EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Physically Consistent AI Framework for Predictive Design of Microfluidic Double Emulsions Toward Precision Liposome Fabrication

S Morteza Mousavi iD, Milad Razbin iD, Robert A Taylor iD, Ming Li iD

Small Methods · 13.11.2026

DOI: 10.1002/smtd.71198 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Small Methods, online erschienen am 13.11.2026. Verfasst von S Morteza Mousavi und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, New South Wales, Australia. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council, National Health and Medical Research Council, International Macquarie Research Excellence Scholarship (iMQRES) at Macquarie University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Microfluidic double emulsions offer a powerful route for templated liposome fabrication; however, precise and reproducible control over droplet architecture remains challenging due to the highly nonlinear coupling between flow dynamics and interfacial phenomena. Here, we present a physics‐consistent, data‐driven framework that combines artificial neural networks (ANNs) with genetic algorithms (GAs) to enable predictive inverse design and target‐driven optimization of double‐emulsion generation. By systematically varying lipid concentration, surfactant concentration, and flow‐rate parameters within a flow‐focusing microfluidic platform, the ANN model learns the underlying relationships governing droplet formation with near‐unity predictive accuracy. Coupling the trained model with a GA enables precise control of droplet morphology, demonstrated here by the generation of droplets with a targeted 30 µm core diameter and 5 µm shell thickness, resulting in liposomes with diameters of approximately 30 µm after solvent extraction. Experimental results closely matched the model predictions for both the selected processing conditions and the resulting droplet properties, confirming the reliability of the proposed framework. The flow‐related parameters had the greatest impact on droplet diameter and production frequency. This study demonstrates a practical, interpretable AI‐guided optimization approach for complex microfluidic platforms, while offering a scalable route for the fabrication of liposomes and other structured soft‐material systems.

Schlagwörter

Stichwörter der Autor:innen

double emulsionsgenetic optimizationliposomesmicrofluidicsneural‐network modeling

Autor:innen und Institutionen

  • School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, New South Wales, Australia.
  • School of Engineering, Macquarie University, Sydney, New South Wales, Australia.
  • School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney, New South Wales, Australia.

ORCID-Profile: S Morteza Mousavi, Milad Razbin, Robert A Taylor, Ming Li

Förderung

  • Australian Research Council
  • National Health and Medical Research Council
  • International Macquarie Research Excellence Scholarship (iMQRES) at Macquarie University
  • Tuition Fee Scholarship (TFS) at the University of New South Wales

Zitieren

APA

Mousavi, S. M., Razbin, M., Taylor, R. A., & Li, M. (2026). A Physically Consistent AI Framework for Predictive Design of Microfluidic Double Emulsions Toward Precision Liposome Fabrication. Small Methods. https://doi.org/10.1002/smtd.71198

Vancouver

Mousavi SM, Razbin M, Taylor RA, Li M. A Physically Consistent AI Framework for Predictive Design of Microfluidic Double Emulsions Toward Precision Liposome Fabrication. Small Methods. 2026. doi:10.1002/smtd.71198

BibTeX
@article{Mousavi2026,
  author = {Mousavi, S Morteza and Razbin, Milad and Taylor, Robert A and Li, Ming},
  title = {A Physically Consistent AI Framework for Predictive Design of Microfluidic Double Emulsions Toward Precision Liposome Fabrication},
  journal = {Small Methods},
  year = {2026},
  doi = {10.1002/smtd.71198}
}
Kostenlos starten →