Farokhmanesh, FatemehHöhlein, KevinNeuhauser, ChristophNecker, TobiasWeissmann, MartinMiyoshi, TakemasaWestermann, RüdigerGuthe, MichaelGrosch, Thorsten2023-09-252023-09-252023978-3-03868-232-5https://doi.org/10.2312/vmv.20231229https://diglib.eg.org:443/handle/10.2312/vmv20231229We 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.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Neural networks; Computer graphics; Applied computing → Earth and atmospheric sciencesComputing methodologies → Neural networksComputer graphicsApplied computing → Earth and atmospheric sciences10.2312/vmv.2023122981-888 pages