Deep Regression Network-Assisted Efficient Streamline Generation Method

Abstract

Streamlining is one of the most frequently utilized visualization methods to analyze the flow structure of computational fluid dynamics (CFD) data. However, it is challenging to find a set of streamlines showing the most prominent flow across the entire flow field due to the heavy computation time required to generate bundles of streamlines. In this paper, we propose an efficient streamline generation method that removes several seed candidates that are predicted as less important using a 3D U-net based regression model. We employ 3D line integral convolution (LIC) volumes that depict the entire flow field for training data of the proposed learning model and evaluate our method using a real-world CFD data set. We find using our model that we can obtain quality of visualization results comparable to that of the ground truth even when more than 90% of the seed candidates are truncated while operating 6.6∼17.1 times faster than the competing method.INDEX TERMS deep regression network, dilated convolutional neural network, flow visualization, line integral convolution, streamline

Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

“…Li et al (2015) employed a support vector machine (SVM) to segment streamlines based on user-identified features. For the widely studied task of selecting a representative set of particle trajectories (Sane et al, 2020), recent state-of-the-art techniques by Han et al (2018) and Lee and Park (2021) have used deep-learning-based clustering approaches. Further, modern techniques to reconstruct steady-state vector fields using a set of streamlines employ machine learning Sahoo and Berger, 2021).…”

Polar Vortex Multi-Day Intensity Prediction Relying on New Deep Learning Model: A Combined Convolution Neural Network with Long Short-Term Memory Based on Gaussian Smoothing Method

“…With the renewal and iteration of the neural networks, many spatiotemporal prediction models are constantly proposed and applied to the prediction of various systems in the atmosphere [76][77][78][79][80][81][82][83]. The ensemble DL model is one of the most typical cases.…”

“…Similarly, the application of SmaAt-UNet proposed by [78] to short-term precipitation can also make up for the defection of numerical weather forecast to use the latest information for a short-term forecast. The generation of streamline model is also an essential way to analyze the meteorological; Lee et al [81] described the flow field based on the three-dimensional U-net regression model and line integral convolution (LIC) volume with remarkable speed and visualization effect. With the development of mathematical and physical, many mathematical methods for time series and image processing have been gradually proposed and updated.…”