VDL-Surrogate: A View-Dependent Latent-based Model for Parameter Space Exploration of Ensemble Simulations
VDL-Surrogate: A View-Dependent Latent-based Model for Parameter Space Exploration of Ensemble Simulations
复制标题
DOI：
10.1109/tvcg.2022.3209413
复制
发表时间：
2022-07
影响因子：
5.2
通讯作者：
Neng Shi;Jiayi Xu;Hanqi Guo;J. Woodring;Han-Wei Shen
中科院分区：
文献类型：
--
作者：
Neng Shi;Jiayi Xu;Hanqi Guo;J. Woodring;Han-Wei Shen
我们提出了VDL-Surrogate，一个基于视图依赖神经网络潜伏的代理模型，用于集成模拟的参数空间探索，允许高分辨率的可视化和用户指定的视觉映射。代理启用参数空间探索允许域科学家预览仿真结果，而不必运行大量的计算成本高的仿真。然而，受计算资源的限制，现有的代理模型可能无法产生具有足够分辨率的预览以用于可视化和分析。为了提高计算资源的有效利用并支持高分辨率探索，我们从不同的角度执行光线投射以收集样本并产生紧凑的潜在表示。这种潜在的编码过程降低了代理模型训练的成本，同时保持了输出质量。在模型训练阶段，我们选择视点覆盖整个观察范围，并为所选视点训练相应的VDL-Surrogate模型。在模型推理阶段，我们预测在先前选定的视点的潜在表示，并解码的潜在表示的数据空间。对于任何给定的视点，我们在选定的视点对解码数据进行插值，并使用用户指定的视觉映射生成可视化。我们展示了VDL-Surrogate在宇宙学和海洋模拟中的有效性和效率，并进行了定量和定性评价。源代码可在https://github.com/trainsn/VDL-Surrogate上公开获取。
We propose VDL-Surrogate, a view-dependent neural-network-latent-based surrogate model for parameter space exploration of ensemble simulations that allows high-resolution visualizations and user-specified visual mappings. Surrogate-enabled parameter space exploration allows domain scientists to preview simulation results without having to run a large number of computationally costly simulations. Limited by computational resources, however, existing surrogate models may not produce previews with sufficient resolution for visualization and analysis. To improve the efficient use of computational resources and support high-resolution exploration, we perform ray casting from different viewpoints to collect samples and produce compact latent representations. This latent encoding process reduces the cost of surrogate model training while maintaining the output quality. In the model training stage, we select viewpoints to cover the whole viewing sphere and train corresponding VDL-Surrogate models for the selected viewpoints. In the model inference stage, we predict the latent representations at previously selected viewpoints and decode the latent representations to data space. For any given viewpoint, we make interpolations over decoded data at selected viewpoints and generate visualizations with user-specified visual mappings. We show the effectiveness and efficiency of VDL-Surrogate in cosmological and ocean simulations with quantitative and qualitative evaluations. Source code is publicly available at https://github.com/trainsn/VDL-Surrogate.