{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/30257"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/30257","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Neural Modelling of Astrophysical Gas","abstract":"We investigate the abilities of neural models to model astrophysical gases, addressing limitations in traditional numerical solvers such as energy bottlenecks, resolution effects, grid anisotropy effects, and strict time-stepping constraints. In particular, we focus on simulations of turbulent flows and thermochemical networks in the interstellar medium (ISM). We employ the chaotic Kuramoto-Sivashinsky (KS) equation as a one-dimensional testbed for neural network architectures commonly employed in simulations of threedimensional hydrodynamical turbulence. We benchmark a wide range of state-ofthe-art neural architectures. Our experiments demonstrate that hierarchical context aggregation, residual connections, and group equivariance play a critical role in capturing faithful dynamics and spectral properties of turbulent flows. Additionally, we model the thermochemical evolution of astrophysical gas using a residual neural network (ResNet) trained on data generated by the CHIMES code. The network predicts the evolution of chemical abundances and thermal states across a range of densities, temperatures, and metallicities, effectively integrating over large timesteps to mitigate the stiffness issues of conventional solvers. Our findings suggest that modern deep learning methods may provide a viable and efficient alternative to traditional numerical solvers for astrophysical simulations","abstract_html":"We investigate the abilities of neural models to model astrophysical gases, addressing limitations in traditional numerical solvers such as energy bottlenecks, resolution effects, grid anisotropy effects, and strict time-stepping constraints. In particular, we focus on simulations of turbulent flows and thermochemical networks in the interstellar medium (ISM). We employ the chaotic Kuramoto-Sivashinsky (KS) equation as a one-dimensional testbed for neural network architectures commonly employed in simulations of threedimensional hydrodynamical turbulence. We benchmark a wide range of state-ofthe-art neural architectures. Our experiments demonstrate that hierarchical context aggregation, residual connections, and group equivariance play a critical role in capturing faithful dynamics and spectral properties of turbulent flows. Additionally, we model the thermochemical evolution of astrophysical gas using a residual neural network (ResNet) trained on data generated by the CHIMES code. The network predicts the evolution of chemical abundances and thermal states across a range of densities, temperatures, and metallicities, effectively integrating over large timesteps to mitigate the stiffness issues of conventional solvers. Our findings suggest that modern deep learning methods may provide a viable and efficient alternative to traditional numerical solvers for astrophysical simulations","abstract_has_math":false,"creators":["McFarlane, Emmett"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Physics and Astronomy","school":null,"contributors":[],"advisors":["Wadsley, James"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-11-18T19:39:00Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/22406"],"render_values":[{"text":"https://doi.org/10.71548/22406","href":"https://doi.org/10.71548/22406","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/30257","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/30257","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F30257","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Wadsley, James"]},{"key":"dc:contributor.department","label":"Department","values":["Physics and Astronomy"]},{"key":"dc:creator","label":"Author","values":["McFarlane, Emmett"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-30T17:17:21Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-30T17:17:21Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"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":["http://hdl.handle.net/11375/30257","https://doi.org/10.71548/22406"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We investigate the abilities of neural models to model astrophysical gases, addressing limitations in traditional numerical solvers such as energy bottlenecks, resolution effects, grid anisotropy effects, and strict time-stepping constraints. In particular, we focus on simulations of turbulent flows and thermochemical networks in the interstellar medium (ISM). We employ the chaotic Kuramoto-Sivashinsky (KS) equation as a one-dimensional testbed for neural network architectures commonly employed in simulations of threedimensional hydrodynamical turbulence. We benchmark a wide range of state-ofthe-art neural architectures. Our experiments demonstrate that hierarchical context aggregation, residual connections, and group equivariance play a critical role in capturing faithful dynamics and spectral properties of turbulent flows. Additionally, we model the thermochemical evolution of astrophysical gas using a residual neural network (ResNet) trained on data generated by the CHIMES code. The network predicts the evolution of chemical abundances and thermal states across a range of densities, temperatures, and metallicities, effectively integrating over large timesteps to mitigate the stiffness issues of conventional solvers. Our findings suggest that modern deep learning methods may provide a viable and efficient alternative to traditional numerical solvers for astrophysical simulations"]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science (MSc)"]},{"key":"dc:title","label":"Title","values":["Neural Modelling of Astrophysical Gas"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Wadsley, James"],"dc:contributor.department":["Physics and Astronomy"],"dc:creator":["McFarlane, Emmett"],"dc:date.accessioned":["2024-09-30T17:17:21Z"],"dc:date.available":["2024-09-30T17:17:21Z"],"dc:date.issued":["2024"],"dc:description.abstract":["We investigate the abilities of neural models to model astrophysical gases, addressing limitations in traditional numerical solvers such as energy bottlenecks, resolution effects, grid anisotropy effects, and strict time-stepping constraints. In particular, we focus on simulations of turbulent flows and thermochemical networks in the interstellar medium (ISM). We employ the chaotic Kuramoto-Sivashinsky (KS) equation as a one-dimensional testbed for neural network architectures commonly employed in simulations of threedimensional hydrodynamical turbulence. We benchmark a wide range of state-ofthe-art neural architectures. Our experiments demonstrate that hierarchical context aggregation, residual connections, and group equivariance play a critical role in capturing faithful dynamics and spectral properties of turbulent flows. Additionally, we model the thermochemical evolution of astrophysical gas using a residual neural network (ResNet) trained on data generated by the CHIMES code. The network predicts the evolution of chemical abundances and thermal states across a range of densities, temperatures, and metallicities, effectively integrating over large timesteps to mitigate the stiffness issues of conventional solvers. Our findings suggest that modern deep learning methods may provide a viable and efficient alternative to traditional numerical solvers for astrophysical simulations"],"dc:description.degree":["Master of Science (MSc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/30257","https://doi.org/10.71548/22406"],"dc:language.iso":["en"],"dc:title":["Neural Modelling of Astrophysical Gas"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:39:00Z"}