Predicting Stellar Parameters of Massive Stars from Light Curves with Machine Learning Article Swipe
Rachel C. Zhang
,
Kaze W. K. Wong
,
G. Holgado
,
Matteo Cantiello
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3847/1538-4357/ae1d70
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3847/1538-4357/ae1d70
High-resolution spectroscopic measurements of OB stars are important for understanding processes like stellar evolution but require labor-intensive observations. In contrast, photometric missions like the Transiting Exoplanet Survey Satellite (TESS) can monitor hundreds of thousands of stars with a range of temporal resolutions but do not provide such detailed measurements. With surveys like the Legacy Survey of Space and Time promising unprecedented photometric coverage over the next 10 yr, it is increasingly important to develop methods that connect large-scale time-series photometry with the detailed stellar parameter measurements typically derived from spectroscopy. In this paper, we test whether machine learning can recover such parameters by combining TESS light curves with spectroscopic measurements from the IACOB project, using a sample of 285 light curves from 106 unique O stars. Using both multilayer perceptrons and convolutional neural networks, we demonstrate that (1) O star light curves contain sufficient information to meaningfully infer stellar parameters, and (2) periodograms derived from light curves capture substantially more information than previously identified correlation parameters. Our best model achieves moderate success in predicting both spectroscopic luminosity ( ) and effective temperature ( ), key stellar parameters for determining positions of stars on the spectroscopic Hertzsprung–Russell diagram, despite the small dataset size. Further progress will require expanded datasets of matched photometric and spectroscopic observations.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Landing Page
- https://doi.org/10.3847/1538-4357/ae1d70
- OA Status
- gold
- References
- 36
- OpenAlex ID
- https://openalex.org/W4417223703
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4417223703Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.3847/1538-4357/ae1d70Digital Object Identifier
- Title
-
Predicting Stellar Parameters of Massive Stars from Light Curves with Machine LearningWork title
- Type
-
articleOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-12-11Full publication date if available
- Authors
-
Rachel C. Zhang, Kaze W. K. Wong, G. Holgado, Matteo CantielloList of authors in order
- Landing page
-
https://doi.org/10.3847/1538-4357/ae1d70Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.3847/1538-4357/ae1d70Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
36Number of works referenced by this work
Full payload
| id | https://openalex.org/W4417223703 |
|---|---|
| doi | https://doi.org/10.3847/1538-4357/ae1d70 |
| ids.doi | https://doi.org/10.3847/1538-4357/ae1d70 |
| ids.openalex | https://openalex.org/W4417223703 |
| fwci | |
| type | article |
| title | Predicting Stellar Parameters of Massive Stars from Light Curves with Machine Learning |
| biblio.issue | 2 |
| biblio.volume | 995 |
| biblio.last_page | 136 |
| biblio.first_page | 136 |
| is_xpac | False |
| apc_list.value | 4499 |
| apc_list.currency | USD |
| apc_list.value_usd | 4499 |
| apc_paid.value | 4499 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 4499 |
| language | |
| locations[0].id | doi:10.3847/1538-4357/ae1d70 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S1980519 |
| locations[0].source.issn | 0004-637X, 1538-4357 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 0004-637X |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | The Astrophysical Journal |
| locations[0].source.host_organization | https://openalex.org/P4310320083 |
| locations[0].source.host_organization_name | IOP Publishing |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320083, https://openalex.org/P4310311669 |
| locations[0].source.host_organization_lineage_names | IOP Publishing, Institute of Physics |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | The Astrophysical Journal |
| locations[0].landing_page_url | https://doi.org/10.3847/1538-4357/ae1d70 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5044449886 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2905-9239 |
| authorships[0].author.display_name | Rachel C. Zhang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Rachel C. Zhang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5078311510 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8432-7788 |
| authorships[1].author.display_name | Kaze W. K. Wong |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Kaze W. K. Wong |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5027099666 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-9296-8259 |
| authorships[2].author.display_name | G. Holgado |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Gonzalo Holgado |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5014376782 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8171-8596 |
| authorships[3].author.display_name | Matteo Cantiello |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Matteo Cantiello |
| authorships[3].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.3847/1538-4357/ae1d70 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-12-11T00:00:00 |
| display_name | Predicting Stellar Parameters of Massive Stars from Light Curves with Machine Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-11T23:13:37.075516 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.3847/1538-4357/ae1d70 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S1980519 |
| best_oa_location.source.issn | 0004-637X, 1538-4357 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 0004-637X |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | The Astrophysical Journal |
| best_oa_location.source.host_organization | https://openalex.org/P4310320083 |
| best_oa_location.source.host_organization_name | IOP Publishing |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320083, https://openalex.org/P4310311669 |
| best_oa_location.source.host_organization_lineage_names | IOP Publishing, Institute of Physics |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | The Astrophysical Journal |
| best_oa_location.landing_page_url | https://doi.org/10.3847/1538-4357/ae1d70 |
| primary_location.id | doi:10.3847/1538-4357/ae1d70 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S1980519 |
| primary_location.source.issn | 0004-637X, 1538-4357 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 0004-637X |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | The Astrophysical Journal |
| primary_location.source.host_organization | https://openalex.org/P4310320083 |
| primary_location.source.host_organization_name | IOP Publishing |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320083, https://openalex.org/P4310311669 |
| primary_location.source.host_organization_lineage_names | IOP Publishing, Institute of Physics |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | The Astrophysical Journal |
| primary_location.landing_page_url | https://doi.org/10.3847/1538-4357/ae1d70 |
| publication_date | 2025-12-11 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W3122729254, https://openalex.org/W4385302682, https://openalex.org/W3028093248, https://openalex.org/W2093088659, https://openalex.org/W2919321764, https://openalex.org/W4390399194, https://openalex.org/W2943407499, https://openalex.org/W3186145816, https://openalex.org/W2344233738, https://openalex.org/W4402654894, https://openalex.org/W4281694390, https://openalex.org/W4295974042, https://openalex.org/W2147344503, https://openalex.org/W3184043521, https://openalex.org/W2159714423, https://openalex.org/W4406275065, https://openalex.org/W3138401838, https://openalex.org/W2140288612, https://openalex.org/W2171168357, https://openalex.org/W1974618482, https://openalex.org/W2127375519, https://openalex.org/W3036195485, https://openalex.org/W2906986493, https://openalex.org/W2039550481, https://openalex.org/W2109519881, https://openalex.org/W2761986865, https://openalex.org/W1498436455, https://openalex.org/W2026381476, https://openalex.org/W1986316936, https://openalex.org/W4206191271, https://openalex.org/W1610780328, https://openalex.org/W2012636597, https://openalex.org/W4293228807, https://openalex.org/W2972978217, https://openalex.org/W2116228339, https://openalex.org/W2780156044 |
| referenced_works_count | 36 |
| abstract_inverted_index.( | 178, 210 |
| abstract_inverted_index.) | 206 |
| abstract_inverted_index.O | 125, 139 |
| abstract_inverted_index.a | 38, 116 |
| abstract_inverted_index.), | 238 |
| abstract_inverted_index.10 | 67 |
| abstract_inverted_index.In | 19, 91 |
| abstract_inverted_index.OB | 5 |
| abstract_inverted_index.by | 103 |
| abstract_inverted_index.do | 44 |
| abstract_inverted_index.in | 173 |
| abstract_inverted_index.is | 70 |
| abstract_inverted_index.it | 69 |
| abstract_inverted_index.of | 4, 33, 35, 40, 56, 118, 245, 263 |
| abstract_inverted_index.on | 247 |
| abstract_inverted_index.to | 73, 146 |
| abstract_inverted_index.we | 94, 135 |
| abstract_inverted_index.(1) | 138 |
| abstract_inverted_index.(2) | 152 |
| abstract_inverted_index.106 | 123 |
| abstract_inverted_index.285 | 119 |
| abstract_inverted_index.Our | 167 |
| abstract_inverted_index.and | 58, 131, 151, 207, 266 |
| abstract_inverted_index.are | 7 |
| abstract_inverted_index.but | 15, 43 |
| abstract_inverted_index.can | 30, 99 |
| abstract_inverted_index.for | 9, 242 |
| abstract_inverted_index.key | 239 |
| abstract_inverted_index.not | 45 |
| abstract_inverted_index.the | 24, 53, 65, 82, 112, 248, 253 |
| abstract_inverted_index.yr, | 68 |
| abstract_inverted_index.TESS | 105 |
| abstract_inverted_index.Time | 59 |
| abstract_inverted_index.With | 50 |
| abstract_inverted_index.best | 168 |
| abstract_inverted_index.both | 128, 175 |
| abstract_inverted_index.from | 89, 111, 122, 155 |
| abstract_inverted_index.like | 12, 23, 52 |
| abstract_inverted_index.more | 160 |
| abstract_inverted_index.next | 66 |
| abstract_inverted_index.over | 64 |
| abstract_inverted_index.star | 140 |
| abstract_inverted_index.such | 47, 101 |
| abstract_inverted_index.test | 95 |
| abstract_inverted_index.than | 162 |
| abstract_inverted_index.that | 76, 137 |
| abstract_inverted_index.this | 92 |
| abstract_inverted_index.will | 259 |
| abstract_inverted_index.with | 37, 81, 108 |
| abstract_inverted_index.IACOB | 113 |
| abstract_inverted_index.Space | 57 |
| abstract_inverted_index.Using | 127 |
| abstract_inverted_index.infer | 148 |
| abstract_inverted_index.light | 106, 120, 141, 156 |
| abstract_inverted_index.model | 169 |
| abstract_inverted_index.range | 39 |
| abstract_inverted_index.size. | 256 |
| abstract_inverted_index.small | 254 |
| abstract_inverted_index.stars | 6, 36, 246 |
| abstract_inverted_index.using | 115 |
| abstract_inverted_index.(TESS) | 29 |
| abstract_inverted_index.Legacy | 54 |
| abstract_inverted_index.Survey | 27, 55 |
| abstract_inverted_index.curves | 107, 121, 142, 157 |
| abstract_inverted_index.neural | 133 |
| abstract_inverted_index.paper, | 93 |
| abstract_inverted_index.sample | 117 |
| abstract_inverted_index.stars. | 126 |
| abstract_inverted_index.unique | 124 |
| abstract_inverted_index.Further | 257 |
| abstract_inverted_index.capture | 158 |
| abstract_inverted_index.connect | 77 |
| abstract_inverted_index.contain | 143 |
| abstract_inverted_index.dataset | 255 |
| abstract_inverted_index.derived | 88, 154 |
| abstract_inverted_index.despite | 252 |
| abstract_inverted_index.develop | 74 |
| abstract_inverted_index.machine | 97 |
| abstract_inverted_index.matched | 264 |
| abstract_inverted_index.methods | 75 |
| abstract_inverted_index.monitor | 31 |
| abstract_inverted_index.provide | 46 |
| abstract_inverted_index.recover | 100 |
| abstract_inverted_index.require | 16, 260 |
| abstract_inverted_index.stellar | 13, 84, 149, 240 |
| abstract_inverted_index.success | 172 |
| abstract_inverted_index.surveys | 51 |
| abstract_inverted_index.whether | 96 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.achieves | 170 |
| abstract_inverted_index.coverage | 63 |
| abstract_inverted_index.datasets | 262 |
| abstract_inverted_index.detailed | 48, 83 |
| abstract_inverted_index.diagram, | 251 |
| abstract_inverted_index.expanded | 261 |
| abstract_inverted_index.hundreds | 32 |
| abstract_inverted_index.learning | 98 |
| abstract_inverted_index.missions | 22 |
| abstract_inverted_index.moderate | 171 |
| abstract_inverted_index.progress | 258 |
| abstract_inverted_index.project, | 114 |
| abstract_inverted_index.temporal | 41 |
| abstract_inverted_index.<mml:math | 179, 211 |
| abstract_inverted_index.Exoplanet | 26 |
| abstract_inverted_index.Satellite | 28 |
| abstract_inverted_index.combining | 104 |
| abstract_inverted_index.contrast, | 20 |
| abstract_inverted_index.effective | 208 |
| abstract_inverted_index.evolution | 14 |
| abstract_inverted_index.important | 8, 72 |
| abstract_inverted_index.networks, | 134 |
| abstract_inverted_index.parameter | 85 |
| abstract_inverted_index.positions | 244 |
| abstract_inverted_index.processes | 11 |
| abstract_inverted_index.promising | 60 |
| abstract_inverted_index.thousands | 34 |
| abstract_inverted_index.typically | 87 |
| abstract_inverted_index.<mml:mrow> | 183, 186, 193, 196, 200, 215, 218, 225, 228, 232 |
| abstract_inverted_index.<mml:msup> | 182, 214 |
| abstract_inverted_index.Transiting | 25 |
| abstract_inverted_index.identified | 164 |
| abstract_inverted_index.luminosity | 177 |
| abstract_inverted_index.multilayer | 129 |
| abstract_inverted_index.parameters | 102, 241 |
| abstract_inverted_index.photometry | 80 |
| abstract_inverted_index.predicting | 174 |
| abstract_inverted_index.previously | 163 |
| abstract_inverted_index.sufficient | 144 |
| abstract_inverted_index.</mml:math> | 205, 237 |
| abstract_inverted_index.</mml:mrow> | 185, 188, 195, 199, 203, 217, 220, 227, 231, 235 |
| abstract_inverted_index.</mml:msup> | 189, 221 |
| abstract_inverted_index.correlation | 165 |
| abstract_inverted_index.demonstrate | 136 |
| abstract_inverted_index.determining | 243 |
| abstract_inverted_index.information | 145, 161 |
| abstract_inverted_index.large-scale | 78 |
| abstract_inverted_index.parameters, | 150 |
| abstract_inverted_index.parameters. | 166 |
| abstract_inverted_index.perceptrons | 130 |
| abstract_inverted_index.photometric | 21, 62, 265 |
| abstract_inverted_index.resolutions | 42 |
| abstract_inverted_index.temperature | 209 |
| abstract_inverted_index.time-series | 79 |
| abstract_inverted_index.increasingly | 71 |
| abstract_inverted_index.meaningfully | 147 |
| abstract_inverted_index.measurements | 3, 86, 110 |
| abstract_inverted_index.periodograms | 153 |
| abstract_inverted_index.<mml:msubsup> | 192, 224 |
| abstract_inverted_index.convolutional | 132 |
| abstract_inverted_index.measurements. | 49 |
| abstract_inverted_index.observations. | 18, 268 |
| abstract_inverted_index.spectroscopic | 2, 109, 176, 249, 267 |
| abstract_inverted_index.spectroscopy. | 90 |
| abstract_inverted_index.substantially | 159 |
| abstract_inverted_index.understanding | 10 |
| abstract_inverted_index.unprecedented | 61 |
| abstract_inverted_index.</mml:msubsup> | 204, 236 |
| abstract_inverted_index.High-resolution | 1 |
| abstract_inverted_index.labor-intensive | 17 |
| abstract_inverted_index.<mml:mi>R</mml:mi> | 184, 216 |
| abstract_inverted_index.<mml:mn>1</mml:mn> | 194 |
| abstract_inverted_index.<mml:mn>2</mml:mn> | 187, 219 |
| abstract_inverted_index.<mml:mn>3</mml:mn> | 226 |
| abstract_inverted_index.<mml:mo>+</mml:mo> | 201, 233 |
| abstract_inverted_index.<mml:mo>=</mml:mo> | 190, 222 |
| abstract_inverted_index.overflow="scroll"> | 181, 213 |
| abstract_inverted_index.<mml:mo>−</mml:mo> | 197, 229 |
| abstract_inverted_index.<mml:mn>0.44</mml:mn> | 223 |
| abstract_inverted_index.<mml:mn>0.64</mml:mn> | 191 |
| abstract_inverted_index.Hertzsprung–Russell | 250 |
| abstract_inverted_index.<mml:mn>0.056</mml:mn> | 234 |
| abstract_inverted_index.<mml:mn>0.107</mml:mn> | 202 |
| abstract_inverted_index.<mml:mn>0.167</mml:mn> | 198 |
| abstract_inverted_index.<mml:mn>0.234</mml:mn> | 230 |
| abstract_inverted_index.xmlns:mml="http://www.w3.org/1998/Math/MathML" | 180, 212 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |