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 2401.12381cond-mat.soft
收藏

用于解释二维小角散射剖面的散射实验计算逆向工程分析方法 (CREASE-2D)

Computational Reverse Engineering Analysis of Scattering Experiments Method for Interpretation of 2D Small-Angle Scattering Profiles (CREASE-2D)

Sri Vishnuvardhan Reddy Akepati, Nitant Gupta, Arthi Jayaraman

AI总结:

本文提出名为CREASE-2D的新方法,通过遗传算法和XGBoost代理机器学习模型,直接解释二维小角散射剖面I(q,θ)并输出相关结构特征,以帮助研究人员探索软材料的结构各向异性。

摘要:

表征软材料内部的结构多样性是开发面向各种应用的新材料的关键。小角散射 (SAS) 是一种广泛使用的表征技术,可在不同长度尺度上提供软材料的结构信息,通常输出散射强度 I(q) 作为散射波矢的函数,由其大小 q 和方位角 θ 表示。虽然各向同性结构可以通过方位角平均的一维 SAS 剖面来解释,但要理解各向异性的空间排列,必须解释二维 SAS 剖面 I(q,θ)。在本文中,我们提出了一种名为 CREASE-2D 的新方法,该方法直接解释 I(q,θ) 并输出相关的结构特征。CREASE-2D 是“散射实验计算逆向工程分析” (CREASE) 方法的扩展,该方法已成功用于分析各种软材料的一维 SAS 剖面。CREASE 使用遗传算法进行优化,并使用代理机器学习 (ML) 模型快速计算一维“计算”散射剖面,然后在优化过程中将其与实验一维散射剖面进行比较。在超越 CREASE 以解释二维散射剖面的 CREASE-2D 中,我们使用 XGBoost 作为代理 ML 模型,将结构特征与 I(q,θ) 剖面关联起来。CREASE-2D 工作流程能够识别出其计算 I(q,θ) 剖面与输入实验 I(q,θ) 相匹配的结构特征。我们通过使用多种已知结构特征的计算机模拟二维 SAS 剖面作为输入,测试了 CREASE-2D 的性能,并证明 CREASE-2D 能够收敛到正确的结构特征。我们期望该方法对于需要直接解释二维散射剖面以探索结构各向异性的材料研究人员具有重要价值。

英文摘要:

Characterization of structural diversity within soft materials is key for engineering new materials for various applications. Small-angle scattering (SAS) is a widely used characterization technique that provides structural information in soft materials at varying length scales and typically outputs scattered intensity I(q) as a function of the scattered wavevector represented by its magnitude q and azimuthal angle θ. While isotropic structures can be interpreted from azimuthally averaged 1D SAS profile, to understand anisotropic spatial arrangements, one has to interpret the 2D SAS profile, I(q,θ). In this paper, we present a new method called CREASE-2D that interprets I(q,θ) as is and outputs the relevant structural features. CREASE-2D is an extension of the 'computational reverse engineering analysis for scatting experiments' (CREASE) method that has been used successfully to analyze 1D SAS profiles for a variety of soft materials. CREASE uses a genetic algorithm for optimization and a surrogate machine learning (ML) model for fast calculation of 1D 'computed' scattering profiles that are then compared to the experimental 1D scattering profiles during optimization. In CREASE-2D, which goes beyond CREASE in interpretting 2D scattering profiles, we use XGBoost as the surrogate ML model to relate structural features to the I(q,θ) profile. The CREASE-2D workflow identifies the structural features whose computed I(q,θ) profiles match the input experimental I(q,θ). We test the performance of CREASE-2D by using as input a variety of in silico 2D SAS profiles with known structural features and demonstrate that CREASE-2D converges towards their correct structural features. We expect this method will be valuable for materials' researchers who need direct interpretation of 2D scattering profiles to explore structural anisotropy.

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。

↑