Ensemble latent assimilation with deep learning surrogate model: application to drop interaction in microfluidics device

Yilin Zhuang, Sibo Cheng, Nina Kovalchuk, M. J. H. Simmons, Omar Matar, Yike Guo, Rossella Arcucci

Research output: Contribution to journalArticlepeer-review

137 Downloads (Pure)

Abstract

A major challenge in the field of microfluidics is to predict and monitor drop interactions. In this work, based on experiments performed on a microfluidics device, we developed an image-based data-driven model to forecast drop dynamics. To alleviate the computational burden, reduced-order modelling techniques, namely proper orthogonal decomposition and convolutional neural networks, are applied to compress the recorded images into low-dimensional spaces. Recurrent neural networks are then employed to build a surrogate model of drop interactions by learning the dynamics of compressed variables in the reduced-order space. To incorporate real-time observations, we developed an ensemble-based Latent Assimilation algorithm scheme. With the help of ensemble-based data assimilation techniques, the novel approach improve the prediction results by adjusting the starting point of the next time-level forecast. The performance of the developed system is evaluated by experimental data (i.e., recorded videos), which is excluded from the training of reduced-order modelling and recurrent neural networks. The developed scheme is general, and it can be applied to other dynamical systems.
Original languageEnglish
Pages (from-to)3187-3202
Number of pages16
JournalLab on a Chip
Volume22
Issue number17
Early online date5 Jul 2022
DOIs
Publication statusE-pub ahead of print - 5 Jul 2022

ASJC Scopus subject areas

  • Bioengineering
  • Biochemistry
  • General Chemistry
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Ensemble latent assimilation with deep learning surrogate model: application to drop interaction in microfluidics device'. Together they form a unique fingerprint.

Cite this