Characterizing soot in TEM images using a convolutional neural network

TL;DR

This paper introduces a convolutional neural network trained to analyze soot particles in TEM images, enabling more accurate and automated characterization of particle morphology despite low contrast and complex structures.

Contribution

A novel CNN model specifically designed for soot particle analysis in TEM images, improving automation and accuracy over existing classifiers.

Findings

CNN outperforms existing classifiers in soot characterization

Uncertainty in automated size estimates ranges from 25% to 85%

Consistent correlation between projected-area diameter and primary particle size

Abstract

Soot is an important material with impacts that depend on particle morphology. Transmission electron microscopy (TEM) represents one of the most direct routes to qualitatively assess particle characteristics. However, producing quantitative information requires robust image processing tools, which is complicated by the low image contrast and complex aggregated morphologies characteristic of soot. The current work presents a new convolutional neural network explicitly trained to characterize soot, using pre-classified images of particles from a natural gas engine; a laboratory gas flare; and a marine engine. The results are compared against other existing classifiers before considering the effect that the classifiers have on automated primary particle size methods. Estimates of the overall uncertainties between fully automated approaches of aggregate characterization range from 25% in d_{p,100} to 85% in D_{TEM}. A consistent correlation is observed between projected-area equivalent diameter and primary particle size across all of the techniques.