Please wait a minute...
Vis Inf
Vis Inf  2020, Vol. 4 Issue (2): 109-121    DOI: 10.1016/j.visinf.2020.04.004
论文     
CECAV-DNN：使用深度神经网络进行集合比较和可视化
Wenbin Hea, Junpeng Wangb, Hanqi Guoc, Han-Wei Shena, Tom Peterkac
aThe Ohio State University, Columbus, OH, United States  bVisa Research, Palo Alto, CA, United States  cArgonne National Laboratory, Lemont, IL, United States
CECAV-DNN: Collective Ensemble Comparison and Visualization using Deep Neural Networks
Wenbin Hea, Junpeng Wangb, Hanqi Guoc, Han-Wei Shena, Tom Peterkac
aThe Ohio State University, Columbus, OH, United States  bVisa Research, Palo Alto, CA, United States  cArgonne National Laboratory, Lemont, IL, United States
 全文: PDF 
摘要： 本文提出了一种深度学习方法以集合方式比较两组或多组数据，其中每一组都是仿真的输出结果。集合式比较的目的是通过比较成组的仿真结果来帮助科学家理解仿真模型之间的差异。然而，由于成组仿真结果的时空分布位于一个非常高维的空间中，因此以集合方式进行比较并非易事。为此，本文选择训练一个深度判别神经网络，来测量两组给定结果之间的差异，并识别出两组输出数据在什么时间和什么位置不同。本文还设计、开发了一个可视化系统，以帮助用户理解判别网络给出的成组比较结果，并通过两项实际应用验证了本文方法的有效性，这两项应用包括对用于气候研究的社区大气模型（CAM）和面向普通循环模型的快速辐射传输模型（RRTMG）的成组结果比较，以及对不同的空间分辨率下的计算流体动力学（CFD）计算结果进行成组比较。
关键词： 集合比较;  集合数据可视化;  深度神经网络    
Abstract: We propose a deep learning approach to collectively compare two or multiple ensembles, each of which is a collection of simulation outputs. The purpose of collective comparison is to help scientists understand differences between simulation models by comparing their ensemble simulation outputs. However, the collective comparison is non-trivial because the spatiotemporal distributions of ensemble simulation outputs reside in a very high dimensional space. To this end, we choose to train a deep discriminative neural network to measure the dissimilarity between two given ensembles, and to identify when and where the two ensembles are different. We also design and develop a visualization system to help users understand the collective comparison results based on the discriminative network. We demonstrate the effectiveness of our approach with two real-world applications, including the ensemble comparison of the community atmosphere model (CAM) and the rapid radiative transfer model for general circulation models (RRTMG) for climate research, and the comparison of computational fluid dynamics (CFD) ensembles with different spatial resolutions.
Key words: Collective ensemble comparison    Ensemble data visualization    Deep neural networks
出版日期: 2020-06-03
通讯作者: Wenbin He     E-mail: he.495@osu.edu
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Wenbin He
Junpeng Wang
Hanqi Guo
Han-Wei Shen
Tom Peterka

引用本文:

Wenbin He, Junpeng Wang, Hanqi Guo, Han-Wei Shen, Tom Peterka. CECAV-DNN: Collective Ensemble Comparison and Visualization using Deep Neural Networks. Vis Inf, 2020, 4(2): 109-121.

链接本文:

http://www.zjujournals.com/vi/CN/10.1016/j.visinf.2020.04.004    或    http://www.zjujournals.com/vi/CN/Y2020/V4/I2/109

No related articles found!