Machine Learning Models Capture Plasmon Dynamics in Ag Nanoparticles

Abstract

Highly energetic electron-hole pairs (hot carriers) formed from plasmon decay in metallic nanostructures promise sustainable pathways for energy-harvesting devices. However, efficient collection before thermalization remains an obstacle for realization of their full energy generating potential. Addressing this challenge requires detailed understanding of physical processes from plasmon excitation in metal to their collection in a molecule or a semiconductor, where atomistic theoretical investigation may be particularly beneficial. Unfortunately, first-principles theoretical modeling of these processes is extremely costly, limiting the analysis to systems with a few 100s of atoms. Recent advances in machine learned interatomic potentials suggest that dynamics can be accelerated with surrogate models which replace the full solution of the Schroedinger Equation. Here, we modify an existing neural network, Hierarchically Interacting Particle Neural Network (HIP-NN), to predict plasmon dynamics in Ag nanoparticles. We demonstrate the model's capability to accurately predict plasmon dynamics in large nanoparticles of up to 561 atoms not present in the training dataset. More importantly, with machine learning models we gain a speed-up of about 200 times as compared with the rt-TDDFT calculations when predicting important physical quantities such as dynamic dipole moments in Ag55 and about 4000 times for extended nanoparticles that are 10 times larger. This underscores the promise of future machine learning accelerated electron/nuclear dynamics simulations for understanding fundamental properties of plasmon-driven hot carrier devices.

References in corpus (15)

• SchNet - a deep learning architecture for molecules and materials
• A real-space grid implementation of the Projector Augmented Wave method
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Hierarchical modeling of molecular energies using a deep neural network
• Ultrafast Studies of Hot-Hole Dynamics in Au/p-GaN Heterostructures
• Localized surface plasmon resonance in silver nanoparticles: Atomistic first-principles time-dependent density-functional theory calculations
• Hot Carrier Dynamics in Photoexcited Gold Nanostructures: Role of Interband Excitations and Evidence for Ballistic Transport
• Hot-Carrier Generation in Plasmonic Nanoparticles: The Importance of Atomic Structure
• Kohn-Sham decomposition in real-time time-dependent density-functional theory: An efficient tool for analyzing plasmonic excitations
• Experimental and ab initio ultrafast carrier dynamics in plasmonic nanoparticles
• Automated discovery of a robust interatomic potential for aluminum
• Landau damping of surface plasmons in metal nanostructures
• Nanoplasmonics simulations at the basis set limit through completeness-optimized, local numerical basis sets