Learning local equivariant representations for large-scale atomistic dynamics.

A simultaneously accurate and computationally efficient parametrization of the potential energy surface of molecules and materials is a long-standing goal in the natural sciences. While atom-centered message passing neural networks (MPNNs) have shown remarkable accuracy, their information propagation has limited the accessible length-scales. Local methods, conversely, scale to large simulations but have suffered from inferior accuracy. This work introduces Allegro, a strictly local equivariant deep neural network interatomic potential architecture that simultaneously exhibits excellent accuracy and scalability. Allegro represents a many-body potential using iterated tensor products of learned equivariant representations without atom-centered message passing. Allegro obtains improvements over state-of-the-art methods on QM9 and revMD17. A single tensor product layer outperforms existing deep MPNNs and transformers on QM9. Furthermore, Allegro displays remarkable generalization to out-of-distribution data. Molecular simulations using Allegro recover structural and kinetic properties of an amorphous electrolyte in excellent agreement with ab-initio simulations. Finally, we demonstrate parallelization with a simulation of 100 million atoms.

Orbital Mixer: Using Atomic Orbital Features for Basis-Dependent Prediction of Molecular Wavefunctions.

Leveraging ab initio data at scale has enabled the development of machine learning models capable of extremely accurate and fast molecular property prediction. A central paradigm of many previous studies focuses on generating predictions for only a fixed set of properties. Recent lines of research instead aim to explicitly learn the electronic structure via molecular wavefunctions, from which other quantum chemical properties can be directly derived. While previous methods generate predictions as a function of only the atomic configuration, in this work we present an alternate approach that directly purposes basis-dependent information to predict molecular electronic structure. Our model, Orbital Mixer, is composed entirely of multi-layer perceptrons (MLPs) using MLP-Mixer layers within a simple, intuitive, and scalable architecture that achieves competitive Hamiltonian and molecular orbital energy and coefficient prediction accuracies compared to the state-of-the-art.

E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials.

This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. While most contemporary symmetry-aware models use invariant convolutions and only act on scalars, NequIP employs E(3)-equivariant convolutions for interactions of geometric tensors, resulting in a more information-rich and faithful representation of atomic environments. The method achieves state-of-the-art accuracy on a challenging and diverse set of molecules and materials while exhibiting remarkable data efficiency. NequIP outperforms existing models with up to three orders of magnitude fewer training data, challenging the widely held belief that deep neural networks require massive training sets. The high data efficiency of the method allows for the construction of accurate potentials using high-order quantum chemical level of theory as reference and enables high-fidelity molecular dynamics simulations over long time scales.

Spectral Denoising for Accelerated Analysis of Correlated Ionic Transport.

Computation of correlated ionic transport properties from molecular dynamics in the Green-Kubo formalism is expensive, as one cannot rely on the affordable mean square displacement approach. We use spectral decomposition of the short-time ionic displacement covariance to learn a set of diffusion eigenmodes that encode the correlation structure and form a basis for analyzing the ionic trajectories. This allows systematic reduction of the uncertainty and accelerate computations of ionic conductivity in systems with a steady-state correlation structure. We provide mathematical and numerical proofs of the method's robustness and demonstrate it on realistic electrolyte materials.

A community-powered search of machine learning strategy space to find NMR property prediction models.

The rise of machine learning (ML) has created an explosion in the potential strategies for using data to make scientific predictions. For physical scientists wishing to apply ML strategies to a particular domain, it can be difficult to assess in advance what strategy to adopt within a vast space of possibilities. Here we outline the results of an online community-powered effort to swarm search the space of ML strategies and develop algorithms for predicting atomic-pairwise nuclear magnetic resonance (NMR) properties in molecules. Using an open-source dataset, we worked with Kaggle to design and host a 3-month competition which received 47,800 ML model predictions from 2,700 teams in 84 countries. Within 3 weeks, the Kaggle community produced models with comparable accuracy to our best previously published 'in-house' efforts. A meta-ensemble model constructed as a linear combination of the top predictions has a prediction accuracy which exceeds that of any individual model, 7-19x better than our previous state-of-the-art. The results highlight the potential of transformer architectures for predicting quantum mechanical (QM) molecular properties.

Plasma Synthesis of Spherical Crystalline and Amorphous Electrolyte Nanopowders for Solid-State Batteries.

Here, we demonstrate the theory-guided plasma synthesis of high purity nanocrystalline Li3.5Si0.5P0.5O4 and fully amorphous Li2.7Si0.7P0.3O3.17N0.22. The synthesis involves the injection of single or mixed phase precursors directly into a plasma torch. As the material exits the plasma torch, it is quenched into spherical nanocrystalline or amorphous nanopowders. This process has virtually zero Li loss and allows for the inclusion of N, which is not accessible with traditional synthesis methods. We further demonstrate the ability to sinter the crystalline nanopowder into a dense electrolyte membrane at 800 °C, well below the traditional 1000 °C required for a conventional Li3.5Si0.5P0.5O4 powder.

Origin of Spinel Nanocheckerboards via First Principles.

Self-organizing nanocheckerboards have been experimentally fabricated in Mn-based spinels but have not yet been explained with first principles. Using density-functional theory, we explain the phase diagram of the ZnMn_{x}Ga_{2-x}O_{4} system and the origin of nanocheckerboards. We predict total phase separation at zero temperature and then show the combination of kinetics, thermodynamics, and Jahn-Teller physics that generates the system's observed behavior. We find that the {011} surfaces are strongly preferred energetically, which mandates checkerboard ordering by purely geometrical considerations.

Light-induced electronic non-equilibrium in plasmonic particles.

We consider the transient non-equilibrium electronic distribution that is created in a metal nanoparticle upon plasmon excitation. Following light absorption, the created plasmons decohere within a few femtoseconds, producing uncorrelated electron-hole pairs. The corresponding non-thermal electronic distribution evolves in response to the photo-exciting pulse and to subsequent relaxation processes. First, on the femtosecond timescale, the electronic subsystem relaxes to a Fermi-Dirac distribution characterized by an electronic temperature. Next, within picoseconds, thermalization with the underlying lattice phonons leads to a hot particle in internal equilibrium that subsequently equilibrates with the environment. Here we focus on the early stage of this multistep relaxation process, and on the properties of the ensuing non-equilibrium electronic distribution. We consider the form of this distribution as derived from the balance between the optical absorption and the subsequent relaxation processes, and discuss its implication for (a) heating of illuminated plasmonic particles, (b) the possibility to optically induce current in junctions, and (c) the prospect for experimental observation of such light-driven transport phenomena.