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

Simple item page
dc.contributor.authorFarokhmanesh, Fatemehen_US
dc.contributor.authorHöhlein, Kevinen_US
dc.contributor.authorNeuhauser, Christophen_US
dc.contributor.authorNecker, Tobias
dc.contributor.authorWeissmann, Martin
dc.contributor.authorMiyoshi, Takemasa
dc.contributor.authorWestermann, Rüdigeren_US
dc.contributor.editorGuthe, Michaelen_US
dc.contributor.editorGrosch, Thorstenen_US
dc.date.accessioned2023-09-25T11:37:23Z
dc.date.available2023-09-25T11:37:23Z
dc.date.issued2023
dc.description.abstractWe 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.en_US
dc.description.sectionheadersImage Visualization and Analysis
dc.description.seriesinformationVision, Modeling, and Visualization
dc.identifier.doi10.2312/vmv.20231229
dc.identifier.isbn978-3-03868-232-5
dc.identifier.pages81-88
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/vmv.20231229
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vmv20231229
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Neural networks; Computer graphics; Applied computing → Earth and atmospheric sciences
dc.subjectComputing methodologies → Neural networks
dc.subjectComputer graphics
dc.subjectApplied computing → Earth and atmospheric sciences
dc.titleNeural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensemblesen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
corrigendum_Farokhmanesh_VMV23.pdf
Size:
8.56 MB
Format:
Adobe Portable Document Format
Description:
Corrigendum (updated author list and acknowledgements)
Download
No Thumbnail Available
Name:
paper1051_mm.mp4
Size:
15.44 MB
Format:
Unknown data format
Download
No Thumbnail Available
Name:
081-088.pdf
Size:
8.48 MB
Format:
Adobe Portable Document Format
Download
Collections
VMV2023