Machine learning enables design automation of microfluidic | ResearchBunny

Index

Abstract

Droplet-based microfluidic devices offer cost-effective screening platforms for life science applications. However, the unpredictable nature of droplet generation hinders efficient device engineering. This paper introduces DAFD, a web-based tool using machine learning to predict and automate the design of flow-focusing droplet generators. DAFD predicts droplet diameter and rate with high accuracy (MAE < 10 µm and 20 Hz), delivering user-specified performance within a narrow margin. The tool's design allows community extension to support additional fluid combinations, simplifying microfluidics adoption in life sciences.

Publisher

Nature Communications

Published On

Jan 04, 2021

Authors

Ali Lashkaripour, Christopher Rodriguez, Noushin Mehdipour, Rizki Mardian, David McIntyre, Luis Ortiz, Joshua Campbell, Douglas Densmore

Related Publications

Explore these studies to deepen your understanding of the subject.

Medicine and Health

Machine learning models to accelerate the design of polymeric long-acting injectables

P. Bannigan, Z. Bao, et al.

Engineering and Technology

Machine learning-enabled forward prediction and inverse design of 4D-printed active plates

X. Sun, L. Yue, et al.

Engineering and Technology

Machine learning enables the discovery of 2D Invar and anti-Invar monolayers

S. Tian, K. Zhou, et al.

Engineering and Technology

Generation of tumor spheroids using a droplet-based microfluidic device for photothermal therapy

J. M. Lee, J. W. Choi, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny