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 2409.00230cs.LGcs.AIphysics.flu-dyn
收藏

具有交叉注意力的空间感知扩散模型用于稀疏观测的全局场重建

Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observations

University of Michigan(密歇根大学);École des Ponts(巴黎路桥学院);EDF R&D(法国电力研发中心);Institut Polytechnique de Paris(巴黎综合理工学院)

Yilin Zhuang, Sibo Cheng, Karthik Duraisamy

AI总结:

本研究提出一种带交叉注意力的空间感知扩散模型,通过条件编码融合稀疏观测与插值场,实现全局场重建,并在多种偏微分方程基准上验证了其在噪声条件下的优越性。

摘要:

扩散模型因其能够表示复杂分布并纳入不确定性而受到关注,使其成为在存在噪声或不完整数据的情况下进行稳健预测的理想选择。在本研究中,我们开发并增强了基于分数的扩散模型在场地重建任务中的应用,其目标是从部分观测中估计完整的空间场。我们引入了一种条件编码方法,通过将稀疏观测和插值场的可学习集成作为归纳偏置,构建观测区域与未观测区域之间可处理的映射。凭借精细化的传感表示和展开的时间维度,我们的方法能够处理任意移动传感器并有效重建场。此外,我们对我们的方法与一种基于确定性插值的方法在各种静态和与时间相关的偏微分方程上进行了全面基准测试。我们的研究试图解决在评估不同采样超参数、噪声水平和条件方法下性能时缺乏强基线的空白。我们的结果表明,具有交叉注意力和所提出的条件编码的扩散模型在噪声条件下通常优于其他方法,尽管确定性方法在无噪声数据上表现优异。此外,对于稳态问题,扩散模型和确定性方法在精度和计算成本方面均超越了数值方法。我们还展示了模型捕捉可能重建的能力,并通过集成采样在基于协方差的校正任务中提高融合结果的精度。

英文摘要:

Diffusion models have gained attention for their ability to represent complex distributions and incorporate uncertainty, making them ideal for robust predictions in the presence of noisy or incomplete data. In this study, we develop and enhance score-based diffusion models in field reconstruction tasks, where the goal is to estimate complete spatial fields from partial observations. We introduce a condition encoding approach to construct a tractable mapping mapping between observed and unobserved regions using a learnable integration of sparse observations and interpolated fields as an inductive bias. With refined sensing representations and an unraveled temporal dimension, our method can handle arbitrary moving sensors and effectively reconstruct fields. Furthermore, we conduct a comprehensive benchmark of our approach against a deterministic interpolation-based method across various static and time-dependent PDEs. Our study attempts to addresses the gap in strong baselines for evaluating performance across varying sampling hyperparameters, noise levels, and conditioning methods. Our results show that diffusion models with cross-attention and the proposed conditional encoding generally outperform other methods under noisy conditions, although the deterministic method excels with noiseless data. Additionally, both the diffusion models and the deterministic method surpass the numerical approach in accuracy and computational cost for the steady problem. We also demonstrate the ability of the model to capture possible reconstructions and improve the accuracy of fused results in covariance-based correction tasks using ensemble sampling.

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。

↑