scholarly journals Data-driven approach for synchrotron X-ray Laue microdiffraction scan analysis

2019 ◽  
Vol 75 (6) ◽  
pp. 876-888 ◽  
Author(s):  
Yintao Song ◽  
Nobumichi Tamura ◽  
Chenbo Zhang ◽  
Mostafa Karami ◽  
Xian Chen
Keyword(s):  
Machine Learning ◽  
National Laboratory ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Computational Pipeline ◽  
X Ray Diffraction ◽  
X Ray ◽  
Data Driven Approach ◽  
Labeling Algorithms ◽  
Diffraction Patterns

A novel data-driven approach is proposed for analyzing synchrotron Laue X-ray microdiffraction scans based on machine learning algorithms. The basic architecture and major components of the method are formulated mathematically. It is demonstrated through typical examples including polycrystalline BaTiO3, multiphase transforming alloys and finely twinned martensite. The computational pipeline is implemented for beamline 12.3.2 at the Advanced Light Source, Lawrence Berkeley National Laboratory. The conventional analytical pathway for X-ray diffraction scans is based on a slow pattern-by-pattern crystal indexing process. This work provides a new way for analyzing X-ray diffraction 2D patterns, independent of the indexing process, and motivates further studies of X-ray diffraction patterns from the machine learning perspective for the development of suitable feature extraction, clustering and labeling algorithms.

scholarly journals Machine‐Learning Clustering Technique Applied to Powder X‐Ray Diffraction Patterns to Distinguish Compositions of ThMn 12 ‐Type Alloys

2020 ◽  
Vol 3 (7) ◽  
pp. 2000039
Author(s):  
Keishu Utimula ◽  
Rutchapon Hunkao ◽  
Masao Yano ◽  
Hiroyuki Kimoto ◽  
Kenta Hongo ◽  
...  
Keyword(s):  
Machine Learning ◽  
X Ray Diffraction ◽  
X Ray ◽  
Clustering Technique ◽  
Diffraction Patterns

scholarly journals Symmetry prediction and knowledge discovery from X-ray diffraction patterns using an interpretable machine learning approach

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Yuta Suzuki ◽  
Hideitsu Hino ◽  
Takafumi Hawai ◽  
Kotaro Saito ◽  
Masato Kotsugi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Crystal Structure Analysis ◽  
Group Classification ◽  
X Ray Diffraction ◽  
Space Group ◽  
X Ray ◽  
Crystal System ◽  
Machine Learning Approach ◽  
Diffraction Patterns ◽  
Xrd Patterns

AbstractDetermination of crystal system and space group in the initial stages of crystal structure analysis forms a bottleneck in material science workflow that often requires manual tuning. Herein we propose a machine-learning (ML)-based approach for crystal system and space group classification based on powder X-ray diffraction (XRD) patterns as a proof of concept using simulated patterns. Our tree-ensemble-based ML model works with nearly or over 90% accuracy for crystal system classification, except for triclinic cases, and with 88% accuracy for space group classification with five candidates. We also succeeded in quantifying empirical knowledge vaguely shared among experts, showing the possibility for data-driven discovery of unrecognised characteristics embedded in experimental data by using an interpretable ML approach.

Pyromorphite formation and stability after quick lime neutralisation in the presence of soil and clay sorbents

2007 ◽  
Vol 4 (2) ◽  
pp. 109 ◽  
Author(s):  
Mark A. Chappell ◽  
Kirk G. Scheckel
Keyword(s):  
Phosphoric Acid ◽  
Contaminated Soils ◽  
National Laboratory ◽  
Argonne National Laboratory ◽  
Natural Soil ◽  
X Ray Diffraction ◽  
Quick Lime ◽  
X Ray ◽  
Soil Systems ◽  
Diffraction Patterns

Environmental context. Questions remain regarding the potential risk of human Pb exposure from metal-contaminated soils. Studies show that the risk of human exposure is more accurately linked to the toxicity of the Pb species in soil than the total quantity of Pb. This work explores the practicality of converting Pb to a less toxic, less bioavailable species called pyromorphite in the presence of soil. Abstract. Soluble Pb is immobilised in pure systems as pyromorphite by adding sources of P, but doubts remain about the effectiveness of this approach in natural soil systems, particularly given the ability of soil humic substances to interfere with Pb-mineral formation. In addition, recent thermodynamic modelling predicts that pyromorphite formed by the addition of phosphoric acid to Pb-contaminated soils, followed by neutralisation with quick lime (Ca(OH)2) will destabilise the mineral, reverting the Pb back to more soluble species such as cerussite or anglesite. In this paper, we describe experiments to form pyromorphite in the presence of two different sorbents: a reference smectite called Panther Creek Bentonite, and a commercially available, organically rich potting mixture. We present X-ray diffraction (XRD) evidence suggestive of pyromorphite formation, yet, like similar studies, the evidence is less than conclusive. Linear combination fits of Pb X-ray absorption fine-structure spectroscopy (XAFS) data collected at the Advanced Photon Source at Argonne National Laboratory show that pyromorphite is the major Pb species formed after the addition of phosphoric acid. Furthermore, XAFS data shows that neutralising with quick lime enhances (as opposed to reducing) pyromorphite content in these systems. These results call into question relying solely on XRD data to confirm or deny the existence of minerals like pyromorphite, whose complex morphology give less intense and more complicated diffraction patterns than some of the simpler Pb minerals.

Data-Driven Thermal Comfort Prediction With Support Vector Machine

2017 ◽  
Author(s):  
Bo Peng ◽  
Sheng-Jen Hsieh
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Thermal Comfort ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Support Vector ◽  
Climate Control ◽  
Data Driven Approach ◽  
Ubiquitous Sensor Networks ◽  
Model Training

Personal thermal comfort is a crucial yet often over-simplified factor in building climate control. Traditional comfort models lack the adaptability to fit individuals’ demand. Recent advances of machine learning and ubiquitous sensor networks enable the data-driven approach of thermal comfort. In this paper, we built a platform that can simulate occupants with different thermal sensations and used it to examine the performance of support vector machine (SVM) and compared with several other popular machine learning algorithms on thermal comfort prediction. We also proposed a hybrid SVM-LDA thermal comfort classifier that can improve the efficiency of model training.

scholarly journals Supervised learning from noisy observations: Combining machine-learning techniques with data assimilation

2021 ◽  
Author(s):  
Georg Gottwald ◽  
Sebastian Reich
Keyword(s):  
Machine Learning ◽  
Data Assimilation ◽  
Forecast Model ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Probabilistic Forecasting ◽  
Feature Maps ◽  
Data Driven Approach ◽  
Forecast Models

<p>Data-driven prediction and physics-agnostic machine-learning methods have attracted increased interest in recent years achieving forecast horizons going well beyond those to be expected for chaotic dynamical systems.<span>  </span>In a separate strand of research data-assimilation has been successfully used to optimally combine forecast models and their inherent uncertainty with incoming noisy observations. The key idea in our work here is to achieve increased forecast capabilities by judiciously combining machine-learning algorithms and data assimilation. We combine the physics-agnostic data-driven approach of random feature maps as a forecast model within an ensemble Kalman filter data assimilation procedure. The machine-learning model is learned sequentially by incorporating incoming noisy observations. We show that the obtained forecast model has remarkably good forecast skill while being computationally cheap once trained. Going beyond the task of forecasting, we show that our method can be used to generate reliable ensembles for probabilistic forecasting as well as to learn effective model closure in multi-scale systems.</p>

Evaluation of Freezing Methods by Low Temperature X-Ray Diffraction

1977 ◽  
Vol 35 ◽  
pp. 330-333
Author(s):  
T. Gulik-Krzywicki ◽  
M.J. Costello
Keyword(s):  
Biological Materials ◽  
Molecular Organization ◽  
X Ray Diffraction ◽  
Glass Capillary ◽  
X Ray ◽  
Rate Dependent ◽  
Before And After ◽  
Freeze Etching ◽  
Diffraction Patterns ◽  
Set Up

Freeze-etching electron microscopy is currently one of the best methods for studying molecular organization of biological materials. Its application, however, is still limited by our imprecise knowledge about the perturbations of the original organization which may occur during quenching and fracturing of the samples and during the replication of fractured surfaces. Although it is well known that the preservation of the molecular organization of biological materials is critically dependent on the rate of freezing of the samples, little information is presently available concerning the nature and the extent of freezing-rate dependent perturbations of the original organizations. In order to obtain this information, we have developed a method based on the comparison of x-ray diffraction patterns of samples before and after freezing, prior to fracturing and replication.Our experimental set-up is shown in Fig. 1. The sample to be quenched is placed on its holder which is then mounted on a small metal holder (O) fixed on a glass capillary (p), whose position is controlled by a micromanipulator.

Sign in / Sign up

Export Citation Format

Share Document