BYU

Abstract by Rachel Drapeau

Personal Infomation


Presenter's Name

Rachel Drapeau

Degree Level

Masters

Abstract Infomation


Department

Geological Sciences

Faculty Advisor

Barry Bickmore

Title

Reducing user error in QXRD analysis using machine learning

Abstract

Quantitative x-ray powder diffraction (QXRD) analysis is used to determine the phases contained in rock samples. However, the accurate identification of phases in a sample is largely dependent on the expertise and geologic knowledge of the analyst. To reduce this user error, we plan to incorporate supervised machine learning (SML) algorithms into RockJockML - a MATLAB based program for full-pattern summation QXRD analysis - to mimic the decisions expert analysts make. The data set will be created by using GSAS-II software to generate synthetic XRD patterns for samples by combining known crystal structure information and a calculated probability distribution of Rietveld parameters for each mineral in a sample. The models produced by the SML will then be compared to current progressive optimization techniques using the validation data set to determine which SML model performs best.