<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T05:27:36Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/29701" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/29701</identifier><datestamp>2026-09-24T07:29:52Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Botton, Gianluigi</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Mousavi Masouleh, Seyed Shayan</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Materials Science and Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-04-26T19:11:22Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-04-26T19:11:22Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2024</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/29701</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/11184</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">The emergence of advanced computational techniques and artificial intelligence has&#xd;
strongly impacted the materials discovery and optimization. This study focuses on&#xd;
applying computational methods to extract information from complex spectral systems.&#xd;
Three distinct tiers of information extraction from hyperspectral data are explored: integrating&#xd;
light data treatment with computational modeling, employing convolutional&#xd;
neural networks for signal reconstruction, and advancing quantification using probabilistic&#xd;
machine learning.&#xd;
In the first tier, utilizing electron energy loss spectroscopy (EELS) in conjunction with&#xd;
boundary element method modeling, we uncovered the broadband plasmonic properties&#xd;
in wrinkled gold structures and their origin. We demonstrated the link between broadband&#xd;
plasmonic characteristics and surface nano-features, offering insights into property&#xd;
tunability.&#xd;
To benefit the broader microscopy community, in the second tier, we developed EELSpecNet,&#xd;
a Python script based on convolutional neural networks. EELSpecNet reconstructs&#xd;
signals to retrieve details that were obscured by various signal artifacts. EELSpecNet&#xd;
was benchmarked for near-zero-loss EELS, a challenging signal that contains&#xd;
crucial phononic and plasmonic information. The results clearly show that this neural&#xd;
network approach surpasses conventional Bayesian methods in deconvolution, particularly&#xd;
in terms of information retrieval, signal fidelity, and noise reduction.&#xd;
The final tier of this research introduces an innovative approach to spectral analysis&#xd;
and quantification using probabilistic machine learning methods. By employing&#xd;
the Markov Chain Monte Carlo sampling and Gaussian Process Regression models, this&#xd;
tool facilitates spectral quantifications, provides comprehensive uncertainty analysis, reduces&#xd;
human biases in the decision-making and model selection processes. This tool is&#xd;
particularly useful for in-operando X-ray diffraction data analysis, a key technique for&#xd;
examining battery materials. This method effectively disentangles overlapping peaks,&#xd;
quantifies each peak, and tracks their evolution. Tested on both synthetic and real&#xd;
experimental data, the tool demonstrated its efficacy and versatility. Given its broad&#xd;
adaptability, this method is suitable for a variety of spectroscopy techniques.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Doctor of Science  (PhD)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Artificial Intelligence</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Computational Methods</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Advanced Spectroscopy Analysis</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Machine Learning</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Harnessing Artificial Intelligence and Computational Methods for Advanced Spectroscopy Analysis</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>