Related papers: Phonon predictions with E(3)-equivariant graph neu…

Gravitational-wave data analysis is rapidly absorbing techniques from deep learning, with a focus on convolutional networks and related methods that treat noisy time series as images. We pursue an alternative approach, in which waveforms…

Hyperbolic phonon polariton is important in precisely controlling photons at the nanoscale. It was common practice to calculate the dielectric function of the phonon polariton system with the Drude-Lorenz model. We considered the impact of…

Deep learning has emerged as a powerful framework for analyzing biomolecular dynamics trajectories, enabling efficient representations that capture essential system dynamics and facilitate mechanistic studies. We propose a neural network…

Vibrational dynamics governs the fundamental properties of molecular crystals, shaping their thermodynamics, mechanics, spectroscopy, and transport phenomena. However desirable, the first-principles calculation of solid-state vibrations,…

We report that single interatomic potential, developed using Gaussian regression of density functional theory calculation data, has high accuracy and flexibility to describe phonon transport with ab initio accuracy in two different…

We present a machine learning (ML) method for efficient computation of vibrational thermal expectation values of physical properties from first principles. Our approach is based on the non-perturbative frozen phonon formulation in which…

During oscillations of cosmology inflation around the minimum of a cuspy potential after inflation, the existence of extra high frequency gravitational waves (HFGWs) (GHz) has been proven effectively recently. Based on the electromagnetic…

The accuracy of classical physical property predictions using molecular dynamics simulations is determined by the quality of the interatomic potentials. Here we introduce a training approach for empirical interatomic potentials (EIPs) which…

First-principles calculations are used in order to investigate phonon anomalies in non-magnetic and magnetic Heusler alloys. Phonon dispersions for several systems in their cubic L2$\mathrm{_1}$ structure were obtained along the [110]…

Equivariant neural networks (ENNs) are graph neural networks embedded in $\mathbb{R}^3$ and are well suited for predicting molecular properties. The ENN library e3nn has customizable convolutions, which can be designed to depend only on…

Improving the interpretability of deep neural networks has recently gained increased attention, especially when the power of deep learning is leveraged to solve problems in physics. Interpretability helps us understand a model's ability to…

We develop a hyperelastic constitutive model for graphene --- describing in-plane deformations involving both large isotropic and deviatoric strains --- based on the invariant-theoretic approach to representation of anisotropic functions.…

Accurate determination of the electron energy probability function (EEPF) is vital for understanding electron kinetics and energy distributions in plasmas. However, interpreting Langmuir probe current-voltage (I-V) characteristics is often…

Based on the fact that both hardness and vibrational Raman spectrum depend on the intrinsic property of chemical bonds, we propose a new theoretical model for predicting hardness of a covalent crystal. The quantitative relationship between…

Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. In this chapter, we present neural network architectures that are able to learn efficient representations of molecules and…

Materials property predictions have improved from advances in machine learning algorithms, delivering materials discoveries and novel insights through data-driven models of structure-property relationships. Nearly all available models rely…

In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring…

We developed a deep generative model-based variational free energy approach to the equations of state of dense hydrogen. We employ a normalizing flow network to model the proton Boltzmann distribution and a fermionic neural network to model…

The discovery of localized plasmon polariton resonances has been pivotal in enabling tunability of the optical resonance. Recently, extensive research efforts have aimed to expand these achievements to other polaritonic states that exhibit…

Previous work on symmetric group equivariant neural networks generally only considered the case where the group acts by permuting the elements of a single vector. In this paper we derive formulae for general permutation equivariant layers,…