{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53126"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53126","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"SPECIES AND ORIGIN CLASSIFICATION FOR MICHIGAN HARDWOODS USING DIRECT ANALYSIS IN REAL TIME MASS SPECTROMETRY AND MACHINE LEARNING","abstract":"Thesis (M.S.)--Michigan State University. Forestry - Master of Science, 2026","abstract_html":"Thesis (M.S.)--Michigan State University. Forestry - Master of Science, 2026","abstract_has_math":false,"creators":["Fitzharris, Jacob Helle"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Macfarlane, David W","Finley, Andrew","Nejad, Mojgan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:41Z","subjects":["Forestry","Forests and forestry"],"languages":["eng"],"rights":["Attribution 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53126","local:Fitzharris_grad.msu_0128N_22139"],"render_values":[{"text":"etd:53126","href":null,"code":true},{"text":"local:Fitzharris_grad.msu_0128N_22139","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/1nj9-y434","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/1nj9-y434","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53126","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Macfarlane, David W","Finley, Andrew","Nejad, Mojgan"]},{"key":"dc:creator","label":"Author","values":["Fitzharris, Jacob Helle"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Forestry","Forests and forestry"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53126","local:Fitzharris_grad.msu_0128N_22139","https://doi.org/doi:10.25335/1nj9-y434"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (M.S.)--Michigan State University. Forestry - Master of Science, 2026","Wood species and origin verification is important to continued efforts against illegal logging and timber trading. This thesis investigates how chemical information from Direct Analysis in Real Time Time-of-Flight Mass Spectrometry (DART-TOFMS) could be used to distinguish among 10 broadleaf, angiosperm tree species from Michigan, USA, which are important timber species in the eastern United States. It then examines how the same information from DART-TOFMS can be used to verify the origin of samples from 6 of the same species. Core samples were collected throughout Michigan, and heartwood from each sample was analyzed with DART-TOFMS. A Random Forest (RF) model was built to classify species, with predictor variables selected through Principal Component Analysis. This led to a 93.8% overall classification accuracy, with false positives and false negatives ranging from 0 to 10% for individual species, except for Liriodendron tulipifera and Quercus alba (FNR = 42.9% and 17.7%, respectively) and Fagus grandifolia (FPR = 13.3%), which showed lower accuracy. RF was used to predict whether a wood sample came from either the Upper, Northern Lower or Southern Lower Peninsulas. The 2-Region RF model performed with an 86.7% classification accuracy across the 6 included species, and the 3-region, 2-stage RF model performed with a 71.5% accuracy. When combining models to take a sample from species classification to the finest regional classification, the classification accuracy across the 6 included species was 86.3%. Through variable importance measurements and heatmapping analysis, ions were identified which differentiated intra- and inter- specific differences in metabolomes.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (98 p.) : ill."]},{"key":"dc:title","label":"Title","values":["SPECIES AND ORIGIN CLASSIFICATION FOR MICHIGAN HARDWOODS USING DIRECT ANALYSIS IN REAL TIME MASS SPECTROMETRY AND MACHINE LEARNING"]}]}],"canonical_facts":{"dc:contributor":["Macfarlane, David W","Finley, Andrew","Nejad, Mojgan"],"dc:creator":["Fitzharris, Jacob Helle"],"dc:date":["2026"],"dc:description":["Thesis (M.S.)--Michigan State University. Forestry - Master of Science, 2026","Wood species and origin verification is important to continued efforts against illegal logging and timber trading. This thesis investigates how chemical information from Direct Analysis in Real Time Time-of-Flight Mass Spectrometry (DART-TOFMS) could be used to distinguish among 10 broadleaf, angiosperm tree species from Michigan, USA, which are important timber species in the eastern United States. It then examines how the same information from DART-TOFMS can be used to verify the origin of samples from 6 of the same species. Core samples were collected throughout Michigan, and heartwood from each sample was analyzed with DART-TOFMS. A Random Forest (RF) model was built to classify species, with predictor variables selected through Principal Component Analysis. This led to a 93.8% overall classification accuracy, with false positives and false negatives ranging from 0 to 10% for individual species, except for Liriodendron tulipifera and Quercus alba (FNR = 42.9% and 17.7%, respectively) and Fagus grandifolia (FPR = 13.3%), which showed lower accuracy. RF was used to predict whether a wood sample came from either the Upper, Northern Lower or Southern Lower Peninsulas. The 2-Region RF model performed with an 86.7% classification accuracy across the 6 included species, and the 3-region, 2-stage RF model performed with a 71.5% accuracy. When combining models to take a sample from species classification to the finest regional classification, the classification accuracy across the 6 included species was 86.3%. Through variable importance measurements and heatmapping analysis, ions were identified which differentiated intra- and inter- specific differences in metabolomes.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (98 p.) : ill."],"dc:identifier":["etd:53126","local:Fitzharris_grad.msu_0128N_22139","https://doi.org/doi:10.25335/1nj9-y434"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution 4.0 International"],"dc:subject":["Forestry","Forests and forestry"],"dc:title":["SPECIES AND ORIGIN CLASSIFICATION FOR MICHIGAN HARDWOODS USING DIRECT ANALYSIS IN REAL TIME MASS SPECTROMETRY AND MACHINE LEARNING"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:41Z"}