Separating physically distinct mechanisms in complex infrared plasmonic nanostructures via machine learning enhanced electron energy loss spectroscopy

TL;DR

This paper introduces machine learning techniques, including supervised classification and unsupervised autoencoders, to analyze complex infrared plasmonic nanostructures via electron energy loss spectroscopy, enabling separation of distinct physical mechanisms.

Contribution

It presents a novel machine learning framework for analyzing EELS data that separates and classifies physically distinct spectral responses in complex nanostructures.

Findings

Supervised classification accurately identifies different spectral regions.

Autoencoders reveal reduced representations that provide physical insights.

Method is transferable for high-throughput analysis across datasets.

Abstract

Low-loss electron energy loss spectroscopy (EELS) has emerged as a technique of choice for exploring the localization of plasmonic phenomena at the nanometer level, necessitating analysis of physical behaviors from 3D spectral data sets. For systems with high localization, linear unmixing methods provide an excellent basis for exploratory analysis, while in more complex systems large numbers of components are needed to accurately capture the true plasmonic response and the physical interpretability of the components becomes uncertain. Here, we explore machine learning based analysis of low-loss EELS data on heterogeneous self-assembled monolayer films of doped-semiconductor nanoparticles, which support infrared resonances. We propose a pathway for supervised analysis of EELS datasets that separate and classify regions of the films with physically distinct spectral responses. The classifications are shown to be robust, to accurately capture the common spatiospectral tropes of the complex nanostructures, and to be transferable between different datasets to allow high-throughput analysis of large areas of the sample. As such, it can be used as a basis for automated experiment workflows based on Bayesian optimization, as demonstrated on the ex situ data. We further demonstrate the use of non-linear autoencoders (AE) combined with clustering in the latent space of the AE yields highly reduced representations of the system response that yield insight into the relevant physics that do not depend on operator input and bias. The combination of these supervised and unsupervised tools provides complementary insight into the nanoscale plasmonic phenomena.