Rohan S. Adhikari, Sri Vishnuvardhan Reddy Akepati, Matthew R. Carbone, Asritha Polu, Hyeong Jin Kim, Yugang Zhang, Arthi Jayaraman
{"title":"Quantifying dispersity in size and shape of nanoparticles from small-angle scattering data using machine learning based CREASE","authors":"Rohan S. Adhikari, Sri Vishnuvardhan Reddy Akepati, Matthew R. Carbone, Asritha Polu, Hyeong Jin Kim, Yugang Zhang, Arthi Jayaraman","doi":"10.1107/S1600576725005746","DOIUrl":"https://doi.org/10.1107/S1600576725005746","url":null,"abstract":"<p>We use machine learning (ML) enhanced computational reverse engineering analysis of scattering experiments (CREASE) to interpret small-angle X-ray scattering (SAXS) data obtained from a system of nanoparticles without <i>a priori</i> knowledge of their exact shapes (<i>e.g.</i> spheres or ellipsoids), sizes (0.5–50 nm) and distributions. The SAXS measurements yielded three categories of scattering profiles exhibiting `strong', `weak' and `no' features. Diminishing features (<i>e.g.</i> broadening or disappearing peaks) in scattering profiles have always been attributed to the presence of significant dispersity in the system. Such featureless SAXS data are not suitable for traditional analysis using analytical models. If one were to fit a relevant analytical model (<i>e.g.</i> the <i>lmfit</i> analytical model for polydisperse spheres) to these `weak' and `no' SAXS profiles from our nanoparticle systems, one would obtain non-unique interpretations of the data. Relying on electron microscopy to identify the distributions of nanoparticle shapes and sizes is also unfeasible, especially in high-throughput synthesis and characterization loops. In such situations, to identify the distributions of particle sizes and shapes that could be present in the sample, one must rely on methods like ML-CREASE to interpret the data quickly and output all relevant interpretations about the structure present in the system. The ML-CREASE optimization loop takes the experimental scattering profile as input and outputs multiple candidate solutions whose computed scattering profiles match the SAXS profile input. The ML-CREASE method outputs distributions of relevant structural features, such as the volume fraction of the nanoparticles in the system and the mean and standard deviation of the particle size and aspect ratio, assuming a type of distribution (<i>e.g.</i> normal, log-normal) for size and aspect ratio. We find that, for the SAXS profiles analyzed here, accounting for the shape dispersity along with size dispersity of the nanoparticles using ML-CREASE improved the match between the computed scattering profiles and input experimental profiles.</p>","PeriodicalId":48737,"journal":{"name":"Journal of Applied Crystallography","volume":"58 4","pages":"1384-1398"},"PeriodicalIF":2.8,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144774006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xuke Li, Lianlian Fu, Yunhang Liu, Xiaodan Meng, Ming Li, Peiling Ke
{"title":"CorFuncSAXSNet: deep-learning-driven extraction of nanostructural parameters from small-angle X-ray scattering data of polymeric materials","authors":"Xuke Li, Lianlian Fu, Yunhang Liu, Xiaodan Meng, Ming Li, Peiling Ke","doi":"10.1107/S1600576725005047","DOIUrl":"https://doi.org/10.1107/S1600576725005047","url":null,"abstract":"<p>Small-angle X-ray scattering (SAXS) analysis of semi-crystalline polymers remains a labour-intensive process requiring expert interpretation of correlation functions. To address this challenge, we present CorFuncSAXSNet: a deep neural network framework designed to directly predict nanostructural parameters – including lamellar crystalline thickness (dc) and amorphous layer thickness (da) – from 1D raw SAXS curves. Building upon SAXS datasets collected at the Shanghai Synchrotron Radiation Facility's BL19U2 beamline, we developed three neural architectures: a convolutional neural network, a residual network and a <i>q</i>-space attention network. Data augmentation strategies, including Gaussian noise injection and <i>q</i>-shift interpolation, improved model robustness against experimental uncertainties. Cross-validation results demonstrate that all networks achieve mean absolute errors of 0.109–0.112 nm for dc and 0.459–0.499 nm for da. Though amorphous layer predictions at large values exhibit higher errors due to dataset skewness (83.3% of data clustered at 4.5 < dc < 6.5 nm, 5.0 < da < 20.0 nm), our framework enables rapid parameter extraction (<1 s per curve), reducing reliance on manual graphical methods. CorFuncSAXSNet bridges the gap between AI and synchrotron-based structural analysis, establishing a foundation for real-time smart beamline architectures.</p>","PeriodicalId":48737,"journal":{"name":"Journal of Applied Crystallography","volume":"58 4","pages":"1399-1406"},"PeriodicalIF":2.8,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Accurate dynamical simulation of continuous precession electron diffraction tomography","authors":"Zeyue Zhang, Xiaoyu Liu, Yihan Shen, Junliang Sun","doi":"10.1107/S1600576725005333","DOIUrl":"https://doi.org/10.1107/S1600576725005333","url":null,"abstract":"<p>Continuous precession rotation electron diffraction (cPEDT) is a novel method combining continuous goniometer rotation and precession of the incident beam to enhance three-dimensional electron diffraction (3D ED) data completeness and collection efficiency. However, cPEDT remains computationally prohibitive for dynamical refinement due to its intrinsic reciprocal-space oversampling. Herein, we present a MATLAB-based framework implementing golden-ratio shift orientation sampling, achieving convergence within 512 Bloch wave calculations per frame, which is a tenfold reduction compared with conventional protocols. Systematic benchmarking across different 3D ED methods reveals cPEDT's superior robustness with respect to crystal misorientations and self-consistency for intensity integration for kinematical treatment. This article also validates the thickness-inversion theorem, enabling enantiomorph assignment through thickness reversal (<i>t</i> → −<i>t</i>), and the impact of unobserved high-resolution reflections is evaluated to be negligible. Verified by eight representative structures, this work establishes cPEDT's robustness and potential feasibility for dynamical refinement applications.</p>","PeriodicalId":48737,"journal":{"name":"Journal of Applied Crystallography","volume":"58 4","pages":"1234-1248"},"PeriodicalIF":2.8,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
