Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles

TL;DR

This paper introduces a neural network that efficiently learns and reconstructs complex statistical dependencies in large 3D simulation ensembles, enabling interactive visualization of mutual dependencies without heavy runtime computation.

Contribution

The authors develop the first neural network model for compactly representing and reconstructing non-linear statistical dependencies in large 3D simulation data.

Findings

Successfully learned dependencies in a weather ensemble with 1000 members

Reduced memory and computation for dependency reconstruction

Enabled GPU-accelerated interactive visualization of dependencies

Abstract

We present the first neural network that has learned to compactly represent and can efficiently reconstruct the statistical dependencies between the values of physical variables at different spatial locations in large 3D simulation ensembles. Going beyond linear dependencies, we consider mutual information as a measure of non-linear dependence. We demonstrate learning and reconstruction with a large weather forecast ensemble comprising 1000 members, each storing multiple physical variables at a 250 x 352 x 20 simulation grid. By circumventing compute-intensive statistical estimators at runtime, we demonstrate significantly reduced memory and computation requirements for reconstructing the major dependence structures. This enables embedding the estimator into a GPU-accelerated direct volume renderer and interactively visualizing all mutual dependencies for a selected domain point.