{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/116048"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/116048","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Deep learning application for astrophysics: Supermassive black hole, dark matter substructures, and galaxy morphology","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01","abstract_has_math":false,"creators":["Lin, Yao-Yu"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Physics","degree_department":null,"school":null,"contributors":["Holder, Gilbert","Gammie, Charles F","Liu, Xin","Neubauer, Mark"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-08","date_published":"2022-08","updated_at":"2026-07-22T22:24:55Z","subjects":["Black holes","Dark Matter: Machine Learning","Deep Learning","VLBI","Vision Transformer"],"languages":["en","eng"],"rights":["Copyright 2022 Yao-Yu Lin"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/116048","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Holder, Gilbert","Gammie, Charles F","Liu, Xin","Neubauer, Mark"]},{"key":"dc:creator","label":"Author","values":["Lin, Yao-Yu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-08","2022-07-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Physics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Black holes","Dark Matter: Machine Learning","Deep Learning","VLBI","Vision Transformer"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2022 Yao-Yu Lin"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/116048"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01","The student, Yao-Yu Lin, accepted the attached license on 2022-07-01 at 14:04.","The student, Yao-Yu Lin, submitted this Dissertation for approval on 2022-07-01 at 14:30.","This Dissertation was approved for publication on 2022-07-08 at 14:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #18133 on 2022-11-15 at 19:16:55","Modern astronomy research has been thriving due to newly observations. To handle large and novel datasets, deep learning provides new way to tackle the challenges in data analysis. This thesis include deep learning applications on several astrophysics projects related to supermassive black holes (SMBH), dark matter substructures in strong gravitational lensing, and galaxy morphology classification. For SMBH, the Event Horizon Telescope (EHT) recently released the first horizon-scale images of the black hole in M87. Combined with other astronomical data, these images constrain the mass and spin of the black hole as well as the accretion rate and magnetic flux trapped on the black hole. An important question for EHT is how well key parameters such as spin, ring-size and trapped magnetic flux can be extracted from present and future EHT data alone. We explore parameter extraction using a convolutional neural network (CNN) trained on high resolution synthetic images drawn from state-of-the-art simulations. We find that the neural network is able to recover spin and flux with high accuracy. We are particularly interested in interpreting the neural network output and understanding which features are used to identify, e.g., black hole spin. Using feature maps, we find that the network keys on low surface brightness features in particular. We further investigate ring-size estimation using a neural network trained on noisy and blurry images drawn from state-of-the-art simulations. We find that the neural network can recover the physical scale, $GM/(Dc^2)$, in blind data tests of synthetic M87* images with an uncertainty distribution that is approximately Gaussian, with standard deviation around $13\\%$. While we found our ML pipeline works well in image domain, we further investigate the possibility of using ML for an end-to-end VLBI data cassification. We propose a data-driven approach to analyze complex visibilities and closure quantities for radio interferometric data with neural networks. Using mock interferometric data, we show that our neural networks are able to infer the accretion state as either high magnetic flux (MAD) or low magnetic flux (SANE), suggesting that it is possible to perform parameter extraction directly in the visibility domain without image reconstruction. We have applied VLBInet to real M87 EHT data taken on four different days in 2017 (April 5, 6, 10, 11), and our neural networks give a score prediction $0.52, 0.4, 0.43, 0.76$ for each day, with an average score $0.53$, which shows no significant indication for the data to lean toward either the MAD or SANE state. This thesis also include three individual projects: Weighing Supermassive Black Holes directly from photometric light curves with Deep Learning, Hunting for Dark Matter Substructures in Strong Gravitational Lensing with Neural Networks, Galaxy Classification with Vision Transformer. We find that deep learning could help tackle these problems, and we also discuss future directions in these projects."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep learning application for astrophysics: Supermassive black hole, dark matter substructures, and galaxy morphology"]}]}],"canonical_facts":{"dc:contributor":["Holder, Gilbert","Gammie, Charles F","Liu, Xin","Neubauer, Mark"],"dc:creator":["Lin, Yao-Yu"],"dc:date":["2022-08","2022-07-08"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01","The student, Yao-Yu Lin, accepted the attached license on 2022-07-01 at 14:04.","The student, Yao-Yu Lin, submitted this Dissertation for approval on 2022-07-01 at 14:30.","This Dissertation was approved for publication on 2022-07-08 at 14:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #18133 on 2022-11-15 at 19:16:55","Modern astronomy research has been thriving due to newly observations. To handle large and novel datasets, deep learning provides new way to tackle the challenges in data analysis. This thesis include deep learning applications on several astrophysics projects related to supermassive black holes (SMBH), dark matter substructures in strong gravitational lensing, and galaxy morphology classification. For SMBH, the Event Horizon Telescope (EHT) recently released the first horizon-scale images of the black hole in M87. Combined with other astronomical data, these images constrain the mass and spin of the black hole as well as the accretion rate and magnetic flux trapped on the black hole. An important question for EHT is how well key parameters such as spin, ring-size and trapped magnetic flux can be extracted from present and future EHT data alone. We explore parameter extraction using a convolutional neural network (CNN) trained on high resolution synthetic images drawn from state-of-the-art simulations. We find that the neural network is able to recover spin and flux with high accuracy. We are particularly interested in interpreting the neural network output and understanding which features are used to identify, e.g., black hole spin. Using feature maps, we find that the network keys on low surface brightness features in particular. We further investigate ring-size estimation using a neural network trained on noisy and blurry images drawn from state-of-the-art simulations. We find that the neural network can recover the physical scale, $GM/(Dc^2)$, in blind data tests of synthetic M87* images with an uncertainty distribution that is approximately Gaussian, with standard deviation around $13\\%$. While we found our ML pipeline works well in image domain, we further investigate the possibility of using ML for an end-to-end VLBI data cassification. We propose a data-driven approach to analyze complex visibilities and closure quantities for radio interferometric data with neural networks. Using mock interferometric data, we show that our neural networks are able to infer the accretion state as either high magnetic flux (MAD) or low magnetic flux (SANE), suggesting that it is possible to perform parameter extraction directly in the visibility domain without image reconstruction. We have applied VLBInet to real M87 EHT data taken on four different days in 2017 (April 5, 6, 10, 11), and our neural networks give a score prediction $0.52, 0.4, 0.43, 0.76$ for each day, with an average score $0.53$, which shows no significant indication for the data to lean toward either the MAD or SANE state. This thesis also include three individual projects: Weighing Supermassive Black Holes directly from photometric light curves with Deep Learning, Hunting for Dark Matter Substructures in Strong Gravitational Lensing with Neural Networks, Galaxy Classification with Vision Transformer. We find that deep learning could help tackle these problems, and we also discuss future directions in these projects."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/116048"],"dc:language":["en","eng"],"dc:rights":["Copyright 2022 Yao-Yu Lin"],"dc:subject":["Black holes","Dark Matter: Machine Learning","Deep Learning","VLBI","Vision Transformer"],"dc:title":["Deep learning application for astrophysics: Supermassive black hole, dark matter substructures, and galaxy morphology"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Physics"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:55Z"}