InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations

Abstract

We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ. In situ visualization, generating visualizations at simulation time, is becoming prevalent in handling large-scale simulations because of the I/O and storage constraints. However, in situ visualization approaches limit the flexibility of post-hoc exploration because the raw simulation data are no longer available. Although multiple image-based approaches have been proposed to mitigate this limitation, those approaches lack the ability to explore the simulation parameters. Our approach allows flexible exploration of parameter space for large-scale ensemble simulations by taking advantage of the recent advances in deep learning. Specifically, we design InSituNet as a convolutional regression model to learn the mapping from the simulation and visualization parameters to the visualization results. With the trained model, users can generate new images for different simulation parameters under various visualization settings, which enables in-depth analysis of the underlying ensemble simulations. We demonstrate the effectiveness of InSituNet in combustion, cosmology, and ocean simulations through quantitative and qualitative evaluations.Index Terms-In situ visualization, ensemble visualization, parameter space exploration, deep learning, image synthesis.

Online data analysis and reduction: An important Co-design motif for extreme-scale computers

“…Asynchronous coordination structures such as DataSpaces (Docan et al, 2012) can be useful, as we later discuss in our CANDLE case study. Specialized analysis methods such as deep learning may be used to identify interesting elements in ensembles (He et al, 2019) and to evaluate the quality of trajectories (Lee et al, 2019).…”

IsoExplorer: an isosurface-driven framework for 3D shape analysis of biomedical volume data

“…Yang et al (2019) proposed a CNN-based neural network model to evaluate the score of a specific rendered image for viewpoint recommendation in DVR. He et al (2019) designed InSituNet with a GAN architecture to assist in exploring the parameter space in in-situ visualization. For IVR, deep learning can help analyze geometric primitives obtained from volume data in multiple perspectives.…”

State of the Art in Time‐Dependent Flow Topology: Interpreting Physical Meaningfulness Through Mathematical Properties

“…He et al . [HWG*20] use a deep‐learning‐based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ.…”