Accelerating reionization simulations using machine learning
| dc.contributor.advisor | Sultan, Hassan | |
| dc.contributor.author | Masipa, Mosima Portia | |
| dc.date.accessioned | 2023-11-14T08:37:18Z | |
| dc.date.accessioned | 2024-10-30T10:23:29Z | |
| dc.date.available | 2023-11-14T08:37:18Z | |
| dc.date.available | 2024-10-30T10:23:29Z | |
| dc.date.issued | 2023 | |
| dc.description | >Magister Scientiae - MSc | en_US |
| dc.description.abstract | Epoch of Reionization (EoR) refers to the time in the history of the universe when the appearance of the first luminous sources reionized the intergalactic medium (IGM). The EoR carries a wealth of information regarding structure formation and evolution. Ongoing and planned 21cm experiments such as the Hydrogen Epoch of Reionization Array (HERA) and the Square Kilometre Array (SKA) are expected to generate huge amounts of high dimensional datasets, and hence a new generation of efficient simulations and tools are required in order to maximize their scientific return. While Convolutional neural networks (CNNs) achieve the state-of-the-art performance to extract information from large scale fields, generating large training datasets and fully exploring the cosmological and astrophysical parameter space require fast simulations. | en_US |
| dc.identifier.uri | https://hdl.handle.net/10566/16644 | |
| dc.language.iso | en | en_US |
| dc.publisher | University of the Western Cape | en_US |
| dc.rights.holder | University of the Western Cape | en_US |
| dc.subject | Machine Learning | en_US |
| dc.subject | Continuous maps | en_US |
| dc.subject | Cosmology | en_US |
| dc.subject | Square Kilometre Array (SKA) | en_US |
| dc.subject | Hydrogen Epoch of Reionization Array (HERA) | en_US |
| dc.title | Accelerating reionization simulations using machine learning | en_US |