物理引导的时序U-Net用于高保真流体插值
Physics-Informed Temporal U-Net for High-Fidelity Fluid Interpolation
AI总结:
本文提出一种融合感知损失和物理引导的时序U-Net架构,以解决稀疏时间观测下流体动力学重建的挑战,通过时间加权特征融合和抛物线边界条件提升重建质量与稳定性。
摘要:
从稀疏时间观测重建高保真流体动力学极具挑战性,主要由于流体传输的混沌和非线性特性。标准深度学习插值方法常趋向均值,导致空间模糊和时间闪烁,尤其在观测锚点周围显得明显。本文提出一种新颖的时序U-Net架构,结合基于VGG的感知损失和物理引导桥,通过引入时间加权特征融合和由t(1 - t)定义的抛物线边界条件,确保平滑过渡同时保持端点一致性。多通道RGB流体数据实验表明,该方法在结构保真度和纹理保持方面优于标准模型。特别地,模型在均方误差上达到0.015,优于标准L1基线的0.085。进一步的空间功率谱密度分析显示,模型能保留通常在确定性重建中丢失的高频湍流细节。
英文摘要:
Reconstructing high-fidelity fluid dynamics from sparse temporal observations is quite challenging, mainly due to the chaotic and non-linear nature of fluid transport. Standard deep learning-based interpolation methods often tend to regress to the mean, which results in spatial blurring and temporal strobing, especially noticeable around the observed anchor frames where transitions become discontinuous. In this work, we propose a novel Temporal U-Net architecture that integrates a VGG-based perceptual loss along with a Physics-Informed Bridge to overcome these issues. By introducing time-weighted feature blending and enforcing a parabolic boundary condition defined by t(1 - t), the model ensures smooth transitions while also maintaining perfect consistency at the endpoints. Experimental results on multi-channel RGB fluid data show that our method clearly outperforms standard models, both in terms of structural fidelity and texture preservation. In particular, the model achieves a Mean Absolute Error of 0.015, compared to 0.085 for a standard L1 baseline. Further Spatial Power Spectral Density (PSD) analysis reveals that the model is able to retain high-frequency turbulent details that are usually lost in deterministic reconstructions.
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。