arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20959cond-mat.mtrl-sci
收藏

通过主动学习框架确定原子结构

Determining Atomic Structure from Spectroscopy via an Active Learning Framework

Georgia Institute of Technology(佐治亚理工学院)

Ian Slagle, Faisal Alamgir, Victor Fung

AI总结:

ActiveStructOpt通过整合图神经网络与主动学习,高效确定复杂材料的原子结构,优于现有方法。

摘要:

从光谱数据确定原子结构是材料科学的核心问题,但受限于有限的技巧和材料类别,主要由于结构细化的计算成本和复杂性。本文引入了ActiveStructOpt,一个整合图神经网络代理模型与主动学习的一般框架,以高效地确定能够再现目标光谱的候选结构,且计算成本最低。通过X射线对分布函数数据以及更计算密集的X射线吸收近边谱(XANES)和扩展X射线吸收精细结构(EXAFS)模拟的基准测试,证明ActiveStructOpt在不同材料类别中都能可靠地确定与目标光谱高度匹配的结构。在等效计算预算下,ActiveStructOpt优于现有结构确定方法。通过在广泛的可计算光谱技术中实现数据高效、多目标的结构细化,ActiveStructOpt提供了一种灵活且可扩展的复杂材料原子结构确定方法。

英文摘要:

Determining atomic structure from spectroscopic data is central to materials science but remains restricted to a limited set of techniques and material classes, largely due to the computational cost and complexity of structural refinement. Here we introduce ActiveStructOpt, a general framework that integrates graph neural network surrogate models with active learning to efficiently determine candidate structures that reproduce target spectra with minimal computational expenditure. Benchmarking with X-ray pair distribution function data, and with the more computationally demanding simulations of X-ray absorption near-edge spectra (XANES) and extended X-ray absorption fine structure (EXAFS), demonstrate that ActiveStructOpt reliably determines structures that match closely in spectra across diverse materials classes. Under equivalent computational budgets, ActiveStructOpt outperforms existing structure determination methods. By enabling data-efficient, multi-objective structural refinement across a broad range of computable spectroscopic techniques, ActiveStructOpt provides a flexible and extensible approach to atomic structure determination in complex materials.

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。

↑