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

Abstract
We present neural dependence fields (NDFs) - the first neural network that learns to compactly represent and 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 an exemplary 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 250×352×20 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.
Description

CCS Concepts: Computing methodologies → Neural networks; Computer graphics; Applied computing → Earth and atmospheric sciences

        
@inproceedings{
10.2312:vmv.20231229
, booktitle = {
Vision, Modeling, and Visualization
}, editor = {
Guthe, Michael
and
Grosch, Thorsten
}, title = {{
Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles
}}, author = {
Farokhmanesh, Fatemeh
and
Höhlein, Kevin
and
Neuhauser, Christoph
and
Necker, Tobias
and
Weissmann, Martin
and
Miyoshi, Takemasa
and
Westermann, Rüdiger
}, year = {
2023
}, publisher = {
The Eurographics Association
}, ISBN = {
978-3-03868-232-5
}, DOI = {
10.2312/vmv.20231229
} }
Citation
Collections