Laser-Induced Fluorescence coupled with Machine Learning as an effective approach for real-time identification of bacteria in bioaerosols

Fontal, Alejandro; Borràs, Sílvia; Cañas, Lídia; Pozdniakova, Sofya; Rodó, Xavier

doi:10.5194/amt-18-7297-2025

Articles | Volume 18, issue 23

https://doi.org/10.5194/amt-18-7297-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-18-7297-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 23

Research article

|

02 Dec 2025

Research article |

| 02 Dec 2025

Laser-Induced Fluorescence coupled with Machine Learning as an effective approach for real-time identification of bacteria in bioaerosols

Alejandro Fontal, Sílvia Borràs, Lídia Cañas, Sofya Pozdniakova, and Xavier Rodó

Supplement

https://doi.org/10.5194/amt-18-7297-2025-supplement

Data sets

Rapid-E output for aerosolized fluorophores and Bacteria Alejandro Fontal https://doi.org/10.5281/zenodo.15485702

Model code and software

GitHub Repository containing model code definitions and figures generation Alejandro Fontal et al. https://github.com/AlFontal/lif-bacteria-aerosols-ms

lif-bacteria-aerosols-ms: AMT paper code companion Alejandro Fontal https://doi.org/10.5281/zenodo.17753297

Short summary

Monitoring airborne microbes is crucial for health and ecosystems, but often slow and expensive. We adapted an existing instrument, Rapid-E, using Laser-Induced Fluorescence and machine learning, for rapid, field-deployable bacterial identification. Our system successfully detected bacteria and showed promise in distinguishing various species. This faster approach improves environmental monitoring and helps safeguard public health by quickly spotting potential microbial threats in the air.