arXiv subjects

Ethan J. Crumlin

Publications and source records attributed to Ethan J. Crumlin.

3 recordsLinked to original sources

arXiv2026

Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders

Scientific user facilities generate X-ray scattering data faster than traditional workflows can process them. We address this challenge across two settings, offline dataset exploration and live on-the-fly analysis. We train a domain-specific attention-based Convolutional Variational Autoencoder (C-VAE) on 1.5 million X-ray scattering images to learn low-dimensional representations capturing structural variation across diverse experimental conditions. The learned latent space reveals well-organized clusters and smooth trajectories reflecting experimental progression. It further supports controlled synthetic scattering image generation across diverse structural states. When deployed without retraining, the model organizes time-resolved film formation experiments at two synchrotron facilities into interpretable latent structures. Benchmarking against DINOv3 (ViT-7B), a general-purpose vision foundation model, demonstrates that domain-specific training yields more interpretable latent organization for scattering data. Both workflows are integrated within Latent Space Explorer, a component of the MLExchange platform, supporting interactive structural exploration across archived datasets and live experiments.

cs.LG↗

arXiv2026

Prediction and Experimental Verification of Electrolyte Solvation Structure from an OMol25-Trained Interatomic Potential

Machine learning interatomic potentials (MLIPs) trained on large, chemically diverse datasets are revolutionizing computational chemistry, enabling molecular dynamics simulations of battery electrolytes with near-DFT accuracy over 10,000 times faster than DFT. While previous MLIP training datasets with suitable elemental coverage for electrolytes have been based on inorganic materials, the Open Molecules 2025 (OMol25) dataset provides large-scale molecular DFT MLIP training data with broad elemental coverage and specifically samples tens of millions of electrolyte configurations. Here, we integrate computational modeling with experimental validation to systematically assess the ability of large-scale MLIPs pre-trained on materials data or on OMol25 to accurately resolve nanoscale structural organization and ion-solvation characteristics in Na-ion battery electrolytes across diverse physicochemical conditions and compositional regimes. We find that the OMol25-trained Universal Model of Atoms (UMA-OMol) predicts experimentally measured densities and X-ray structure factors in substantially better agreement compared to state-of-the-art models trained only on inorganic materials data. Using UMA-OMol, we further analyze systematic trends in solvation structure as a function of cation identity, anion chemistry, salt concentration, and solvent topology. We observe that increasing system temperature amplifies the heterogeneity within the solvation environment, perturbing cation-solvent interactions and promoting the formation of contact ion pairs (CIPs). Moreover, subtle variations in the solvent topology of glyme-based electrolytes cause pronounced changes in ion-correlations and solvation structure. The experimental agreement and microscopic insights shown here position OMol25-trained MLIPs as a practical route to predictive, high-throughput electrolyte simulations.

physics.chem-ph↗

arXiv2020

Harnessing Structural and Dynamic Heterogeneity to Direct Ion Transport in Plastic Crystal-Polymer Composite Solid-Ion Conductors

Solid-ion conductors (SICs) comprising non-ionic plastic crystals and lithium salts often require compositing with polymers to render them processable for use in solid-state lithium-metal batteries. Here, we show that polymer-doped plastic crystal SICs form a previously unrecognized plastic crystal-polymer high entropy interphase, where ions selectively partition and exhibit a higher fraction of matrix-separated ion pairs than in the bulk. Liithium ion diffusivity in this interphase is an order of magnitude higher than in other microenvironments due to an increase in the molar volume of the plastic crystal in the vicinity of the polymer, which increases the frequency of bond rotation in the plastic crystal required for ion conduction. Surprisingly, the polymer does not directly participate in ion transport. These insights led us to prepare SICs from specific polymers, plastic crystals, and lithium halide salts that concomitantly deliver fast ion conduction at ambient and sub-ambient temperatures and sustainable passivation of the lithium anode.

physics.app-ph↗