Generating galaxy clusters mass density maps from mock multiview images via deep learning
Galaxy clusters are composed of dark matter, gas and stars. Their dark matter component, which amounts to around 80% of the total mass, cannot be directly observed but traced by the distribution of diffused gas and galaxy members. In this work, we aim to infer the cluster’s projected total mass dist...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | EPJ Web of Conferences |
| Online Access: | https://www.epj-conferences.org/articles/epjconf/pdf/2024/03/epjconf_mmUniverse2023_00013.pdf |
| _version_ | 1797235239037173760 |
|---|---|
| author | de Andres Daniel Cui Weiguang Yepes Gustavo De Petris Marco Aversano Gianmarco Ferragamo Antonio De Luca Federico Muñoz A. Jiménez |
| author_facet | de Andres Daniel Cui Weiguang Yepes Gustavo De Petris Marco Aversano Gianmarco Ferragamo Antonio De Luca Federico Muñoz A. Jiménez |
| author_sort | de Andres Daniel |
| collection | DOAJ |
| description | Galaxy clusters are composed of dark matter, gas and stars. Their dark matter component, which amounts to around 80% of the total mass, cannot be directly observed but traced by the distribution of diffused gas and galaxy members. In this work, we aim to infer the cluster’s projected total mass distribution from mock observational data, i.e. stars, Sunyaev-Zeldovich, and X-ray, by training deep learning models. To this end, we have created a multiview images dataset from The Three Hundred simulation that is optimal for training Machine Learning models. We further study deep learning architectures based on the U-Net to account for single-input and multi-input models. We show that the predicted mass distribution agrees well with the true one. |
| first_indexed | 2024-04-24T16:44:47Z |
| format | Article |
| id | doaj.art-2bfa74f145364812a035b67485b41fa3 |
| institution | Directory Open Access Journal |
| issn | 2100-014X |
| language | English |
| last_indexed | 2024-04-24T16:44:47Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | EPJ Web of Conferences |
| spelling | doaj.art-2bfa74f145364812a035b67485b41fa32024-03-29T08:31:00ZengEDP SciencesEPJ Web of Conferences2100-014X2024-01-012930001310.1051/epjconf/202429300013epjconf_mmUniverse2023_00013Generating galaxy clusters mass density maps from mock multiview images via deep learningde Andres Daniel0Cui Weiguang1Yepes Gustavo2De Petris Marco3Aversano Gianmarco4Ferragamo Antonio5De Luca Federico6Muñoz A. Jiménez7Departamento de Física Teórica and CIAFF, Modulo 8 Universidad Autónoma de MadridDepartamento de Física Teórica and CIAFF, Modulo 8 Universidad Autónoma de MadridDepartamento de Física Teórica and CIAFF, Modulo 8 Universidad Autónoma de MadridDipartimento di Fisica, Sapienza Universitá di Roma, Piazzale Aldo MoroEURANOVADipartimento di Fisica, Sapienza Universitá di Roma, Piazzale Aldo MoroDipartimento di Fisica, Sapienza Universitá di Roma, Piazzale Aldo MoroDepartamento de Física Teórica and CIAFF, Modulo 8 Universidad Autónoma de MadridGalaxy clusters are composed of dark matter, gas and stars. Their dark matter component, which amounts to around 80% of the total mass, cannot be directly observed but traced by the distribution of diffused gas and galaxy members. In this work, we aim to infer the cluster’s projected total mass distribution from mock observational data, i.e. stars, Sunyaev-Zeldovich, and X-ray, by training deep learning models. To this end, we have created a multiview images dataset from The Three Hundred simulation that is optimal for training Machine Learning models. We further study deep learning architectures based on the U-Net to account for single-input and multi-input models. We show that the predicted mass distribution agrees well with the true one.https://www.epj-conferences.org/articles/epjconf/pdf/2024/03/epjconf_mmUniverse2023_00013.pdf |
| spellingShingle | de Andres Daniel Cui Weiguang Yepes Gustavo De Petris Marco Aversano Gianmarco Ferragamo Antonio De Luca Federico Muñoz A. Jiménez Generating galaxy clusters mass density maps from mock multiview images via deep learning EPJ Web of Conferences |
| title | Generating galaxy clusters mass density maps from mock multiview images via deep learning |
| title_full | Generating galaxy clusters mass density maps from mock multiview images via deep learning |
| title_fullStr | Generating galaxy clusters mass density maps from mock multiview images via deep learning |
| title_full_unstemmed | Generating galaxy clusters mass density maps from mock multiview images via deep learning |
| title_short | Generating galaxy clusters mass density maps from mock multiview images via deep learning |
| title_sort | generating galaxy clusters mass density maps from mock multiview images via deep learning |
| url | https://www.epj-conferences.org/articles/epjconf/pdf/2024/03/epjconf_mmUniverse2023_00013.pdf |
| work_keys_str_mv | AT deandresdaniel generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT cuiweiguang generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT yepesgustavo generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT depetrismarco generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT aversanogianmarco generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT ferragamoantonio generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT delucafederico generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning AT munozajimenez generatinggalaxyclustersmassdensitymapsfrommockmultiviewimagesviadeeplearning |