EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Machine Learning-Assisted Liquid Crystal Droplet Array Platform for the Sensitive and Selective Detection of Per- and Polyfluoroalkyl Substances (PFAS) in Water

Fengrui Wang iD, Shiyi Qin iD, Zhao Yang iD, Leena M Edwards-Medina, Benjamin L Chiu iD, Claribel Acevedo-Vélez iD, Christina K Remucal iD, Reid C Van Lehn iD, Victor M Zavala iD, David M Lynn iD

ACS Sensors · 24.10.2025 · 10 (10) · 7343-7353

DOI: 10.1021/acssensors.5c00907 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Sensors, online erschienen am 25.09.2025. Verfasst von Fengrui Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, University of Wisconsin-Madison, 1101 University Avenue, Madison, Wisconsin 53706, United States. Hauptthemen laut MEDLINE: Fluorocarbons, Machine Learning, Water Pollutants, Chemical, Liquid Crystals. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wisconsin Alumni Research Foundation, Division of Chemical, Bioengineering, Environmental, and Transport Systems, Division of Information and Intelligent Systems.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We report a machine learning (ML)-assisted liquid crystal (LC) droplet array platform for the detection of per- and polyfluoroalkyl substances (PFAS) in water. Our approach uses an autoencoder network to process thousands of images obtained from arrays of microscale droplets of thermotropic LCs. The latent space obtained using the autoencoder contains significant information that enables sensitive and selective detection of two amphiphilic PFAS [perfluorooctanoic acid (PFOA) and perfluorooctanesulfonic acid (PFOS)] at concentrations as low as parts-per-trillion (ppt) in ultrapure water, municipal tap water, and simulated river water containing dissolved organic matter. Despite the absence of visually discernible changes in the optical outputs of LC arrays at low PFAS concentrations, this approach accurately predicts their presence, even in water containing interfering molecules. We also demonstrate the use of transfer learning to differentiate between PFOA, PFOS, and PFOA/PFOS mixtures, showcasing the potential for practical environmental monitoring. This platform permits identification of PFOA and PFOS below the maximum contaminant levels (4 ppt) established by the U.S. Environmental Protection Agency. Our approach is compatible with automated printing, treatment, and high-throughput optical and ML analysis and could provide a basis for the development of low-cost sensors to monitor PFAS and other amphiphilic contaminants in real-world water samples.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FluorocarbonsMachine LearningWater Pollutants, ChemicalLiquid CrystalsAlkanesulfonic AcidsCaprylatesWaterLimit of Detection

Stichwörter der Autor:innen

PFASautoencoderliquid crystalsmachine learningneural networks

Substanzen

FluorocarbonsWater Pollutants, Chemicalperfluorooctanoic acidAlkanesulfonic AcidsCaprylatesperfluorooctane sulfonic acidWater

Autor:innen und Institutionen

  • Department of Chemistry, University of Wisconsin-Madison, 1101 University Avenue, Madison, Wisconsin 53706, United States.
  • Department of Chemical and Biological Engineering, University of Wisconsin-Madison, 1415 Engineering Dr., Madison, Wisconsin 53706, United States.
  • Department of Civil and Environmental Engineering, University of Wisconsin-Madison, 660 North Park Street, Madison, Wisconsin 53706, United States.
  • Department of Chemical Engineering, University of Puerto Rico-Mayagüez, Call Box 9000, Mayagüez, Puerto Rico 00681-9000, United States.

ORCID-Profile: Fengrui Wang, Shiyi Qin, Zhao Yang, Benjamin L Chiu, Claribel Acevedo-Vélez, Christina K Remucal, Reid C Van Lehn, Victor M Zavala, David M Lynn

Förderung

  • Wisconsin Alumni Research Foundation
  • Division of Chemical, Bioengineering, Environmental, and Transport Systems
  • Division of Information and Intelligent Systems
  • Division of Materials Research

Zitieren

APA

Wang, F., Qin, S., Yang, Z., Edwards-Medina, L. M., Chiu, B. L., Acevedo-Vélez, C., Remucal, C. K., Van Lehn, R. C., Zavala, V. M., & Lynn, D. M. (2025). A Machine Learning-Assisted Liquid Crystal Droplet Array Platform for the Sensitive and Selective Detection of Per- and Polyfluoroalkyl Substances (PFAS) in Water. ACS Sensors, 10(10), 7343-7353. https://doi.org/10.1021/acssensors.5c00907

Vancouver

Wang F, Qin S, Yang Z, Edwards-Medina LM, Chiu BL, Acevedo-Vélez C, et al. A Machine Learning-Assisted Liquid Crystal Droplet Array Platform for the Sensitive and Selective Detection of Per- and Polyfluoroalkyl Substances (PFAS) in Water. ACS Sensors. 2025;10(10):7343-7353. doi:10.1021/acssensors.5c00907

BibTeX
@article{Wang2025,
  author = {Wang, Fengrui and Qin, Shiyi and Yang, Zhao and Edwards-Medina, Leena M and Chiu, Benjamin L and Acevedo-Vélez, Claribel and Remucal, Christina K and Van Lehn, Reid C and Zavala, Victor M and Lynn, David M},
  title = {A Machine Learning-Assisted Liquid Crystal Droplet Array Platform for the Sensitive and Selective Detection of Per- and Polyfluoroalkyl Substances (PFAS) in Water},
  journal = {ACS Sensors},
  year = {2025},
  volume = {10},
  number = {10},
  pages = {7343--7353},
  doi = {10.1021/acssensors.5c00907}
}
Kostenlos starten →