当前位置: X-MOL 学术Signal Process. Image Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Segmentation of turbulent computational fluid dynamics simulations with unsupervised ensemble learning
Signal Processing: Image Communication ( IF 3.5 ) Pub Date : 2021-08-30 , DOI: 10.1016/j.image.2021.116450
Maarja Bussov 1, 2 , Joonas Nättilä 3, 4
Affiliation  

Computer vision and machine learning tools offer an exciting new way for automatically analyzing and categorizing information from complex computer simulations. Here we design an ensemble machine learning framework that can independently and robustly categorize and dissect simulation data output contents of turbulent flow patterns into distinct structure catalogs. The segmentation is performed using an unsupervised clustering algorithm, which segments physical structures by grouping together similar pixels in simulation images. The accuracy and robustness of the resulting segment region boundaries are enhanced by combining information from multiple simultaneously-evaluated clustering operations. The stacking of object segmentation evaluations is performed using image mask combination operations. This statistically-combined ensemble (SCE) of different cluster masks allows us to construct cluster reliability metrics for each pixel and for the associated segments without any prior user input. By comparing the similarity of different cluster occurrences in the ensemble, we can also assess the optimal number of clusters needed to describe the data. Furthermore, by relying on ensemble-averaged spatial segment region boundaries, the SCE method enables reconstruction of more accurate and robust region of interest (ROI) boundaries for the different image data clusters. We apply the SCE algorithm to 2-dimensional simulation data snapshots of magnetically-dominated fully-kinetic turbulent plasma flows where accurate ROI boundaries are needed for geometrical measurements of intermittent flow structures known as current sheets.



中文翻译:

使用无监督集成学习分割湍流计算流体动力学模拟

计算机视觉和机器学习工具为自动分析和分类来自复杂计算机模拟的信息提供了一种令人兴奋的新方法。在这里,我们设计了一个集成机器学习框架,该框架可以独立且稳健地将湍流模式的模拟数据输出内容分类和剖析为不同的结构目录。分割是使用无监督聚类算法执行的,该算法通过将模拟图像中的相似像素分组在一起来分割物理结构。通过组合来自多个同时评估的聚类操作的信息,结果片段区域边界的准确性和鲁棒性得到增强。使用图像掩码组合操作执行对象分割评估的堆叠。这种不同集群掩码的统计组合集成 (SCE) 使我们能够在没有任何事先用户输入的情况下为每个像素和相关段构建集群可靠性指标。通过比较集成中不同簇出现的相似性,我们还可以评估描述数据所需的最佳簇数。此外,通过依赖于整体平均的空间段区域边界,SCE 方法能够为不同的图像数据簇重建更准确和稳健的感兴趣区域 (ROI) 边界。我们将 SCE 算法应用于磁主导的全动力学湍流等离子体流的二维模拟数据快照,其中需要准确的 ROI 边界来对称为电流片的间歇流结构进行几何测量。

更新日期:2021-09-10
down
wechat
bug