Ensemble latent assimilation with deep learning surrogate model: application to drop interaction in a microfluidics device. Issue 17 (25th July 2022)

• Record Type: Journal Article
• Authors: Zhuang, Yilin; Cheng, Sibo; Kovalchuk, Nina; Simmons, Mark; Matar, Omar K.; Guo, Yi-Ke; Arcucci, Rossella
• Is Part Of: Lab on a chip. Volume 22:Issue 17(2022)
• Page Start: 3187
• Page End: 3202
• Publication Date: 2022-07-25
• Subjects: Miniature electronic equipment -- Periodicals; Combinatorial chemistry -- Periodicals; Biotechnology -- Periodicals; 543.0813
• DOI: 10.1039/d2lc00303a
• Languages: English
• ISSNs: 1473-0197

Abstract

Abstract : Upper: predictions using the machine learning surrogate model with ensemble latent assimilation; bottom: recorded experimental images of each corresponding timestep. Abstract : A major challenge in the field of microfluidics is to predict and control drop interactions. This work develops an image-based data-driven model to forecast drop dynamics based on experiments performed on a microfluidics device. Reduced-order modelling techniques are applied to compress the recorded images into low-dimensional spaces and alleviate the computational cost. 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. The surrogate model is integrated with real-time observations using data assimilation. In this paper we developed an ensemble-based latent assimilation algorithm scheme which shows an improvement in terms of accuracy with respect to the previous approaches. This work demonstrates the possibility to create a reliable data-driven model enabling a high fidelity prediction of drop interactions in microfluidics device. The performance of the developed system is evaluated against experimental data ( i.e., recorded videos), which are excluded from the training of the surrogate model. The developed scheme is general and can be applied to other dynamical systems.