Uncertainty Tube Visualization of Particle Trajectories

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Jixian, Ouermi, Timbwaoga Aime Judicael, Han, Mengjiao, Johnson, Chris R.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913997663502336
author Li, Jixian
Ouermi, Timbwaoga Aime Judicael
Han, Mengjiao
Johnson, Chris R.
author_facet Li, Jixian
Ouermi, Timbwaoga Aime Judicael
Han, Mengjiao
Johnson, Chris R.
contents Predicting particle trajectories with neural networks (NNs) has substantially enhanced many scientific and engineering domains. However, effectively quantifying and visualizing the inherent uncertainty in predictions remains challenging. Without an understanding of the uncertainty, the reliability of NN models in applications where trustworthiness is paramount is significantly compromised. This paper introduces the uncertainty tube, a novel, computationally efficient visualization method designed to represent this uncertainty in NN-derived particle paths. Our key innovation is the design and implementation of a superelliptical tube that accurately captures and intuitively conveys nonsymmetric uncertainty. By integrating well-established uncertainty quantification techniques, such as Deep Ensembles, Monte Carlo Dropout (MC Dropout), and Stochastic Weight Averaging-Gaussian (SWAG), we demonstrate the practical utility of the uncertainty tube, showcasing its application on both synthetic and simulation datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13505
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Tube Visualization of Particle Trajectories
Li, Jixian
Ouermi, Timbwaoga Aime Judicael
Han, Mengjiao
Johnson, Chris R.
Machine Learning
Human-Computer Interaction
Predicting particle trajectories with neural networks (NNs) has substantially enhanced many scientific and engineering domains. However, effectively quantifying and visualizing the inherent uncertainty in predictions remains challenging. Without an understanding of the uncertainty, the reliability of NN models in applications where trustworthiness is paramount is significantly compromised. This paper introduces the uncertainty tube, a novel, computationally efficient visualization method designed to represent this uncertainty in NN-derived particle paths. Our key innovation is the design and implementation of a superelliptical tube that accurately captures and intuitively conveys nonsymmetric uncertainty. By integrating well-established uncertainty quantification techniques, such as Deep Ensembles, Monte Carlo Dropout (MC Dropout), and Stochastic Weight Averaging-Gaussian (SWAG), we demonstrate the practical utility of the uncertainty tube, showcasing its application on both synthetic and simulation datasets.
title Uncertainty Tube Visualization of Particle Trajectories
topic Machine Learning
Human-Computer Interaction
url https://arxiv.org/abs/2508.13505