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 2409.08832cs.LG
收藏

KAN能否(重新)发现直接驱动激光聚变的预测模型?

Can Kans (re)discover predictive models for Direct-Drive Laser Fusion?

University of Rochester(罗切斯特大学);Laboratory for Laser Energetics(激光能量学实验室)

Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Aarne Lees, Christopher Kanan

AI总结:

针对激光聚变领域数据少、建模难的问题,研究提出用KAN替代物理信息学习构建预测模型,对比实验验证其在数据匮乏的物理场景中兼具高精度与可解释性的潜力。

摘要:

激光聚变领域因问题复杂度高、训练数据有限,为机器学习方法提供了独特且具挑战性的预测建模应用场景。过去,采用预设函数形式、归纳偏置和物理信息学习(Physics-informed Learning,PIL)方案的数据驱动方法,已成功实现了符合物理预期的理想泛化能力与模型可解释性。然而在复杂的多物理应用领域中,如何构建架构偏置或判别性惩罚项并非总是显而易见。本研究聚焦于高功率激光驱动的核聚变能源领域,提出将柯尔莫哥洛夫-阿诺德网络(Kolmogorov-Arnold Networks,KANs)作为PIL的替代方案,用于开发一种新型数据驱动预测模型,该模型兼具高预测精度与物理可解释性。我们将基于KAN的模型、结合PIL的MLP以及基线MLP模型,在泛化能力和可解释性方面与领域专家推导的符号回归模型进行了对比。通过在这一高物理复杂度领域的实证研究,我们表明KANs在为数据匮乏的物理应用开发预测模型时具备潜在优势。

英文摘要:

The domain of laser fusion presents a unique and challenging predictive modeling application landscape for machine learning methods due to high problem complexity and limited training data. Data-driven approaches utilizing prescribed functional forms, inductive biases and physics-informed learning (PIL) schemes have been successful in the past for achieving desired generalization ability and model interpretation that aligns with physics expectations. In complex multi-physics application domains, however, it is not always obvious how architectural biases or discriminative penalties can be formulated. In this work, focusing on nuclear fusion energy using high powered lasers, we present the use of Kolmogorov-Arnold Networks (KANs) as an alternative to PIL for developing a new type of data-driven predictive model which is able to achieve high prediction accuracy and physics interpretability. A KAN based model, a MLP with PIL, and a baseline MLP model are compared in generalization ability and interpretation with a domain expert-derived symbolic regression model. Through empirical studies in this high physics complexity domain, we show that KANs can potentially provide benefits when developing predictive models for data-starved physics applications.

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。

↑