Neural Fields for Interactive Visualization of Statistical Dependencies in 3D Simulation Ensembles
This enables interactive visualization of complex statistical dependencies in large-scale 3D simulation data, which is incremental but practically useful for domains like weather forecasting.
The authors tackled the problem of representing and reconstructing statistical dependencies in large 3D simulation ensembles, using mutual information to capture non-linear relationships. They demonstrated this with a weather forecast ensemble of 1000 members, achieving significantly reduced memory and computation requirements that enabled interactive GPU-accelerated visualization.
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.