Accelerated Probabilistic Marching Cubes by Deep Learning for Time-Varying Scalar Ensembles
This work addresses the challenge of interactive uncertainty visualization for ensemble simulations, which is incremental as it accelerates an existing technique using deep learning.
The paper tackles the high computational cost of probabilistic marching cubes for visualizing positional uncertainty in time-varying ensemble data by introducing a deep-learning-based approach that learns level-set uncertainty from early time steps, achieving up to 170x speedup over serial and 10x over parallel original methods.
Visualizing the uncertainty of ensemble simulations is challenging due to the large size and multivariate and temporal features of ensemble data sets. One popular approach to studying the uncertainty of ensembles is analyzing the positional uncertainty of the level sets. Probabilistic marching cubes is a technique that performs Monte Carlo sampling of multivariate Gaussian noise distributions for positional uncertainty visualization of level sets. However, the technique suffers from high computational time, making interactive visualization and analysis impossible to achieve. This paper introduces a deep-learning-based approach to learning the level-set uncertainty for two-dimensional ensemble data with a multivariate Gaussian noise assumption. We train the model using the first few time steps from time-varying ensemble data in our workflow. We demonstrate that our trained model accurately infers uncertainty in level sets for new time steps and is up to 170X faster than that of the original probabilistic model with serial computation and 10X faster than that of the original parallel computation.