{"id":{"repo_id":"stellenbosch","oai_identifier":"oai:scholar.sun.ac.za:10019.1/135841"},"canonical_url":"https://search.dev.ndltd.org/etd/stellenbosch/oai:scholar.sun.ac.za:10019.1/135841","repository":{"repo_id":"stellenbosch","name":"Stellenbosch University","base_url":"https://scholar.sun.ac.za/server/oai/request"},"display":{"title":"Quantum Machine Learning Applied to Astronomical Datasets","abstract":"This dissertation investigates the application of quantum machine learning techniques in the field of astronomy. The focus is on a variety of supervised and unsupervised tasks, including classification, clustering, and anomaly detection. Quantum kernel methods, such as quantum-enhanced support vector machines and quantum-enhanced spectral clustering, as well as quantum variational circuits, including quantum convolutional neural networks and quantum autoencoders, are evaluated in comparison to classical learning approaches across multiple astronomical datasets. The primary goal was to benchmark quantum machine learning (QML) methods and assess their feasibility for real-world applications. The studies show that quantum methods are only competitive in very specific cases; for example, when explicit feature representation or limited training data coincidentally favor the quantum approach. These observations are not general and do not hold in most scenarios. Typically, classical machine learning implementations consistently outperform quantum approaches in the majority of cases. Most implementations were simulated only; however, limited runs on current real quantum devices indicate that noise further amplifies the performance gap, reinforcing the disconnect between simulated QML results and practical implementations. Based on these findings, the recommendation is that QML should not yet be relied upon for astronomical applications in its current state. Real progress in applied quantum machine learning will likely require fault-tolerant quantum computers, faster data upload and read-out times, and improved algorithms to make quantum approaches truly viable for practical astronomical tasks.","abstract_html":"This dissertation investigates the application of quantum machine learning techniques in the field of astronomy. The focus is on a variety of supervised and unsupervised tasks, including classification, clustering, and anomaly detection. Quantum kernel methods, such as quantum-enhanced support vector machines and quantum-enhanced spectral clustering, as well as quantum variational circuits, including quantum convolutional neural networks and quantum autoencoders, are evaluated in comparison to classical learning approaches across multiple astronomical datasets. The primary goal was to benchmark quantum machine learning (QML) methods and assess their feasibility for real-world applications. The studies show that quantum methods are only competitive in very specific cases; for example, when explicit feature representation or limited training data coincidentally favor the quantum approach. These observations are not general and do not hold in most scenarios. Typically, classical machine learning implementations consistently outperform quantum approaches in the majority of cases. Most implementations were simulated only; however, limited runs on current real quantum devices indicate that noise further amplifies the performance gap, reinforcing the disconnect between simulated QML results and practical implementations. Based on these findings, the recommendation is that QML should not yet be relied upon for astronomical applications in its current state. Real progress in applied quantum machine learning will likely require fault-tolerant quantum computers, faster data upload and read-out times, and improved algorithms to make quantum approaches truly viable for practical astronomical tasks.","abstract_has_math":false,"creators":["Slabbert, Donovan Michael"],"institution":"Stellenbosch : Stellenbosch University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Petruccione, Francesco"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-03","date_published":"2026-03","updated_at":"2026-07-24T04:40:06Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholar.sun.ac.za/handle/10019.1/135841","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Petruccione, Francesco"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Stellenbosch University. Faculty of Science. Dept. of Physics."]},{"key":"dc:creator","label":"Author","values":["Slabbert, Donovan Michael"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-04-13T09:22:49Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-04-13T09:22:49Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-03"]},{"key":"dc:publisher","label":"Institution","values":["Stellenbosch : Stellenbosch University"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholar.sun.ac.za/handle/10019.1/135841"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (PhD)--Stellenbosch University, 2026.","Slabbert, D. M. 2026. Quantum Machine Learning Applied to Astronomical Datasets. Unpublished doctoral dissertation. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/402e996b-5ee7-422a-bdf6-1d77b500dde0"]},{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation investigates the application of quantum machine learning techniques in the field of astronomy. The focus is on a variety of supervised and unsupervised tasks, including classification, clustering, and anomaly detection. Quantum kernel methods, such as quantum-enhanced support vector machines and quantum-enhanced spectral clustering, as well as quantum variational circuits, including quantum convolutional neural networks and quantum autoencoders, are evaluated in comparison to classical learning approaches across multiple astronomical datasets. The primary goal was to benchmark quantum machine learning (QML) methods and assess their feasibility for real-world applications. The studies show that quantum methods are only competitive in very specific cases; for example, when explicit feature representation or limited training data coincidentally favor the quantum approach. These observations are not general and do not hold in most scenarios. Typically, classical machine learning implementations consistently outperform quantum approaches in the majority of cases. Most implementations were simulated only; however, limited runs on current real quantum devices indicate that noise further amplifies the performance gap, reinforcing the disconnect between simulated QML results and practical implementations. Based on these findings, the recommendation is that QML should not yet be relied upon for astronomical applications in its current state. Real progress in applied quantum machine learning will likely require fault-tolerant quantum computers, faster data upload and read-out times, and improved algorithms to make quantum approaches truly viable for practical astronomical tasks."]},{"key":"dc:title","label":"Title","values":["Quantum Machine Learning Applied to Astronomical Datasets"]}]}],"canonical_facts":{"dc:contributor.advisor":["Petruccione, Francesco"],"dc:contributor.other":["Stellenbosch University. Faculty of Science. Dept. of Physics."],"dc:creator":["Slabbert, Donovan Michael"],"dc:date.accessioned":["2026-04-13T09:22:49Z"],"dc:date.available":["2026-04-13T09:22:49Z"],"dc:date.issued":["2026-03"],"dc:description":["Thesis (PhD)--Stellenbosch University, 2026.","Slabbert, D. M. 2026. Quantum Machine Learning Applied to Astronomical Datasets. Unpublished doctoral dissertation. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/402e996b-5ee7-422a-bdf6-1d77b500dde0"],"dc:description.abstract":["This dissertation investigates the application of quantum machine learning techniques in the field of astronomy. The focus is on a variety of supervised and unsupervised tasks, including classification, clustering, and anomaly detection. Quantum kernel methods, such as quantum-enhanced support vector machines and quantum-enhanced spectral clustering, as well as quantum variational circuits, including quantum convolutional neural networks and quantum autoencoders, are evaluated in comparison to classical learning approaches across multiple astronomical datasets. The primary goal was to benchmark quantum machine learning (QML) methods and assess their feasibility for real-world applications. The studies show that quantum methods are only competitive in very specific cases; for example, when explicit feature representation or limited training data coincidentally favor the quantum approach. These observations are not general and do not hold in most scenarios. Typically, classical machine learning implementations consistently outperform quantum approaches in the majority of cases. Most implementations were simulated only; however, limited runs on current real quantum devices indicate that noise further amplifies the performance gap, reinforcing the disconnect between simulated QML results and practical implementations. Based on these findings, the recommendation is that QML should not yet be relied upon for astronomical applications in its current state. Real progress in applied quantum machine learning will likely require fault-tolerant quantum computers, faster data upload and read-out times, and improved algorithms to make quantum approaches truly viable for practical astronomical tasks."],"dc:identifier.uri":["https://scholar.sun.ac.za/handle/10019.1/135841"],"dc:language.iso":["en"],"dc:publisher":["Stellenbosch : Stellenbosch University"],"dc:title":["Quantum Machine Learning Applied to Astronomical Datasets"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T04:40:06Z"}