國立虎尾科技大學 |

Physics-Guided Deep Learning for Dynamics Forecasting.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Physics-Guided Deep Learning for Dynamics Forecasting./
Author:	Wang, Rui.
Description:	1 online resource (138 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
Contained By:	Dissertations Abstracts International85-01B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798379762131

Physics-Guided Deep Learning for Dynamics Forecasting.
Wang, Rui.

Physics-Guided Deep Learning for Dynamics Forecasting. - 1 online resource (138 pages)

Source: Dissertations Abstracts International, Volume: 85-01, Section: B.

Thesis (Ph.D.)--University of California, San Diego, 2023.

Includes bibliographical references

Modeling complex dynamics is a fundamental task in science, such as turbulence modeling and weather forecasting. Physics-based models, which rely on mathematical principles, can accurately predict dynamics but can be computationally intensive and not fully known. Deep Learning provides efficient alternatives to simulating dynamics but it lacks physical consistency and struggles with generalization. Thus, there is a growing need for integrating prior physics knowledge with deep learning to take the best of both types of approaches to better solve scientific problems. Thus, the study of physics-guided DL emerged and has gained great progress. In this thesis, we described the physics-guide DL for dynamics forecasting and presented several approaches to improving the physical consistency, accuracy, and generalization of DL models for dynamics forecasting. The approaches include incorporating prior physical knowledge into the design of model architecture and loss functions for improved physical consistency and accuracy, leveraging model-based meta-learning for improved generalization across heterogeneous domains, simplifying nonlinear dynamics with Koopman theory for improved generalization over temporal distributional shifts, and incorporating symmetries into deep dynamics models for improved generalization across relevant symmetry groups and consistency with conservation laws. In the end, we also summarize the challenges in this field and discuss the emerging opportunities for future research.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379762131Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

AI for ScienceIndex Terms--Genre/Form:

554714
Electronic books.

Physics-Guided Deep Learning for Dynamics Forecasting.
LDR:02902ntm a22004097 4500 001 1146235
005 20240812064348.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379762131
035 $a (MiAaPQ)AAI30421717
035 $a AAI30421717
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wang, Rui. $3 1106713
245 1 0 $a Physics-Guided Deep Learning for Dynamics Forecasting.
264 0 $c 2023
300 $a 1 online resource (138 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
500 $a Advisor: Yu, Rose.
502 $a Thesis (Ph.D.)--University of California, San Diego, 2023.
504 $a Includes bibliographical references
520 $a Modeling complex dynamics is a fundamental task in science, such as turbulence modeling and weather forecasting. Physics-based models, which rely on mathematical principles, can accurately predict dynamics but can be computationally intensive and not fully known. Deep Learning provides efficient alternatives to simulating dynamics but it lacks physical consistency and struggles with generalization. Thus, there is a growing need for integrating prior physics knowledge with deep learning to take the best of both types of approaches to better solve scientific problems. Thus, the study of physics-guided DL emerged and has gained great progress. In this thesis, we described the physics-guide DL for dynamics forecasting and presented several approaches to improving the physical consistency, accuracy, and generalization of DL models for dynamics forecasting. The approaches include incorporating prior physical knowledge into the design of model architecture and loss functions for improved physical consistency and accuracy, leveraging model-based meta-learning for improved generalization across heterogeneous domains, simplifying nonlinear dynamics with Koopman theory for improved generalization over temporal distributional shifts, and incorporating symmetries into deep dynamics models for improved generalization across relevant symmetry groups and consistency with conservation laws. In the end, we also summarize the challenges in this field and discuss the emerging opportunities for future research.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
653 $a AI for Science
653 $a Deep Learning
653 $a Dynamical systems
653 $a Machine learning
653 $a Spatiotemporal modeling
653 $a Symmetry
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, San Diego. $b Computer Science and Engineering. $3 1189479
773 0 $t Dissertations Abstracts International $g 85-01B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30421717 $z click for full text (PQDT)