Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914729916628992 |
|---|---|
| author | Farokhmanesh, Fatemeh Höhlein, Kevin Neuhauser, Christoph Necker, Tobias Weissmann, Martin Miyoshi, Takemasa Westermann, Rüdiger |
| author_facet | Farokhmanesh, Fatemeh Höhlein, Kevin Neuhauser, Christoph Necker, Tobias Weissmann, Martin Miyoshi, Takemasa Westermann, Rüdiger |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_02203 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles Farokhmanesh, Fatemeh Höhlein, Kevin Neuhauser, Christoph Necker, Tobias Weissmann, Martin Miyoshi, Takemasa Westermann, Rüdiger Computer Vision and Pattern Recognition 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. |
| title | Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2307.02203 |