{"id":{"repo_id":"umkc","oai_identifier":"oai:mospace.umsystem.edu:10355/96576"},"canonical_url":"https://search.dev.ndltd.org/etd/umkc/oai:mospace.umsystem.edu:10355/96576","repository":{"repo_id":"umkc","name":"University of Missouri - Kansas City","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"Efficient Automated Generation of Local Descriptors for Use in ab initio Electronic Structure Simulations","abstract":"First-principles electronic structure calculations based on density functional theory (DFT) are well-known to have a high computational cost that scales algorithmically as O(N³), where N is the number of electrons. Reducing that cost is a key goal of the computational materials physics community and machine learning (ML) is viewed as a potential tool for that task. However, ML model training requires carefully selected input descriptors for training. This thesis presents a computer program that is designed to automate the generation of local atomic environment descriptors for single element systems. The descriptors may be used for training neural networks to predict the set of electronic potential function coefficients, {Ai}, that are used within the DFT based orthogonalized linear combination of atomic orbitals (OLCAO) method. Predicting the potential function coefficients rather than explicitly computing them will reduce the computational cost of a typical OLCAO calculation by at least one order of magnitude and possibly two. We explore additional research directions by connecting the gap between descriptors used in computer vision and those employed in electronic structure predictions. This approach opens up possibilities for cross-disciplinary knowledge and techniques from computer vision, which may further improve the accuracy and efficiency of electronic structure calculations.","abstract_html":"First-principles electronic structure calculations based on density functional theory (DFT) are well-known to have a high computational cost that scales algorithmically as O(N³), where N is the number of electrons. Reducing that cost is a key goal of the computational materials physics community and machine learning (ML) is viewed as a potential tool for that task. However, ML model training requires carefully selected input descriptors for training. This thesis presents a computer program that is designed to automate the generation of local atomic environment descriptors for single element systems. The descriptors may be used for training neural networks to predict the set of electronic potential function coefficients, {Ai}, that are used within the DFT based orthogonalized linear combination of atomic orbitals (OLCAO) method. Predicting the potential function coefficients rather than explicitly computing them will reduce the computational cost of a typical OLCAO calculation by at least one order of magnitude and possibly two. We explore additional research directions by connecting the gap between descriptors used in computer vision and those employed in electronic structure predictions. This approach opens up possibilities for cross-disciplinary knowledge and techniques from computer vision, which may further improve the accuracy and efficiency of electronic structure calculations.","abstract_has_math":false,"creators":["Hoang, Duong Thuy"],"institution":"University of Missouri--Kansas City","degree_name":"M.S. (Master of Science)","degree_level":"Masters","degree_discipline":"Physics (UMKC)","degree_department":null,"school":null,"contributors":[],"advisors":["Rulis, Paul Michael, 1976-"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-07-24T05:18:49Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10355/96576","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Rulis, Paul Michael, 1976-"]},{"key":"dc:creator","label":"Author","values":["Hoang, Duong Thuy"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-08-28T22:05:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-08-28T22:05:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Physics (UMKC)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. (Master of Science)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Kansas City"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/96576"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Title from PDF of title page, viewed September 19, 2023","Thesis advisor: Paul Rulis","Vita","Includes bibliographical references (pages 106-109)","Thesis (M.S.)--Department of Physics and Astronomy. University of Missouri--Kansas City, 2023"]},{"key":"dc:description.abstract","label":"Abstract","values":["First-principles electronic structure calculations based on density functional theory (DFT) are well-known to have a high computational cost that scales algorithmically as O(N³), where N is the number of electrons. Reducing that cost is a key goal of the computational materials physics community and machine learning (ML) is viewed as a potential tool for that task. However, ML model training requires carefully selected input descriptors for training. This thesis presents a computer program that is designed to automate the generation of local atomic environment descriptors for single element systems. The descriptors may be used for training neural networks to predict the set of electronic potential function coefficients, {Ai}, that are used within the DFT based orthogonalized linear combination of atomic orbitals (OLCAO) method. Predicting the potential function coefficients rather than explicitly computing them will reduce the computational cost of a typical OLCAO calculation by at least one order of magnitude and possibly two. We explore additional research directions by connecting the gap between descriptors used in computer vision and those employed in electronic structure predictions. This approach opens up possibilities for cross-disciplinary knowledge and techniques from computer vision, which may further improve the accuracy and efficiency of electronic structure calculations."]},{"key":"dc:title","label":"Title","values":["Efficient Automated Generation of Local Descriptors for Use in ab initio Electronic Structure Simulations"]}]}],"canonical_facts":{"dc:contributor.advisor":["Rulis, Paul Michael, 1976-"],"dc:creator":["Hoang, Duong Thuy"],"dc:date.accessioned":["2023-08-28T22:05:22Z"],"dc:date.available":["2023-08-28T22:05:22Z"],"dc:date.issued":["2023"],"dc:description":["Title from PDF of title page, viewed September 19, 2023","Thesis advisor: Paul Rulis","Vita","Includes bibliographical references (pages 106-109)","Thesis (M.S.)--Department of Physics and Astronomy. University of Missouri--Kansas City, 2023"],"dc:description.abstract":["First-principles electronic structure calculations based on density functional theory (DFT) are well-known to have a high computational cost that scales algorithmically as O(N³), where N is the number of electrons. Reducing that cost is a key goal of the computational materials physics community and machine learning (ML) is viewed as a potential tool for that task. However, ML model training requires carefully selected input descriptors for training. This thesis presents a computer program that is designed to automate the generation of local atomic environment descriptors for single element systems. The descriptors may be used for training neural networks to predict the set of electronic potential function coefficients, {Ai}, that are used within the DFT based orthogonalized linear combination of atomic orbitals (OLCAO) method. Predicting the potential function coefficients rather than explicitly computing them will reduce the computational cost of a typical OLCAO calculation by at least one order of magnitude and possibly two. We explore additional research directions by connecting the gap between descriptors used in computer vision and those employed in electronic structure predictions. This approach opens up possibilities for cross-disciplinary knowledge and techniques from computer vision, which may further improve the accuracy and efficiency of electronic structure calculations."],"dc:identifier.uri":["https://hdl.handle.net/10355/96576"],"dc:title":["Efficient Automated Generation of Local Descriptors for Use in ab initio Electronic Structure Simulations"],"thesis:degree_discipline":["Physics (UMKC)"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S. (Master of Science)"],"thesis:institution_name":["University of Missouri--Kansas City"]},"updated_at":"2026-07-24T05:18:49Z"}