arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.14760hep-phcs.LG
收藏

通过机器学习和Physics-Informed Neural Networks推进物理数据分析

Advancing Physics Data Analysis through Machine Learning and Physics-Informed Neural Networks

Institute of Informatics and Telecommunications, National Centre for Scientific Research “Demokritos”(德谟克里特国家科学研究中心信息学与电信研究所);School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens(雅典国立技术大学农村、测量与地理信息工程学院)

Vasileios Vatellis

AI总结:

本研究评估多种机器学习算法与Physics-Informed Neural Networks在粒子物理二元分类任务中的表现,发现XGBoost计算高效,而PINN准确性更高但耗时更长,揭示了计算效率与模型复杂性间的权衡。

摘要:

在一个日益关注绿色计算和可解释AI的时代,重新审视理论和现象学粒子物理学中的传统方法至关重要。本项目评估了多种机器学习(ML)算法——包括Nearest Neighbors、Decision Trees、Random Forest、AdaBoost、Naive Bayes、Quadratic Discriminant Analysis (QDA)和XGBoost——以及标准神经网络和一种新颖的Physics-Informed Neural Network (PINN)用于物理数据分析。我们将这些技术应用于一个二元分类任务,该任务基于Higgs观测量和基本参数来区分模拟场景的实验可行性。通过这项全面的分析,我们旨在展示每个模型在二元分类任务中的能力和计算效率,从而为将ML和Deep Neural Networks (DNNs)整合到物理研究中的持续讨论做出贡献。在本研究中,XGBoost因其速度和有效性成为评估的机器学习算法中的首选,特别是在数据集有限的计算初始阶段。然而,虽然标准Neural Networks和Physics-Informed Neural Networks (PINNs)在准确性和遵循物理定律方面表现出更优的性能,但它们需要更多的计算时间。这些发现强调了计算效率与模型复杂性之间的权衡。

英文摘要:

In an era increasingly focused on green computing and explainable AI, revisiting traditional approaches in theoretical and phenomenological particle physics is paramount. This project evaluates various machine learning (ML) algorithms-including Nearest Neighbors, Decision Trees, Random Forest, AdaBoost, Naive Bayes, Quadratic Discriminant Analysis (QDA), and XGBoost-alongside standard neural networks and a novel Physics-Informed Neural Network (PINN) for physics data analysis. We apply these techniques to a binary classification task that distinguishes the experimental viability of simulated scenarios based on Higgs observables and essential parameters. Through this comprehensive analysis, we aim to showcase the capabilities and computational efficiency of each model in binary classification tasks, thereby contributing to the ongoing discourse on integrating ML and Deep Neural Networks (DNNs) into physics research. In this study, XGBoost emerged as the preferred choice among the evaluated machine learning algorithms for its speed and effectiveness, especially in the initial stages of computation with limited datasets. However, while standard Neural Networks and Physics-Informed Neural Networks (PINNs) demonstrated superior performance in terms of accuracy and adherence to physical laws, they require more computational time. These findings underscore the trade-offs between computational efficiency and model sophistication.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑