Results for “methods: data analysis” — Page 36

DOE OSTI2016

TH-A-BRC-03: AAPM TG218: Measurement Methods and Tolerance Levels for Patient-Specific IMRT Verification QA

AAPM TG-135U1 QA for Robotic Radiosurgery - Sonja Dieterich Since the publication of AAPM TG-135 in 2011, the technology of robotic radiosurgery has rapidly developed. AAPM TG-135U1 will provide recommendations on the clinical practice for using the IRIS collimator, fiducial-less real-time motion tracking, and Monte Carlo based treatment planning. In addition, it will summarize currently available literature about uncertainties. Learning Objectives: Understand the progression of technology since the first TG publication Learn which new QA procedures should be implemented for new technologies Be familiar with updates to clinical practice guidelines AAPM TG-178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance - Steven Goetsch Purpose: AAPM Task Group 178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance was formed in August, 2008. The Task Group has 12 medical physicists, two physicians and two consultants. Methods: A round robin dosimetry intercomparison of proposed ionization chambers, electrometer and dosimetry phantoms was conducted over a 15 month period in 2011 and 2012 (Med Phys 42, 11, Nov, 2015). The data obtained at 9 institutions (with ten different Elekta Gamma Knife units) was analyzed by the lead author using several protocols. Results: The most consistent results were obtained using the Elekta ABS 16cm diameter phantom, with the TG-51 protocol modified as recommended by Alfonso et al (Med Phys 35, 11, Nov 2008). A key white paper (Med Phys, in press) sponsored by Elekta Corporation, was used to obtain correction factors for the ionization chambers and phantoms used in this intercomparison. Consistent results were obtained for both Elekta Gamma Knife Model 4C and Gamma Knife Perfexion units as measured with each of two miniature ionization chambers. Conclusion: The full report gives clinical history and background of gamma stereotactic radiosurgery, clinical examples and history, quality assurance recommendations and outline of possible dosimetry protocols. The report will be reviewed by the AAPM Working Group on Recommendations for Radiotherapy External Beam Quality Assurance and then by the AAPM Science Council before publication in Medical Physics Survey of possible calibration protocols for calibration of Gamma Stereotactic Radiosurgery (GSR) devices Overview of modern Quality Assurance techniques for GSR AAPM TG-218 Tolerance Levels and Methodologies for IMRT Verification QA - Moyed Miften Patient-specific IMRT QA measurement is a process designed to identify discrepancies between calculated and delivered doses. Error tolerance limits are not well-defined or consistently applied across centers. The AAPM TG-218 report has been prepared to improve the understanding and consistency of this process by providing recommendations for methodologies and tolerance limits in patient-specific IMRT QA. Learning Objectives: Review measurement methods and methodologies for absolute dose verification Provide recommendations on delivery methods, data interpretation, the use of analysis routines and choice of tolerance limits for IMRT QA Sonja Dieterich has a research agreement with Sun Nuclear Inc. Steven Goetsch is a part-time consultant for Elekta.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Iterative Bragg peak removal on X-ray absorption spectra with automatic intensity correction

This study introduces a novel iterative Bragg peak removal with automatic intensity correction (IBR-AIC) methodology for X-ray absorption spectroscopy (XAS), specifically addressing the challenge of Bragg peak interference in the analysis of crystalline materials. The approach integrates experimental adjustments and sophisticated post-processing, including an iterative algorithm for robust calculation of the scaling factor of the absorption coefficients and efficient elimination of the Bragg peaks, a common obstacle in accurately interpreting XAS data, particularly in crystalline samples. The method was thoroughly evaluated on dilute catalysts and thin films, with fluorescence mode and large-angle rotation. The results underscore the technique's effectiveness, adaptability and substantial potential in improving the precision of XAS data analysis. While demonstrating significant promise, the method does have limitations related to signal-to-noise ratio sensitivity and the necessity for meticulous angle selection during experimentation. Overall, IBR-AIC represents a significant advancement in XAS, offering a pragmatic solution to Bragg peak contamination challenges, thereby expanding the applications of XAS in understanding complex materials under diverse experimental conditions.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2021

Developing High-Resolution Constrained Variational Analysis of Vertical Velocity and Advective Tendencies within the Range of ARM Scanning Radars at the SGP

Research progress has been made in two areas. One is about the incorporation of the ARM variationally constrained objective analysis method into the WRF GSI data assimilation system. The other is the development of high resolution ARM data and its applications. Specially, we developed a new data assimilation algorithm by adding dynamical constraints to the WRF GSI data assimilation system using hybrid ensemble variational system to derive 3-D fields of atmospheric dynamics and thermodynamics over the ARM SGP sites. We also developed 4x4 km high-resolution constrained variational analysis data over the SGP during the PECAN and made them available to the community. Details are in the attached report.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2016

TH-A-BRC-00: New Task Groups for External Beam QA: An Overview

AAPM TG-135U1 QA for Robotic Radiosurgery - Sonja Dieterich Since the publication of AAPM TG-135 in 2011, the technology of robotic radiosurgery has rapidly developed. AAPM TG-135U1 will provide recommendations on the clinical practice for using the IRIS collimator, fiducial-less real-time motion tracking, and Monte Carlo based treatment planning. In addition, it will summarize currently available literature about uncertainties. Learning Objectives: Understand the progression of technology since the first TG publication Learn which new QA procedures should be implemented for new technologies Be familiar with updates to clinical practice guidelines AAPM TG-178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance - Steven Goetsch Purpose: AAPM Task Group 178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance was formed in August, 2008. The Task Group has 12 medical physicists, two physicians and two consultants. Methods: A round robin dosimetry intercomparison of proposed ionization chambers, electrometer and dosimetry phantoms was conducted over a 15 month period in 2011 and 2012 (Med Phys 42, 11, Nov, 2015). The data obtained at 9 institutions (with ten different Elekta Gamma Knife units) was analyzed by the lead author using several protocols. Results: The most consistent results were obtained using the Elekta ABS 16cm diameter phantom, with the TG-51 protocol modified as recommended by Alfonso et al (Med Phys 35, 11, Nov 2008). A key white paper (Med Phys, in press) sponsored by Elekta Corporation, was used to obtain correction factors for the ionization chambers and phantoms used in this intercomparison. Consistent results were obtained for both Elekta Gamma Knife Model 4C and Gamma Knife Perfexion units as measured with each of two miniature ionization chambers. Conclusion: The full report gives clinical history and background of gamma stereotactic radiosurgery, clinical examples and history, quality assurance recommendations and outline of possible dosimetry protocols. The report will be reviewed by the AAPM Working Group on Recommendations for Radiotherapy External Beam Quality Assurance and then by the AAPM Science Council before publication in Medical Physics Survey of possible calibration protocols for calibration of Gamma Stereotactic Radiosurgery (GSR) devices Overview of modern Quality Assurance techniques for GSR AAPM TG-218 Tolerance Levels and Methodologies for IMRT Verification QA - Moyed Miften Patient-specific IMRT QA measurement is a process designed to identify discrepancies between calculated and delivered doses. Error tolerance limits are not well-defined or consistently applied across centers. The AAPM TG-218 report has been prepared to improve the understanding and consistency of this process by providing recommendations for methodologies and tolerance limits in patient-specific IMRT QA. Learning Objectives: Review measurement methods and methodologies for absolute dose verification Provide recommendations on delivery methods, data interpretation, the use of analysis routines and choice of tolerance limits for IMRT QA Sonja Dieterich has a research agreement with Sun Nuclear Inc. Steven Goetsch is a part-time consultant for Elekta.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2016

TH-A-BRC-02: AAPM TG-178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance

AAPM TG-135U1 QA for Robotic Radiosurgery - Sonja Dieterich Since the publication of AAPM TG-135 in 2011, the technology of robotic radiosurgery has rapidly developed. AAPM TG-135U1 will provide recommendations on the clinical practice for using the IRIS collimator, fiducial-less real-time motion tracking, and Monte Carlo based treatment planning. In addition, it will summarize currently available literature about uncertainties. Learning Objectives: Understand the progression of technology since the first TG publication Learn which new QA procedures should be implemented for new technologies Be familiar with updates to clinical practice guidelines AAPM TG-178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance - Steven Goetsch Purpose: AAPM Task Group 178 Gamma Stereotactic Radiosurgery Dosimetry and Quality Assurance was formed in August, 2008. The Task Group has 12 medical physicists, two physicians and two consultants. Methods: A round robin dosimetry intercomparison of proposed ionization chambers, electrometer and dosimetry phantoms was conducted over a 15 month period in 2011 and 2012 (Med Phys 42, 11, Nov, 2015). The data obtained at 9 institutions (with ten different Elekta Gamma Knife units) was analyzed by the lead author using several protocols. Results: The most consistent results were obtained using the Elekta ABS 16cm diameter phantom, with the TG-51 protocol modified as recommended by Alfonso et al (Med Phys 35, 11, Nov 2008). A key white paper (Med Phys, in press) sponsored by Elekta Corporation, was used to obtain correction factors for the ionization chambers and phantoms used in this intercomparison. Consistent results were obtained for both Elekta Gamma Knife Model 4C and Gamma Knife Perfexion units as measured with each of two miniature ionization chambers. Conclusion: The full report gives clinical history and background of gamma stereotactic radiosurgery, clinical examples and history, quality assurance recommendations and outline of possible dosimetry protocols. The report will be reviewed by the AAPM Working Group on Recommendations for Radiotherapy External Beam Quality Assurance and then by the AAPM Science Council before publication in Medical Physics Survey of possible calibration protocols for calibration of Gamma Stereotactic Radiosurgery (GSR) devices Overview of modern Quality Assurance techniques for GSR AAPM TG-218 Tolerance Levels and Methodologies for IMRT Verification QA - Moyed Miften Patient-specific IMRT QA measurement is a process designed to identify discrepancies between calculated and delivered doses. Error tolerance limits are not well-defined or consistently applied across centers. The AAPM TG-218 report has been prepared to improve the understanding and consistency of this process by providing recommendations for methodologies and tolerance limits in patient-specific IMRT QA. Learning Objectives: Review measurement methods and methodologies for absolute dose verification Provide recommendations on delivery methods, data interpretation, the use of analysis routines and choice of tolerance limits for IMRT QA Sonja Dieterich has a research agreement with Sun Nuclear Inc. Steven Goetsch is a part-time consultant for Elekta.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Machine Learning in the Context of Laser-Induced Breakdown Spectroscopy

The integration of machine learning (ML) with Laser-Induced Breakdown Spectroscopy (LIBS) has revolutionized the analytical capabilities of LIBS. The combi-nation of both methods enables more accurate and efficient data analysis. While LIBS itself is a powerful technique for elemental analysis, the vast amount of spectral data it generates can be hard to interpret. Machine learning addresses these challenges by leveraging algorithms that can learn from data, identify patterns, and make predictions without explicit programming for the interpretation of each specific task. In LIBS application, ML techniques are used to enhance various analytical processes. For example, ML algorithms can classify materials based on their spectral fingerprints, predict the concentration of elements in a sample, and identify underlying patterns within complex datasets. Here, this application improves the precision of LIBS analyses while significantly reducing the time required for data processing and interpretation. In this chapter, the fundamental concepts of ML will be discussed first. Following this, the process of data splitting and the importance of feature selection will be examined. Several machine learning methods will then be closely examined, exploring how each can benefit LIBS analysis and highlighting their respective advantages and shortcomings. This structured approach will provide a comprehensive understanding of the integration of ML in the context of LIBS analysis.

47 OTHER INSTRUMENTATION↗

DOE OSTI2023

TopoSZ: Preserving Topology in Error-Bounded Lossy Compression

Existing error-bounded lossy compression techniques control the pointwise error during compression to guarantee the integrity of the decompressed data. However, they typically do not explicitly preserve the topological features in data. When performing post hoc analysis with decompressed data using topological methods, preserving topology in the compression process to obtain topologically consistent and correct scientific insights is desirable. In this paper, we introduce TopoSZ, an error-bounded lossy compression method that preserves the topological features in 2D and 3D scalar fields. Specifically, we aim to preserve the types and locations of local extrema as well as the level set relations among critical points captured by contour trees in the decompressed data. The main idea is to derive topological constraints from contour-tree-induced segmentation from the data domain, and incorporate such constraints with a customized error-controlled quantization strategy from the SZ compressor (version 1.4). In conclusion, our method allows users to control the pointwise error and the loss of topological features during the compression process with a global error bound and a persistence threshold.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

Outsourced probe data effectiveness on signalized arterials

This paper presents results of an I-95 Corridor Coalition sponsored project to assess the ability of outsourced vehicle probe data to provide accurate travel time on signalized roadways for the purposes of real-time operations as well as performance measures. The quality of outsourced probe data on freeways has led many departments of transportation to consider such data for arterial performance monitoring. From April 2013 through June of 2014, the University of Maryland Center for Advanced Transportation Technology gathered travel times from several arterial corridors within the mid-Atlantic region using Bluetooth traffic monitoring (BTM) equipment, and compared these travel times with the data reported to the I95 Vehicle Probe Project (VPP) from an outsourced probe data vendor. The analysis consisted of several methodologies: (1) a traditional analysis that used precision and bias speed metrics; (2) a slowdown analysis that quantified the percentage of significant traffic disruptions accurately captured in the VPP data; (3) a sampled distribution method that uses overlay methods to enhance and analyze recurring congestion patterns. (4) Last, the BTM and VPP data from each 24-hour period of data collection were reviewed by the research team to assess the extent to which VPP captured the nature of the traffic flow. Based on the analysis, probe data is recommended only on arterial roadways with signal densities (measured in signals per mile) up to one, and it should be tested and used with caution for signal densities between one and two, and is not recommended when signal density exceeds two.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2016

Appalachian Basin Play Fairway Analysis Analyses and Results

*This submission updates a 2015 submission for the utilization analysis (https://gdr.openei.org/submissions/623)* The files document the analysis of utilization potential in support of Phase 1 Low Temperature Geothermal Play Fairway Analysis for the Appalachian Basin. This 2016 submission includes data pertinent to the methods and results of an analysis of the Surface Levelized Cost of Heat (SLCOH) for US Census Bureau 'Places' within the study area. The SLCOHis was calculated using a modification of a program called GEOPHIRES, available at http://koenraadbeckers.net/geophires/index.php. In addition to calculating SLCOH, this task also identified many industrial sites that may be prospects for use of a geothermal district heating system, based on their size and industry, rather than on the SLCOH. An industry sorted listing and maps of the sites have been plotted as a layer onto different iterations of maps combining the three geologic risk factors (Thermal Quality, Natural Reservoir Quality, and Risk of Seismicity). In addition, a shapefile of the industrial sites is also included with 7 associated files. Supporting files are also supplied.

15 GEOTHERMAL ENERGY↗

DOE OSTI2018

Probabilistic Economic Valuation of Safety Margin Management

The goal of this project was to explore a new methodology for evaluation of potential safety margin upgrades to add a new instrument to the Risk Informed Safety Margin Characterization (RISMC) toolkit. To this end, the RAVEN code developed by the Idaho National Laboratory was used to perform a cost-benefit analysis of several potential power plant safety upgrades to compare the material cost of the upgrades with the probabilistic benefit of avoiding accident scenario consequences to find the most cost-effective safety upgrades. By coupling RAVEN to MELCOR to drive Monte-Carlo method stochastic parameter analysis and using data from existing nuclear codes, as well as MELCOR’s radionuclide relocation tracking capabilities, the radionuclide release source term activity in a severe accident scenario can be estimated. Severe Accident Mitigation upgrades were benchmarked against the Hardened Containment Ventilation upgrade mandated by the USNRC for Mk1 BWRs using dollars spent per Curie of release prevented as a metric by which to evaluate the economic efficacy of the upgrades. Additionally, Fault Tree/Event Tree-based analyses were performed to compare older methods of evaluation to the methodology pioneered in this work, and Monthly Operating Report (MORP) outage data was analyzed for insights into power plant outage optimization and reduction.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

DOE OSTI2024

PV-Finder: ML Based Algorithm for Primary Vertex Identification

he CMS detector at the High-Luminosity Large Hadron Collider (HL-LHC) will operate in challenging conditions with expected pile-up of up to 200 collisions per bunch crossing, necessitating the development of a more resilient primary vertex (PV) reconstruction method to ensure the integrity of data analysis and the efficiency of the CMS triggering system. This contribution describes preliminary studies on a new ML based PV-Finder method for PV identification. The method is based on a model trained using Kernel Density Estimations (KDEs) derived from the positions of reconstructed tracks at the beamline, incorporating uncertainties from track parameters. It also utilizes target histograms, modeled as Gaussian distributions centered on the actual ground truth values of specific primary vertices.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2022

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2021

Illustrated formalisms for total scattering data: a guide for new practitioners

The total scattering method is the simultaneous study of both the real- and reciprocal-space representations of diffraction data. While conventional Bragg-scattering analysis (employing methods such as Rietveld refinement) provides insight into the average structure of the material, pair distribution function (PDF) analysis allows for a more focused study of the local atomic arrangement of a material. Generically speaking, a PDF is generated by Fourier transforming the total measured reciprocal-space diffraction data (Bragg and diffuse) into a real-space representation. However, the details of the transformation employed and, by consequence, the resultant appearance and weighting of the real-space representation of the system can vary between different research communities. As the worldwide total scattering community continues to grow, these subtle differences in nomenclature and data representation have led to conflicting and confusing descriptions of how the PDF is defined and calculated. This paper provides a consistent derivation of many of these different forms of the PDF and the transformations required to bridge between them. Some general considerations and advice for total scattering practitioners in selecting and defining the appropriate choice of PDF in their own research are presented. This contribution aims to benefit people starting in the field or trying to compare their results with those of other researchers.

36 MATERIALS SCIENCE↗

DOE OSTI2019

Atom Probe Tomography Interlaboratory Study on Clustering Analysis in Experimental Data Using the Maximum Separation Distance Approach

We summarize the findings from an interlaboratory study conducted between ten international research groups and investigate the use of the commonly used maximum separation distance and local concentration thresholding methods for solute clustering quantification. The study objectives are: to bring clarity to the range of applicability of the methods; identify existing and/or needed modifications; and interpretation of past published data. Participants collected experimental data from a proton-irradiated 304 stainless steel and analyzed Cu-rich and Ni–Si rich clusters. The datasets were also analyzed by one researcher to clarify variability originating from different operators. The Cu distribution fulfills the ideal requirements of the maximum separation method (MSM), namely a dilute matrix Cu concentration and concentrated Cu clusters. This enabled a relatively tight distribution of the cluster number density among the participants. By contrast, the group analysis of the Ni–Si rich clusters by the MSM was complicated by a high Ni matrix concentration and by the presence of Si-decorated dislocations, leading to larger variability among researchers. While local concentration filtering could, in principle, tighten the results, the cluster identification step inevitably maintained a high scatter. Recommendations regarding reporting, selection of analysis method, and expected variability when interpreting published data are discussed.

APT, Round Robin Studies, atom probe tomography, c↗

DOE OSTI2026

Micro-architected material design for mechanical response

Rapid advances in additive manufacturing (AM) have enabled the creation of micro-architected materials—also known as mechanical metamaterials—with unprecedented control over fine-scale geometries and arrangements of multiple material constituents. These “materials” can achieve unique and extraordinary effective mechanical properties through their complex architectures rather than composition alone. A key challenge is to design for these bespoke effective mechanical responses within the constraints of available AM techniques (i.e., given a set of desired effective properties), identify a (often nonunique) micro-architecture and selection of material constituents that achieves them. Two main strategies have emerged. Gradient-based methods use sensitivity analysis to iteratively refine candidate designs, while data-driven methods learn micro-architecture-constituent relationships from existing examples to propose new designs. This article reviews these design approaches for micro-architected materials with tailored mechanical responses that can be fabricated by AM as well as their applications.

Spadaccini, Christopher M [Lawrence Livermore Nati↗

DOE OSTI2018

Knowledge catalysts

A computer implemented method integrates data from remote disparate data sources by processing a non-transitory media. The non-transitory media stores instructions for detecting data sets in different formats hosted in a plurality of heterogeneous databases that are accessible through a distributed network. The method extracts schema data from the plurality of heterogeneous databases and identifies related fields in two or more of the heterogeneous databases. The method links the related fields in the two or more of the plurality of heterogeneous databases and makes the data accessible through a virtual warehouse. As schemas change, as new data sources and analysis artifacts are created, the computer implemented method and system can act as a meta-data store, a provenance tracking device, and/or a knowledge management service.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Comparison and validation of the QuEChERSER mega-method for determination of per- and polyfluoroalkyl substances in foods by liquid chromatography with high-resolution and triple quadrupole mass spectrometry

Instances of food contamination with per- and polyfluoroalkyl substances (PFAS) continue to occur globally, but sample preparation and analytical methods are quite limited and often monitor for a small percentage of known PFAS. This study aimed to evaluate, validate, and compare performance of two instruments with the recently developed “quick, easy, cheap, effective, rugged, safe, efficient, and robust” (QuEChERSER) sample preparation mega-method – a method developed to monitor chemicals over a broad range of physicochemical properties. Initial evaluation of the QuEChERSER mega-method for determination of PFAS in food demonstrated recoveries, matrix interferences, and co-extractive removal comparable to (or better than) US Food and Drug Administration (FDA) and USDA Food Safety and Inspection Service (FSIS) methods. Subsequent validation of QuEChERSER in beef, catfish, chicken, pork, liquid eggs, and powdered eggs on a high-resolution mass spectrometer achieved acceptable recoveries (70–120%) and precision (RSDs ≤20%) for all 33 target analytes at the 1 and 5 ng g –1 levels and 67–88% of analytes at the 0.1 ng g –1 level, depending on the matrix. Additional validation was performed by tandem mass spectrometry on a triple quadrupole instrument. This approach provided no non-detects and better recoveries at the 0.1 ng g –1 level than the HRMS method but exhibited more variability at 1 and 5 ng g –1 spiking levels. Analysis of NIST SRMs 1946 and 1947 gave accuracies of 70–117%. Furthermore, these results demonstrate the capability of combining PFAS analysis with a mega-method previously validated for 350 analytes, while collecting non-target data for future retrospective analysis of emerging alternatives with a high-resolution mass spectrometry method.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

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

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.

97 MATHEMATICS AND COMPUTING↗