Deep learning analysis of polaritonic waves images

Abstract

Deep learning (DL) is an emerging analysis tool across sciences and engineering. Encouraged by the successes of DL in revealing quantitative trends in massive imaging data, we applied this approach to nano-scale deeply sub-diffractional images of propagating polaritonic waves in complex materials. We developed a practical protocol for the rapid regression of images that quantifies the wavelength and the quality factor of polaritonic waves utilizing the convolutional neural network (CNN). Using simulated near-field images as training data, the CNN can be made to simultaneously extract polaritonic characteristics and materials parameters in a timescale that is at least three orders of magnitude faster than common fitting/processing procedures. The CNN-based analysis was validated by examining the experimental near-field images of charge-transfer plasmon polaritons at Graphene/α-RuCl3 interfaces. Our work provides a general framework for extracting quantitative information from images generated with a variety of scanning probe methods.

References in corpus (31)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Gate-tuning of graphene plasmons revealed by infrared nano-imaging
• Optical nano-imaging of gate-tuneable graphene plasmons
• Mott transition in VO2 revealed by infrared spectroscopy and nano-imaging
• Polaritons in layered 2D materials
• Proximate Kitaev Quantum Spin Liquid Behaviour in α-RuCl${}_3$
• Imaging Quasiparticle Interference in Bi2Sr2CaCu2O8+d
• Infrared nanoscopy of Dirac plasmons at the graphene-SiO2 interface
• Discovering physical concepts with neural networks
• Imaging exciton-polariton transport in MoSe2 waveguides
• Electronic and plasmonic phenomena at graphene grain boundaries
• Principal Graphs and Manifolds
• Edge and surface plasmons in graphene nanoribbons
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Machine Learning for Quantum Matter
• Phase Resolved Surface Plasmon Interferometry of Graphene
• Near-field photocurrent nanoscopy on bare and encapsulated graphene
• Fizeau Drag in Graphene Plasmonics
• Efficient Fizeau Drag from Dirac electrons in monolayer graphene
• Nano-optical imaging of WSe2 waveguide modes revealing light-exciton interactions
• What Do We Understand About Convolutional Networks?
• Graphene/$\alpha$-RuCl${}_3$: An Emergent 2D Plasmonic Interface
• Machine Learning for Condensed Matter Physics
• Computer-inspired Quantum Experiments
• Multi-messenger nano-probes of hidden magnetism in a strained manganite
• Power-Law Decay of Standing Waves on the Surface of Topological Insulators
• $\text{Ab Initio}$ Mismatched Interface Theory of Graphene on $\alpha$-RuCl${}_3$: Doping and Magnetism
• Nano-photocurrent mapping of local electronic structure in twisted bilayer graphene
• Long wavelength local density of states oscillations near graphene step edges
• Hybrid Machine Learning for Scanning Near-field Optical Spectroscopy

Cited by in corpus (1)

• Deep Learning Hamiltonians from Disordered Image Data in Quantum Materials