arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.08338cs.LGphysics.flu-dyn
收藏

使用深度学习的探索性拉格朗日粒子跟踪

Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

University of Utah(犹他大学);SCI Institute(科学计算与成像研究所)

Mengjiao Han, Sudhanshu Sane, Chris R. Johnson

摘要:

由计算流体动力学模拟产生的时变矢量场通常非常大,并对精确的交互式分析和探索提出了挑战。为了解决这些挑战,减少拉格朗日表示已越来越多地研究作为一种手段,以提高科学的时变矢量场的探索能力。本文提出了一种新的基于深度神经网络的粒子跟踪方法,以探索由拉格朗日流图表示的时变矢量场。在我们的工作流程中,首先利用原位处理来提取拉格朗日流图,然后深度神经网络使用提取的数据来学习流场行为。使用经过训练的模型来预测新的粒子轨迹提供了固定的小内存占用和快速推理。为了证明和评估所提出的方法,我们使用一个著名的分析数据集,双陀螺进行了深入的性能研究。我们的研究考虑了两种流图提取策略以及训练样本数量和整合持续时间对疗效的影响,评估了用于训练和测试的多个采样选项,并告知了超参数设置。总的来说,我们发现我们的方法需要10.5 MB的固定内存占用来编码时变向量场的拉格朗日表示,同时保持准确性。对于事后分析,加载训练好的模型只需两秒钟,大大减少了读取数据进行可视化时的I/O负担。此外,我们的并行实现可以使用一个NVIDIA Titan RTX GPU在1.3秒内为整个时间分辨率的2000条新路径线中的每条路径线推断出100个位置。

英文摘要:

Time-varying vector fields produced by computational fluid dynamics simulations are often prohibitively large and pose challenges for accurate interactive analysis and exploration. To address these challenges, reduced Lagrangian representations have been increasingly researched as a means to improve scientific time-varying vector field exploration capabilities. This paper presents a novel deep neural network-based particle tracing method to explore time-varying vector fields represented by Lagrangian flow maps. In our workflow, in situ processing is first utilized to extract Lagrangian flow maps, and deep neural networks then use the extracted data to learn flow field behavior. Using a trained model to predict new particle trajectories offers a fixed small memory footprint and fast inference. To demonstrate and evaluate the proposed method, we perform an in-depth study of performance using a well-known analytical data set, the Double Gyre. Our study considers two flow map extraction strategies as well as the impact of the number of training samples and integration durations on efficacy, evaluates multiple sampling options for training and testing and informs hyperparameter settings. Overall, we find our method requires a fixed memory footprint of 10.5 MB to encode a Lagrangian representation of a time-varying vector field while maintaining accuracy. For post hoc analysis, loading the trained model costs only two seconds, significantly reducing the burden of I/O when reading data for visualization. Moreover, our parallel implementation can infer one hundred locations for each of two thousand new pathlines across the entire temporal resolution in 1.3 seconds using one NVIDIA Titan RTX GPU.

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。

↑