scholarly journals Small Angle Scattering Data Analysis Assisted by Machine Learning Methods

MRS Advances ◽  
2020 ◽  
Vol 5 (29-30) ◽  
pp. 1577-1584
Author(s):  
Changwoo Do ◽  
Wei-Ren Chen ◽  
Sangkeun Lee
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Small Angle ◽  
Confusion Matrix ◽  
Small Angle Scattering ◽  
Scattering Data ◽  
Search Spaces ◽  
Angle Scattering ◽  
Analysis Workflow ◽  
The Right

ABSTRACTSmall angle scattering (SAS) is a widely used technique for characterizing structures of wide ranges of materials. For such wide ranges of applications of SAS, there exist a large number of ways to model the scattering data. While such analysis models are often available from various suites of SAS data analysis software packages, selecting the right model to start with poses a big challenge for beginners to SAS data analysis. Here, we present machine learning (ML) methods that can assist users by suggesting scattering models for data analysis. A series of one-dimensional scattering curves have been generated by using different models to train the algorithms. The performance of the ML method is studied for various types of ML algorithms, resolution of the dataset, and the number of the dataset. The degree of similarities among selected scattering models is presented in terms of the confusion matrix. The scattering model suggestions with prediction scores provide a list of scattering models that are likely to succeed. Therefore, if implemented with extensive libraries of scattering models, this method can speed up the data analysis workflow by reducing search spaces for appropriate scattering models.

scholarly journals SASfit: a tool for small-angle scattering data analysis using a library of analytical expressions

2015 ◽  
Vol 48 (5) ◽  
pp. 1587-1598 ◽  
Author(s):  
Ingo Breßler ◽  
Joachim Kohlbrecher ◽  
Andreas F. Thünemann
Keyword(s):  
Data Analysis ◽  
Reference Material ◽  
Small Angle ◽  
Fractal Model ◽  
Small Angle Scattering ◽  
Scattering Data ◽  
Model Parameters ◽  
Angle Scattering ◽  
Confidence Assessment ◽  
Analysis Workflow

SASfitis one of the mature programs for small-angle scattering data analysis and has been available for many years. This article describes the basic data processing and analysis workflow along with recent developments in theSASfitprogram package (version 0.94.6). They include (i) advanced algorithms for reduction of oversampled data sets, (ii) improved confidence assessment in the optimized model parameters and (iii) a flexible plug-in system for custom user-provided models. A scattering function of a mass fractal model of branched polymers in solution is provided as an example for implementing a plug-in. The newSASfitrelease is available for major platforms such as Windows, Linux and MacOS. To facilitate usage, it includes comprehensive indexed documentation as well as a web-based wiki for peer collaboration and online videos demonstrating basic usage. The use ofSASfitis illustrated by interpretation of the small-angle X-ray scattering curves of monomodal gold nanoparticles (NIST reference material 8011) and bimodal silica nanoparticles (EU reference material ERM-FD-102).

scholarly journals Classifying and analyzing small-angle scattering data using weighted k nearest neighbors machine learning techniques

2020 ◽  
Vol 53 (2) ◽  
pp. 326-334
Author(s):  
Richard K. Archibald ◽  
Mathieu Doucet ◽  
Travis Johnston ◽  
Steven R. Young ◽  
Erika Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Small Angle ◽  
Structural Parameters ◽  
Nearest Neighbors ◽  
Small Angle Scattering ◽  
Machine Learning Techniques ◽  
Stochastic Gradient Descent ◽  
Scattering Data ◽  
Gradient Descent Method ◽  
Angle Scattering

A consistent challenge for both new and expert practitioners of small-angle scattering (SAS) lies in determining how to analyze the data, given the limited information content of said data and the large number of models that can be employed. Machine learning (ML) methods are powerful tools for classifying data that have found diverse applications in many fields of science. Here, ML methods are applied to the problem of classifying SAS data for the most appropriate model to use for data analysis. The approach employed is built around the method of weighted k nearest neighbors (wKNN), and utilizes a subset of the models implemented in the SasView package (https://www.sasview.org/) for generating a well defined set of training and testing data. The prediction rate of the wKNN method implemented here using a subset of SasView models is reasonably good for many of the models, but has difficulty with others, notably those based on spherical structures. A novel expansion of the wKNN method was also developed, which uses Gaussian processes to produce local surrogate models for the classification, and this significantly improves the classification accuracy. Further, by integrating a stochastic gradient descent method during post-processing, it is possible to leverage the local surrogate model both to classify the SAS data with high accuracy and to predict the structural parameters that best describe the data. The linking of data classification and model fitting has the potential to facilitate the translation of measured data into results for both novice and expert practitioners of SAS.

Small-angle scattering data analysis for dense polydisperse systems: the FLAC program

2000 ◽  
Vol 133 (1) ◽  
pp. 66-75 ◽  
Author(s):  
Flavio Carsughi ◽  
Achille Giacometti ◽  
Domenico Gazzillo
Keyword(s):  
Data Analysis ◽  
Small Angle ◽  
Small Angle Scattering ◽  
Scattering Data ◽  
Angle Scattering

scholarly journals ATSAS 2.1 – towards automated and web-supported small-angle scattering data analysis

2007 ◽  
Vol 40 (s1) ◽  
pp. s223-s228 ◽  
Author(s):  
Maxim V. Petoukhov ◽  
Peter V. Konarev ◽  
Alexey G. Kikhney ◽  
Dmitri I. Svergun
Keyword(s):  
Data Analysis ◽  
Small Angle ◽  
Small Angle Scattering ◽  
Scattering Data ◽  
Angle Scattering

Quantification of the information in small-angle scattering data

2014 ◽  
Vol 47 (6) ◽  
pp. 2000-2010 ◽  
Author(s):  
Martin Cramer Pedersen ◽  
Steen Laugesen Hansen ◽  
Bo Markussen ◽  
Lise Arleth ◽  
Kell Mortensen
Keyword(s):  
Data Analysis ◽  
Neutron Scattering ◽  
Ray Tracing ◽  
Information Content ◽  
Small Angle ◽  
Small Angle Scattering ◽  
Scattering Data ◽  
X Ray ◽  
Angle Scattering ◽  
Wide Range

Small-angle X-ray and neutron scattering have become increasingly popular owing to improvements in instrumentation and developments in data analysis, sample handling and sample preparation. For some time, it has been suggested that a more systematic approach to the quantification of the information content in small-angle scattering data would allow for a more optimal experiment planning and a more reliable data analysis. In the present article, it is shown how ray-tracing techniques in combination with a statistically rigorous data analysis provide an appropriate platform for such a systematic quantification of the information content in scattering data. As examples of applications, it is shown how the exposure time at different instrumental settings or contrast situations can be optimally prioritized in an experiment. Also, the gain in information by combining small-angle X-ray and neutron scattering is assessed. While solution small-angle scattering data of proteins and protein–lipid complexes are used as examples in the present case study, the approach is generalizable to a wide range of other samples and experimental techniques. The source code for the algorithms and ray-tracing components developed for this study has been made available on-line.

Sign in / Sign up

Export Citation Format

Share Document