Three-Dimensional Analysis of Particle Distribution on Filter Layers inside N95 Respirators by Deep Learning

• DOI: 10.1021/acs.nanolett.0c04230
• Publication Date: 2020-12-08T07:50:42Z
• Authors: Hye Ryoung Lee; Lei Liao; Wang Xiao; Arturas Vailionis; Antonio J. Ricco; Robin White; Yoshio Nishi; Wah Chiu; Steven Chu; Yi Cui
• Keywords: Respirator; Filtration (mathematics); Particle (ecology)

The global COVID-19 pandemic has changed many aspects of daily lives. Wearing personal protective equipment, especially respirators (face masks), become common for both the public and medical professionals, proving to be effective in preventing spread virus. Nevertheless, a detailed understanding respirator filtration-layer internal structures their physical configurations is lacking. Here, we report three-dimensional (3D) analysis N95 filtration layers via X-ray tomography. Using deep learning methods, uncover how distribution diameters fibers within these directly affect contaminant particle filtration. average porosity filter found 89.1%. Contaminants are more efficiently captured by denser fiber regions, with <1.8 μm diameter being particularly effective, presumably because stronger electric field gradient on smaller fibers. This study provides critical information further development N95-type that combine high efficiency good breathability.