Accelerated Probabilistic Marching Cubes by Deep Learning for Time-Varying Scalar Ensembles

TL;DR

This paper presents a deep learning method to rapidly estimate level-set uncertainty in time-varying ensemble data, significantly reducing computation time compared to traditional Monte Carlo sampling techniques.

Contribution

The authors develop a deep learning model trained on initial time steps to quickly predict uncertainty in level sets for subsequent data, enabling faster visualization.

Findings

Achieves up to 170X speedup over serial probabilistic marching cubes.

Outperforms original parallel implementation with 10X faster inference.

Accurately infers uncertainty in level sets for new time steps.

Abstract

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.