arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.20102eess.IV
收藏

基于深度学习的粒子图像测速中的不确定性预测研究

On Uncertainty Prediction for Deep-Learning-based Particle Image Velocimetry

Wei Wang, Jeremiah Hu, Jia Ai, Yong Lee

AI总结:

针对深度学习PIV缺乏可靠不确定性量化的问题,本文比较UNN、MM和MT三种方法,发现UNN在轻微扰动和三项指标下表现最佳。

摘要:

粒子图像测速(Particle Image Velocimetry,PIV)是一种广泛应用的流动测量技术,传统上依赖互相关来追踪位移。近年来,基于深度学习的方法显著提升了PIV测量的精度和效率。然而,尽管其重要性突出,为基于深度学习的PIV提供可靠的不确定性量化仍是一个关键且在很大程度上被忽视的挑战。本文探讨了用于量化基于深度学习的PIV中不确定性的三种方法:不确定性神经网络(Uncertainty neural network,UNN)、多模型(Multiple models,MM)和多变换(Multiple transforms,MT)。我们在多个数据集上评估了这三种方法。结果表明,三种方法在轻微扰动下均表现良好。在三项评价指标中,UNN方法始终取得最佳性能,能够提供准确的不确定性估计,并展现出在基于深度学习的PIV中进行不确定性量化的巨大潜力。本研究为PIV中的不确定性量化提供了一个综合框架,为未来研究和实际实现提供了见解。

英文摘要:

Particle Image Velocimetry (PIV) is a widely used technique for flow measurement that traditionally relies on cross-correlation to track the displacement. Recent advances in deep learning-based methods have significantly improved the accuracy and efficiency of PIV measurements. However, despite its importance, reliable uncertainty quantification for deep learning-based PIV remains a critical and largely overlooked challenge. This paper explores three methods for quantifying uncertainty in deep learning-based PIV: the Uncertainty neural network (UNN), Multiple models (MM), and Multiple transforms (MT). We evaluate the three methods across multiple datasets. The results show that all three methods perform well under mild perturbations. Among the three evaluation metrics, the UNN method consistently achieves the best performance, providing accurate uncertainty estimates and demonstrating strong potential for uncertainty quantification in deep learning-based PIV. This study provides a comprehensive framework for uncertainty quantification in PIV, offering insights for future research and practical implementation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑