{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124391"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124391","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Machine learning applications in astrophysics: Reduced-order modelling for chemical kinetics and galaxy merger reconstruction with graph neural network","abstract":"This thesis explores the application of deep learning techniques to two astrophysical problems: simplifying chemical kinetics calculations and reconstructing galaxy merger histories. A framework called Dengo is presented that can automatically generate chemical kinetics solvers from user-specified networks, enabling simplified integration of customized chemistry in simulations. The combination of neural ordinary differential equations and autoencoders is shown to be a promising approach for reducing the complexity of chemical kinetics simulations. Specifically, autoencoders identify the reduced reaction subspace while the neural ODE learn the latent space dynamics. This demonstrates the potential of using deep learning for reduced order modeling of complex chemical networks in astrophysics. For studying galaxy evolution, a conditional graph generative model is developed that can reconstruct the merger histories of observed galaxies from cosmological simulations. This allows identifying progenitors and formation pathways of galaxies across cosmic time. The model captures statistical properties of high-redshift progenitors and enables outlier detection and correlation identification. An overview of deep learning methods with a focus on techniques used in this thesis is also provided. The works demonstrate the potential of using deep learning for the selected problems in computational astrophysics and cosmic structure formation.","abstract_html":"This thesis explores the application of deep learning techniques to two astrophysical problems: simplifying chemical kinetics calculations and reconstructing galaxy merger histories. A framework called Dengo is presented that can automatically generate chemical kinetics solvers from user-specified networks, enabling simplified integration of customized chemistry in simulations. The combination of neural ordinary differential equations and autoencoders is shown to be a promising approach for reducing the complexity of chemical kinetics simulations. Specifically, autoencoders identify the reduced reaction subspace while the neural ODE learn the latent space dynamics. This demonstrates the potential of using deep learning for reduced order modeling of complex chemical networks in astrophysics. For studying galaxy evolution, a conditional graph generative model is developed that can reconstruct the merger histories of observed galaxies from cosmological simulations. This allows identifying progenitors and formation pathways of galaxies across cosmic time. The model captures statistical properties of high-redshift progenitors and enables outlier detection and correlation identification. An overview of deep learning methods with a focus on techniques used in this thesis is also provided. The works demonstrate the potential of using deep learning for the selected problems in computational astrophysics and cosmic structure formation.","abstract_has_math":false,"creators":["Tang, Kwok Sun"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Astronomy","degree_department":null,"school":null,"contributors":["Turk, Matthew","Ricker, Paul","Fields, Brian","Narayan, Gautham"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:00Z","subjects":["Astronomy","Machine Learning","Astrophysics","Deep Learning"],"languages":["eng","en"],"rights":["© 2024 Kwok Sun Tang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124391","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Turk, Matthew","Ricker, Paul","Fields, Brian","Narayan, Gautham"]},{"key":"dc:creator","label":"Author","values":["Tang, Kwok Sun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-04-26"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Astronomy"]},{"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":["Astronomy","Machine Learning","Astrophysics","Deep Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng","en"]},{"key":"dc:rights","label":"Dc Rights","values":["© 2024 Kwok Sun Tang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124391"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis explores the application of deep learning techniques to two astrophysical problems: simplifying chemical kinetics calculations and reconstructing galaxy merger histories. A framework called Dengo is presented that can automatically generate chemical kinetics solvers from user-specified networks, enabling simplified integration of customized chemistry in simulations. The combination of neural ordinary differential equations and autoencoders is shown to be a promising approach for reducing the complexity of chemical kinetics simulations. Specifically, autoencoders identify the reduced reaction subspace while the neural ODE learn the latent space dynamics. This demonstrates the potential of using deep learning for reduced order modeling of complex chemical networks in astrophysics. For studying galaxy evolution, a conditional graph generative model is developed that can reconstruct the merger histories of observed galaxies from cosmological simulations. This allows identifying progenitors and formation pathways of galaxies across cosmic time. The model captures statistical properties of high-redshift progenitors and enables outlier detection and correlation identification. An overview of deep learning methods with a focus on techniques used in this thesis is also provided. The works demonstrate the potential of using deep learning for the selected problems in computational astrophysics and cosmic structure formation.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, Kwok Sun Tang, accepted the attached license on 2024-04-24 at 11:35.","The student, Kwok Sun Tang, submitted this Dissertation for approval on 2024-04-24 at 11:42.","This Dissertation was approved for publication on 2024-04-26 at 12:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20608 on 2024-09-16 at 00:36:06"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Machine learning applications in astrophysics: Reduced-order modelling for chemical kinetics and galaxy merger reconstruction with graph neural network"]}]}],"canonical_facts":{"dc:contributor":["Turk, Matthew","Ricker, Paul","Fields, Brian","Narayan, Gautham"],"dc:creator":["Tang, Kwok Sun"],"dc:date":["2024-05","2024-04-26"],"dc:description":["This thesis explores the application of deep learning techniques to two astrophysical problems: simplifying chemical kinetics calculations and reconstructing galaxy merger histories. A framework called Dengo is presented that can automatically generate chemical kinetics solvers from user-specified networks, enabling simplified integration of customized chemistry in simulations. The combination of neural ordinary differential equations and autoencoders is shown to be a promising approach for reducing the complexity of chemical kinetics simulations. Specifically, autoencoders identify the reduced reaction subspace while the neural ODE learn the latent space dynamics. This demonstrates the potential of using deep learning for reduced order modeling of complex chemical networks in astrophysics. For studying galaxy evolution, a conditional graph generative model is developed that can reconstruct the merger histories of observed galaxies from cosmological simulations. This allows identifying progenitors and formation pathways of galaxies across cosmic time. The model captures statistical properties of high-redshift progenitors and enables outlier detection and correlation identification. An overview of deep learning methods with a focus on techniques used in this thesis is also provided. The works demonstrate the potential of using deep learning for the selected problems in computational astrophysics and cosmic structure formation.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, Kwok Sun Tang, accepted the attached license on 2024-04-24 at 11:35.","The student, Kwok Sun Tang, submitted this Dissertation for approval on 2024-04-24 at 11:42.","This Dissertation was approved for publication on 2024-04-26 at 12:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20608 on 2024-09-16 at 00:36:06"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124391"],"dc:language":["eng","en"],"dc:rights":["© 2024 Kwok Sun Tang"],"dc:subject":["Astronomy","Machine Learning","Astrophysics","Deep Learning"],"dc:title":["Machine learning applications in astrophysics: Reduced-order modelling for chemical kinetics and galaxy merger reconstruction with graph neural network"],"dc:type":["Text"],"thesis:degree_discipline":["Astronomy"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}