UTILE-Gen: Automated Image Analysis in Nanoscience Using Synthetic Dataset Generator and Deep Learning

Abstract

This work presents the development and implementation of a deep learning-based workflow for autonomous image analysis in nanoscience. A versatile, agnostic, and configurable tool was developed to generate instance-segmented imaging datasets of nanoparticles. The synthetic generator tool employs domain randomization to expand the image/mask pairs dataset for training supervised deep learning models. The approach eliminates tedious manual annotation and allows training of high-performance models for microscopy image analysis based on convolutional neural networks. We demonstrate how the expanded training set can significantly improve the performance of the classification and instance segmentation models for a variety of nanoparticle shapes, ranging from spherical-, cubic-, to rod-shaped nanoparticles. Finally, the trained models were deployed in a cloud-based analytics platform for the autonomous particle analysis of microscopy images.

Deep learning-enhanced characterization of bubble dynamics in proton exchange membrane water electrolyzers

“…These technological advances have laid the groundwork for automated, objective extraction of data from image sequences, effectively circumventing the issues of manual analysis. [14][15][16][17] Recently, Sun et al performed a study where a multi-task deep learning (DL) network was employed for instance segmentation to elucidate fission gas bubbles within nuclear fuel. 18 Anderson et al utilized DL to autonomously identify helium bubbles in irradiated micrographs and to extract their radii and cumulative volumes.…”

“…These technological advances have laid the groundwork for automated, objective extraction of data from image sequences, effectively circumventing the issues of manual analysis. 14–17…”

Determining the orderliness of carbon materials with nanoparticle imaging and explainable machine learning

“…In recent years, computational modeling in general and particularly machine learning algorithms were actively employed in nanotechnology. 19–21 A significant contribution was made in optimizing synthesis of nanomaterials, 22–25 analyzing nano-scale properties, 26,27 developing datasets, 28,29 new algorithms, 30,31 and revealing correlations between structure and properties, 32 as well as to evolve methodology applied to micro- and nanoscale dynamics 33,34 and spectroscopy. 35…”