為了研究不同的物理現象，科學家們經常在超級電腦上運行電腦模擬，以生成不同初始模擬參數的數據集。分析數據集的常見做法是將數據集從超級電腦移動到磁盤，並在後分析機器上分析數據集。隨著數據規模的增長，連接到超級電腦的有限的帶寬和存儲空間成為數據分析管道的瓶頸。為了支持大規模數據分析和可視化，我們提出了一種深度學習輔助的基於圖像的方法。我們的方法產生了一個小型的基於圖像的數據代理，具有較低的圖像分辨率和較低的原位像素射線採樣率，以減少輸入和輸出時間和磁盤存儲空間需求。深度學習模型經過高級訓練，可將小型數據代理恢復到常規採樣率和圖像分辨率，以實現高質量數據可視化和探索。我們評估並表明我們的方法優於多種選擇。

To study the physical phenomenon, scientists often run the computer simulation on the supercomputer to generate datasets of different initial simulation parameters. The common practice to analyze the dataset is moving the datasets from the supercomputer to the disk and analyze datasets on the post analysis machine. When the data size grows, the limited bandwidth and the storage that connects to the supercomputer becomes the bottleneck of the data analysis pipeline. To support the large-scale data analysis and visualization, we propose a deep-learning assisted image-based approach. Our approach produces a compact image-based data proxy with a lower image resolution and a lower sampling rate along pixel rays in situ to reduce the I/O time and disk storage requirement. A deep learning model is trained in advanced to recover the compact data proxy to regular sampling rate and image resolution for high quality data visualization and exploration. We evaluate and show that our approach outperforms multiple alternative.

Ann S. Almgren, John B. Bell, Mike J. Lijewski, Zarija Lukic, and Ethan Van An-del. Nyx: A MASSIVELY PARALLEL AMR CODE FOR COMPUTATIONAL COSMOLOGY. The Astrophysical Journal, 765(1):39, feb 2013.

Kwan-Liu Ma Anna Tikhonova, Carlos D. Correa. Explorable images for visualizing volume data. 2010.

Kwan-Liu Ma Anna Tikhonova, Carlos D. Correa. An exploratory technique for coherent visualization of time-varying volume data. Computer Graphics Forum, 29:783–792, June 2010.

Yuhua Chen, Feng Shi, Anthony G Christodoulou, Zhengwei Zhou, Yibin Xie, and Debiao Li. Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network. 2018.

Yuhua Chen, Feng Shi, Anthony G, Christodoulou, Zhengwei Zhou, Yibin Xie, and Debiao Li. Brain MRI super resolution using 3D deep densely connected neural networks. 2018.

Sheng Di and Franck Cappello. Fast Error-Bounded Lossy HPC Data Compression with SZ. 2016.

Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image Super-Resolution Using Deep Convolutional Networks. 2014.

Francesco Cardinale et al. Isr. https://github.com/idealo/image-super-resolution, 2018.

Kai Fukami, Koji Fukagata, and Kunihiko Taira. Machine learning based spatiotemporal super resolution reconstruction of turbulent flows. 2020

Igor Gitman and Boris Ginsburg. Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification. 2017.

G. Gopalakrishnan-A. Kartadikaria H. Huang-O. Knio H. Toye, P. Zhan and I. Hoteit. Ensemble data assimilation in the red sea: sensitivity to ensemble selection and atmospheric forcing. Ocean Dynamics, 67:915–933, July 2017.

Jun Han and Chaoli Wang. TSR-TVD: Temporal Super-Resolution for Time-Varying Data Analysis and Visualization. 2019.

Jun Han and Chaoli Wang. SSR-TVD: Spatial Super-Resolution for Time-Varying Data Analysis and Visualization. 2020.

Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. Densely Connected Convolutional Networks. 2017.

Patrick O’Leary-John Patchett David H. Rogers Mark Petersen James Ahrens, Sebastien Jourdain. An Image-based Approach to Extreme Scale In Situ Visualization and Analysis. 2014.

Jianchao Yang-Ning Xu Zhaowen Wang Xinchao Wang Thomas Huang Jiahui Yu, Yuchen Fan. Wide Activation for Efficient and Accurate Image Super-Resolution. 2018.

Shaoqing Ren-Jian Sun Kaiming He, Xiangyu Zhang. Deep Residual Learning for Image Recognition. 2016.

Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. Accurate Image Super-Resolution Using Very Deep Convolutional Networks. 2015.

Ba J. Kingma, D. Adam: A method for stochastic optimization. 2015.

Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. 2017.

Son S. Kim H.-Nah S. Lee K.M. Lim, B. Enhanced deep residual networks for single image super-resolution. 2017.

Peter Lindstrom. Fixed-Rate Compressed Floating-Point Arraysn. 2014.

Kwan-Liu Ma. In Situ Visualization at Extreme Scale: Challenges and Opportunities. 2009.

James Hays-Zsolt Kira Naveen Kodali, Jacob Abernethy. On Convergence and Stability of GANs. 2017.

Filip Sadlo-Thomas Ertl Oliver Fernandes, Steffen Frey. Space-time volumetric depth images for in-situ visualization. 2014.

John Patchett and Galen Gisler. Deep water impact ensemble data set. Technical report, 2017. LA-UR-17-21595.

Chi-Hieu Pham, Carlos Tor-D´ıez, H´el‘ene Meunier, Nathalie Bednarek, Ronan Fablet, Nicolas Passatd, and Fran¸cois Rousseau. Multiscale brain MRI super-resolution using deep 3D convolutional networks. Computerized medical imaging and graphics, vol. 77, 2019.

S.M.R. Soroushmehr-S. Samavi H. Derksen K. Najarian S. Kazeminia, N. Karimi. Region of interest extraction for lossless compression of bone X-ray images. 2015.

Ko-Chih Wang; Naeem Shareef; Han-Wei Shen. Ray-Based Exploration of Large Time-Varying Volume Data Using Per-Ray Proxy Distributions. 2019.

Ioffe S. Vanhoucke V. Szegedy, C. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. 2016.

Masanori Koyama-Yuichi Yoshida Takeru Miyato, Toshiki Kataoka. Spectral Normalization for Generative Adversarial Networks. 2018.

Jarin Tasnim and Debajyoti Mondal. Data Reduction and Deep-Learning Based Recovery for Geospatial Visualization and Satellite Imagery. 2020.

Anna Tikhonova, Carlos D Correa, and Kwan-Liu Ma. Explorable images for visualizaing volume data. PacificVis, 10:177–184, 2010.

Lulu Wang, Jinglong Du, Huazheng Zhu, Zhongshi He1, and Yuanyuan Jia. Brain MR Image Super-resolution using 3D Feature Attention Network. 2020.

Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, and Xiaoou Tang. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. 2018.

Hanqi Guo-Ko-Chih Wang Han-Wei Shen Mukund Raj Youssef S. G. Nashed Tom Peterka Wenbin He, Junpeng Wang. InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations. 2019.

Skylar W. Wurster, Han-Wei Shen, Hanqi Guo, Thomas Peterka, Mukund Raj, and Jiayi Xu. Deep Hierarchical Super-Resolution for Scientific Data Reduction and Visualization. 2021.

Dingwen Tao-Zizhong Chen Franck Cappello Xin Liang, Sheng Di. An Efficient Transformation Scheme for Lossy Data Compression with Point-Wise Relative Error Bound. 2018.

Hao Wang-Dit-Yan Yeung Wai-kin Wong Wang-chun Woo Xingjian Shi, Zhourong Chen. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. 2015.

Shan Liu Yuhang Zhang, Zhenzhong Chen. Video Super Resolution Using Temporal Encoding ConvLSTM and Multi-Stage Fusion. 2020.