Squeeze flow of micro-droplets: convolutional neural network with trainable and tunable refinement

TL;DR

This paper introduces a neural network-based platform for modeling the squeeze flow of micro-droplets, featuring a trainable refinement mechanism that improves image translation accuracy, with applications in data compression and encryption.

Contribution

It presents a novel neural network architecture with tunable residual blocks for inverse image translation in micro-droplet squeeze flow, integrating physics-based PDEs and a scalable Python package.

Findings

The neural network effectively translates high-resolution images to low-resolution droplet patterns.

The refinement level tuning improves image translation accuracy.

The platform is scalable and publicly available for benchmarking.

Abstract

We propose a platform based on neural networks to solve the image-to-image translation problem in the context of squeeze flow of micro-droplets. In the first part of this paper, we present the governing partial differential equations to lay out the underlying physics of the problem. We also discuss our developed Python package, sqflow, which can potentially serve as free, flexible, and scalable standardized benchmarks in the fields of machine learning and computer vision. In the second part of this paper, we introduce a residual convolutional neural network to solve the corresponding inverse problem: to translate a high-resolution (HR) imprint image with a specific liquid film thickness to a low-resolution (LR) droplet pattern image capable of producing the given imprint image for an appropriate spread time of droplets. We propose a neural network architecture that learns to systematically tune the refinement level of its residual convolutional blocks by using the function approximators that are trained to map a given input parameter (film thickness) to an appropriate refinement level indicator. We use multiple stacks of convolutional layers the output of which is translated according to the refinement level indicators provided by the directly-connected function approximators. Together with a non-linear activation function, such a translation mechanism enables the HR imprint image to be refined sequentially in multiple steps until the target LR droplet pattern image is revealed. The proposed platform can be potentially applied to data compression and data encryption. The developed package and datasets are publicly available on GitHub at https://github.com/sqflow/sqflow.