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 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Physics-Informed Neural Networks for...

Inbaraj, Alice,

FindBook

Google Book

Amazon

博客來

Physics-Informed Neural Networks for Trajectory Prediction and Uncertainty Quantification in Urban Air Mobility /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Physics-Informed Neural Networks for Trajectory Prediction and Uncertainty Quantification in Urban Air Mobility // Alice Inbaraj.
作者:	Inbaraj, Alice,
面頁冊數:	1 electronic resource (61 pages)
附註:	Source: Masters Abstracts International, Volume: 86-07.
Contained By:	Masters Abstracts International86-07.
標題:	Aerospace engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31839311
ISBN:	9798302828699

Physics-Informed Neural Networks for Trajectory Prediction and Uncertainty Quantification in Urban Air Mobility /
Inbaraj, Alice,

Physics-Informed Neural Networks for Trajectory Prediction and Uncertainty Quantification in Urban Air Mobility /Alice Inbaraj. - 1 electronic resource (61 pages)

Source: Masters Abstracts International, Volume: 86-07.

Accurate prediction of trajectories is a critical challenge in many fields including aerospace, robotics and autonomous systems. This project focuses on Physics-Informed Neural Networks (PINs) as an approach to predict trajectories and quantify uncertainties in Urban Air Mobility (UAM). We develop and train a PINN model using trajectory data collected from a NASA Generic UAM model, integrating physics laws directly into the training process which ensures that the predictions align with the system dynamics, addressing the limitations of traditional neural networks. The results demonstrate that the PINN model not only achieves high accuracy in trajectory prediction but also provided robust uncertainty quantification, offering insights into prediction confidence. By embedding physics constraints into the learning framework, the PINN enhances interpretability and reliability, making it particularly suitable for safety-critical UAM applications. A comparative analysis with traditional neural networks (NNs) and Gaussian Mixture Regression (GMR) reveals that while GMR captures overall trajectory trends effectively, the PINN model excels in enforcing physics consistency and delivering superior uncertainty quantification. This study underscores the potential of PINNs in advancing trajectory and uncertainty analysis for UAM scenarios. Future work will focus on integrating PINNs with probabilistic models to enhance prediction accuracy and robustness in complex urban air environments. environments. 

English

ISBN: 9798302828699Subjects--Topical Terms:

1002622
Aerospace engineering.
Subjects--Index Terms:

Accurate prediction

Physics-Informed Neural Networks for Trajectory Prediction and Uncertainty Quantification in Urban Air Mobility /
LDR:02977nmm a22004453i 4500 001 2438767
005 20260727134419.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798302828699
035 $a (MiAaPQD)AAI31839311
035 $a AAI31839311
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Inbaraj, Alice, $e author. $3 3830163
245 1 0 $a Physics-Informed Neural Networks for Trajectory Prediction and Uncertainty Quantification in Urban Air Mobility / $c Alice Inbaraj.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (61 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: Masters Abstracts International, Volume: 86-07.
500 $a Advisors: Chen, Jun Committee members: Popov, Pavel; George, Uduak.
502 $b M.S.A.E. $c San Diego State University $d 2025.
520 $a Accurate prediction of trajectories is a critical challenge in many fields including aerospace, robotics and autonomous systems. This project focuses on Physics-Informed Neural Networks (PINs) as an approach to predict trajectories and quantify uncertainties in Urban Air Mobility (UAM). We develop and train a PINN model using trajectory data collected from a NASA Generic UAM model, integrating physics laws directly into the training process which ensures that the predictions align with the system dynamics, addressing the limitations of traditional neural networks. The results demonstrate that the PINN model not only achieves high accuracy in trajectory prediction but also provided robust uncertainty quantification, offering insights into prediction confidence. By embedding physics constraints into the learning framework, the PINN enhances interpretability and reliability, making it particularly suitable for safety-critical UAM applications. A comparative analysis with traditional neural networks (NNs) and Gaussian Mixture Regression (GMR) reveals that while GMR captures overall trajectory trends effectively, the PINN model excels in enforcing physics consistency and delivering superior uncertainty quantification. This study underscores the potential of PINNs in advancing trajectory and uncertainty analysis for UAM scenarios. Future work will focus on integrating PINNs with probabilistic models to enhance prediction accuracy and robustness in complex urban air environments. environments. 
546 $a English
590 $a School code: 0220
650 4 $a Aerospace engineering. $3 1002622
650 4 $a Engineering. $3 586835
650 4 $a Information technology. $3 532993
650 4 $a Fluid mechanics. $3 528155
650 4 $a Computational physics. $3 3343998
653 $a Accurate prediction
653 $a Physics-Informed Neural Networks
653 $a Neural networks
653 $a Urban Air Mobility
690 $a 0538
690 $a 0489
690 $a 0537
690 $a 0204
690 $a 0216
710 2 $a San Diego State University. $b Aerospace Engineering. $e degree granting institution. $3 3830164
720 1 $a Chen, Jun $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-07.
790 $a 0220
791 $a M.S.A.E.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31839311