Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients
Gravitational lenses are caused by massive astronomical objects that distort space-time, bending light. They can distort transient astrophysical events, such as supernovae (SN), which are the subject of extensive study. However, gravitationally-lensed supernovae are rare, with only a few detected so...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ade360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849421441715404800 |
|---|---|
| author | Nicolò Oreste Pinciroli Vago Piero Fraternali |
| author_facet | Nicolò Oreste Pinciroli Vago Piero Fraternali |
| author_sort | Nicolò Oreste Pinciroli Vago |
| collection | DOAJ |
| description | Gravitational lenses are caused by massive astronomical objects that distort space-time, bending light. They can distort transient astrophysical events, such as supernovae (SN), which are the subject of extensive study. However, gravitationally-lensed supernovae are rare, with only a few detected so far. Future astronomical surveys will collect huge amounts of data, calling for automated and accurate discovery techniques to find them. Still, only a few works aim to discover gravitationally-lensed supernovae, most use only a few classes to characterize candidate observations, and only a few exploit spatial and temporal information. This work introduces Hydra, a novel pipeline designed to process spatio-temporal data for identifying and counting astronomical objects, including gravitational lenses and transients. Hydra performs two tasks: (i) counting the occurrences of 7 types of astronomical objects within each observation and (ii) classifying candidate events and objects (e.g. gravitational lenses and transient events). Across four datasets, Hydra achieves an average macro F _1 score higher than 79% for the counting task and macro F _1 scores ranging from ${\approx}59\%$ to ${\approx}94\%$ for classification. These results demonstrate its potential for improving automated discovery in future astronomical surveys and for counting objects in multimodal data. |
| format | Article |
| id | doaj-art-9f6e534fea014ee587bbd6fbb59b696b |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-9f6e534fea014ee587bbd6fbb59b696b2025-08-20T03:31:27ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016202506710.1088/2632-2153/ade360Multimodal multi-output ordinal regression for discovering gravitationally-lensed transientsNicolò Oreste Pinciroli Vago0https://orcid.org/0000-0001-7906-4987Piero Fraternali1https://orcid.org/0000-0002-6945-2625Department of Electronics, Information and Bioengineering , Politecnico di Milano, Milan, Italy; Osservatorio Astronomico di Roma , INAF, Monte Porzio Catone, Rome, ItalyDepartment of Electronics, Information and Bioengineering , Politecnico di Milano, Milan, ItalyGravitational lenses are caused by massive astronomical objects that distort space-time, bending light. They can distort transient astrophysical events, such as supernovae (SN), which are the subject of extensive study. However, gravitationally-lensed supernovae are rare, with only a few detected so far. Future astronomical surveys will collect huge amounts of data, calling for automated and accurate discovery techniques to find them. Still, only a few works aim to discover gravitationally-lensed supernovae, most use only a few classes to characterize candidate observations, and only a few exploit spatial and temporal information. This work introduces Hydra, a novel pipeline designed to process spatio-temporal data for identifying and counting astronomical objects, including gravitational lenses and transients. Hydra performs two tasks: (i) counting the occurrences of 7 types of astronomical objects within each observation and (ii) classifying candidate events and objects (e.g. gravitational lenses and transient events). Across four datasets, Hydra achieves an average macro F _1 score higher than 79% for the counting task and macro F _1 scores ranging from ${\approx}59\%$ to ${\approx}94\%$ for classification. These results demonstrate its potential for improving automated discovery in future astronomical surveys and for counting objects in multimodal data.https://doi.org/10.1088/2632-2153/ade360multimodalordinal regressiongravitational lensensemblingtransient |
| spellingShingle | Nicolò Oreste Pinciroli Vago Piero Fraternali Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients Machine Learning: Science and Technology multimodal ordinal regression gravitational lens ensembling transient |
| title | Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients |
| title_full | Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients |
| title_fullStr | Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients |
| title_full_unstemmed | Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients |
| title_short | Multimodal multi-output ordinal regression for discovering gravitationally-lensed transients |
| title_sort | multimodal multi output ordinal regression for discovering gravitationally lensed transients |
| topic | multimodal ordinal regression gravitational lens ensembling transient |
| url | https://doi.org/10.1088/2632-2153/ade360 |
| work_keys_str_mv | AT nicoloorestepincirolivago multimodalmultioutputordinalregressionfordiscoveringgravitationallylensedtransients AT pierofraternali multimodalmultioutputordinalregressionfordiscoveringgravitationallylensedtransients |