$μ$-FlowNet: A Deep Learning Approach for Mapping Flow Fields in Irregular Microchannels Using an Attention-based U-Net Encoder-Decoder Architecture

2026-04-19

AI Summary

This study addresses the high computational cost and low efficiency of traditional computational fluid dynamics (CFD) methods in simulating flow fields within irregular circular microchannels. To overcome these limitations, the authors propose μ-FlowNet, a U-Net-based encoder-decoder architecture augmented with attention mechanisms, which learns complex microfluidic flow field distributions through end-to-end training on CFD-generated data. The proposed method achieves significantly improved prediction accuracy and structural similarity, attaining a Dice coefficient of 0.9317 and an Intersection over Union (IoU) of 0.8731 on the test set. These results outperform those of standard U-Net and T-Net, establishing μ-FlowNet as a novel and efficient paradigm for microfluidic flow field mapping.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

In the complex domain of microfluidics systems, analysing fluid flow patterns through random-shaped circular microchannels is significantly challenging task. Conventional approach of solving such problems using computational fluid dynamics often incapable due to their intensive computational requirements and high simulation times. In this study, addressing these limitations, we introduce $μ$-FlowNet, a deep learning framework based on the adaptable U-Net autoencoders. This model provides a data-driven approach that enhances the prediction and mapping of random-shaped circular microchannels and their corresponding fluid flow patterns. The datasets required for the training of the model is generated by performing extensive simulations using conventional approach of computational fluid dynamics methods. The datasets are then pre-processed and accessed the required spatial and temporal features that are essential for the training. We have trained three different models based on U-Net framework namely, standard U-Net, T-Net, and U-Net with attention mechanism to compare the prediction accuracy and loss. The accuracy of the $μ$-FlowNet is compared using metrics of dice score and intersection over union and it shows that U-Net with attention mechanism shows the highest dice score and IoU of 0.9317 and 0.8731, respectively and shows the highest structural similarity as compared to standard U-Net and T-Net. This show that U-Net with attention mechanism serves best model to map the fluid flow pattern with random datasets on testing.

Problem

• microfluidics
• irregular microchannels
• flow field mapping
• fluid flow patterns
• computational fluid dynamics

Innovation

• attention mechanism
• U-Net
• microfluidics
• flow field prediction
• deep learning