diffraction of a focused X-ray nanobeam by an epitaxial thin film and can directly make reasonable predictions on experimental data without the need for additional fine-tuning. We demonstrate that this approach represents a significant advancement in computational speed over conventional methods, as well as a potential improvement in accuracy over the current standard.

physics.app-ph↗

arXiv2024

X-ray Nano-imaging of a Heterogeneous Structural Phase Transition in V2O3

Controlling the Mott transition through strain engineering is crucial for advancing the development and application of memristive and neuromorphic computing devices. Yet, Mott insulators are heterogeneous due to intrinsic phase boundaries and extrinsic defects, posing significant challenges to fully understanding the impact of local microscopic distortions on the local Mott transition. Addressing these challenges demands structural characterizations at the relevant length scale. Here, using a synchrotron-based scanning X-ray nanoprobe, we studied the real-space structural heterogeneity during the structural phase transition in a V2O3 thin film. Through temperature-dependent metal-insulator phase coexistence mapping, we report a variation in the local transition temperature of up to 7 K across the film and the presence of the transition hysteresis at the nanoscale. Furthermore, a detailed quantitative analysis demonstrates that the spatial heterogeneity of the transition is closely tied to the tilting of crystallographic planes in the pure insulating phase. Our work highlights the impact of local heterogeneity on the Mott transition and lays the groundwork for future innovations in harnessing strain heterogeneity within Mott systems for the next-generation computational technologies.

cond-mat.mtrl-sci↗

arXiv2023

X-ray Nano-imaging of Defects in Thin Film Catalysts via Cluster Analysis

Functional properties of transition-metal oxides strongly depend on crystallographic defects. In transition-metal-oxide electrocatalysts such as SrIrO3 (SIO), crystallographic lattice deviations can affect ionic diffusion and adsorbate binding energies. Scanning x-ray nanodiffraction enables imaging of local structural distortions across an extended spatial region of thin samples. Line defects remain challenging to detect and localize using nanodiffraction, due to their weak diffuse scattering. Here we apply an unsupervised machine learning clustering algorithm to isolate the low-intensity diffuse scattering in as-grown and alkaline-treated thin epitaxially strained SIO films. We pinpoint the defect locations, find additional strain variation in the morphology of electrochemically cycled SIO, and interpret the defect type by analyzing the diffraction profile through clustering. Our findings demonstrate the use of a machine learning clustering algorithm for identifying and characterizing hard-to-find crystallographic defects in thin films of electrocatalysts and highlight the potential to study electrochemical reactions at defect sites in operando experiments.

cond-mat.mtrl-sci↗