Segmentation of turbulent computational fluid dynamics simulations with unsupervised ensemble learning

Abstract

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 catalogues. 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.

arXiv comment15 pages, 8 figures. Accepted to Signal Processing: Image Communication. Code available from a repository: https://github.com/mkruuse/segmenting-turbulent-simulations-with-ensemble-learning

References in corpus (8)

• Particle Acceleration in Relativistic Plasma Turbulence
• Statistical Analysis of Current Sheets in Three-Dimensional Magnetohydrodynamic Turbulence
• Non-local Neural Networks
• Kinetic turbulence in relativistic plasma: from thermal bath to non-thermal continuum
• Structures in magnetohydrodynamic turbulence: detection and scaling
• Identifying magnetic reconnection in 2D Hybrid Vlasov Maxwell simulations with Convolutional Neural Networks
• Detecting Reconnection Events in Kinetic Vlasov Hybrid Simulations Using Clustering Techniques
• Identification and characterization of current sheets in collisionless plasma turbulence