東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Deep Learning for Scientific Data Representation and Generation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Learning for Scientific Data Representation and Generation./
作者:	Han, Jun.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	152 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
Contained By:	Dissertations Abstracts International83-10B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29061662
ISBN:	9798209990000

Deep Learning for Scientific Data Representation and Generation.
Han, Jun.

Deep Learning for Scientific Data Representation and Generation. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 152 p.

Source: Dissertations Abstracts International, Volume: 83-10, Section: B.

Thesis (Ph.D.)--University of Notre Dame, 2022.

This item must not be sold to any third party vendors.

Scientific visualization (SciVis) is one of the core components in supporting fundamental scientific discoveries and engineering designs. For example, scientists perform numerical simulations and produce 3D scalar and vector data to visualize, analyze, and understand various kinds of natural phenomena, such as climate change and star formation. However, the cost of these simulations is expensive when time, ensemble, and multivariate are involved and the scientific data are presented in diverse forms including streamline, pathline, stream surface, volume, and isosurface. A core problem in SciVis is how to efficiently and effectively produce and analyze these diversified data. In this dissertation, I develop novel deep learning methods to enable more effective and efficient frameworks for scientific data representation and generation.In scientific data representation, I propose a unified framework that processes both streamlines and stream surfaces through auto-encoder decoder structure. Moreover, I build an interface that allows users to explore the relationships between the learned features and visual representations. I also utilize geometric deep learning (e.g., graph neural network) to extract node-level and surface-level features in an unsupervised fashion for node clustering and surface selection tasks. In scientific data generation, I introduce a comprehensive pipeline for variable selection and translation through feature learning, translation graph construction, and variable translation. This framework can serve as a data extrapolation and compression solution to reduce simulation costs. Besides, I develop an end-to-end generative framework that can synthesize spatiotemporal super-resolution volumes with high fidelity. Further, to improve network generalization, I propose an unsupervised pre-training stage using cycle loss. This spatiotemporal super-resolution approach can upscale data up to 512 times in spatial dimension and 11 times in temporal dimension, which offers scientists an option to reduce data storage.

ISBN: 9798209990000Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Data generation

Deep Learning for Scientific Data Representation and Generation.
LDR:03180nmm a2200361 4500 001 2352198
005 20221118093840.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798209990000
035 $a (MiAaPQ)AAI29061662
035 $a AAI29061662
040 $a MiAaPQ $c MiAaPQ
100 1 $a Han, Jun. $3 1294702
245 1 0 $a Deep Learning for Scientific Data Representation and Generation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 152 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
500 $a Advisor: Wang, Chaoli.
502 $a Thesis (Ph.D.)--University of Notre Dame, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Scientific visualization (SciVis) is one of the core components in supporting fundamental scientific discoveries and engineering designs. For example, scientists perform numerical simulations and produce 3D scalar and vector data to visualize, analyze, and understand various kinds of natural phenomena, such as climate change and star formation. However, the cost of these simulations is expensive when time, ensemble, and multivariate are involved and the scientific data are presented in diverse forms including streamline, pathline, stream surface, volume, and isosurface. A core problem in SciVis is how to efficiently and effectively produce and analyze these diversified data. In this dissertation, I develop novel deep learning methods to enable more effective and efficient frameworks for scientific data representation and generation.In scientific data representation, I propose a unified framework that processes both streamlines and stream surfaces through auto-encoder decoder structure. Moreover, I build an interface that allows users to explore the relationships between the learned features and visual representations. I also utilize geometric deep learning (e.g., graph neural network) to extract node-level and surface-level features in an unsupervised fashion for node clustering and surface selection tasks. In scientific data generation, I introduce a comprehensive pipeline for variable selection and translation through feature learning, translation graph construction, and variable translation. This framework can serve as a data extrapolation and compression solution to reduce simulation costs. Besides, I develop an end-to-end generative framework that can synthesize spatiotemporal super-resolution volumes with high fidelity. Further, to improve network generalization, I propose an unsupervised pre-training stage using cycle loss. This spatiotemporal super-resolution approach can upscale data up to 512 times in spatial dimension and 11 times in temporal dimension, which offers scientists an option to reduce data storage.
590 $a School code: 0165.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Information science. $3 554358
653 $a Data generation
653 $a Data representation
653 $a Deep learning
653 $a Scientific visualization
690 $a 0984
690 $a 0800
690 $a 0723
710 2 $a University of Notre Dame. $b Computer Science and Engineering. $3 3553652
773 0 $t Dissertations Abstracts International $g 83-10B.
790 $a 0165
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29061662