arxiv: 2604.09152 · v1 · submitted 2026-04-10 · 🌌 astro-ph.EP

Recognition: unknown

Machine Learning as a Transformative Tool for (Exo-)Planetary Science

J. Davoult , V. T. Bickel , C. Haslebacher , Y. Alibert , D. Angerhausen , C. Cantero , J. A. Egger , R. Eltschinger

show 6 more authors

Y. Eyholzer E. O. Garvin S. Gruchola A. Leleu S. Marques Y. Zhao

Authors on Pith no claims yet

Pith reviewed 2026-05-10 17:22 UTC · model grok-4.3

classification 🌌 astro-ph.EP

keywords machine learningexoplanetsplanetary scienceneural networkstime series analysispattern recognitiongenerative modelsdata processing

0 comments

The pith

Machine learning techniques can process the large, inconsistent datasets that limit progress in planetary and exoplanetary science.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that recent machine learning advances open ways to handle the messy, high-volume data coming from solar-system missions and exoplanet observations. It organizes the work around three practical problems: modelling sequences such as radial-velocity time series, spotting patterns and anomalies in spectra or images, and building fast predictive models of planet interiors. A reader would care because these data problems currently slow down analysis and limit what can be learned from existing and future observations. The authors present specific neural-network approaches developed for each problem and claim the combined set of tools marks a broad change in how the field works with data and simulations.

Core claim

The authors describe machine-learning methods for three challenges: sequence modelling of one-dimensional time series such as radial velocities and light curves; pattern recognition that uses convolutional neural networks for feature extraction and variational autoencoders for anomaly detection and unsupervised clustering; and generative models that employ deep neural networks to emulate planetary interior structures and formation processes. These techniques are presented as direct responses to the spatio-temporal inconsistencies and heterogeneity of (exo)planetary datasets, with the claim that their adoption will enable revolutionary discoveries.

What carries the argument

Three categories of machine learning applied to planetary data: sequence modelling for time series, pattern recognition via convolutional and variational networks, and generative neural-network models for interior structure and formation.

Load-bearing premise

The selected machine-learning methods are new enough and well enough tested to produce a genuine shift in how planetary data are processed, even though the review gives no side-by-side performance numbers against standard statistical tools.

What would settle it

A controlled test on the same planetary or exoplanet datasets in which traditional statistical or physical modelling methods match or exceed the accuracy and speed of the described neural-network approaches would undermine the claim that these methods constitute a paradigm shift.

Figures

Figures reproduced from arXiv: 2604.09152 by A. Leleu, C. Cantero, C. Haslebacher, D. Angerhausen, E. O. Garvin, J. A. Egger, J. Davoult, R. Eltschinger, S. Gruchola, S. Marques, V. T. Bickel, Y. Alibert, Y. Eyholzer, Y. Zhao.

**Figure 3.** Figure 3: Data collection LMS Pre-processing Embedding Clustering Histogramming Mineral 1 Mineral 2 Mineral 3 Mineral 4 [PITH_FULL_IMAGE:figures/full_fig_p016_3.png] view at source ↗

read the original abstract

The exploration of planetary bodies in our Solar system and beyond relies on the processing and interpretation of large, spatio-temporally inconsistent, and heterogeneous datasets. Recent advances in machine learning (ML) provide unprecedented opportunities to address many fundamental challenges posed by these heterogeneous and hyper-dimensional datasets. This review chapter highlights innovative ML methodologies that were developed and used by NCCR PlanetS members to address three overarching challenges in (exo)planetary science. The first challenge is sequence modelling, which encompasses the intricate analysis of one-dimensional data such as time series of radial velocities and light curves, among other examples. Secondly, there is pattern recognition that involves studying correlations, leveraging convolutional neural networks for feature extraction, mapping and cross correlation among other examples., anomaly detection through variational autoencoders, and unsupervised clustering of mass spectrometric data. Lastly, there are generative models and emulation-based Bayesian analysis, which encompass the development of predictive models for planetary interior structure, employing Deep Neural Networks to understand planet formation mechanisms. These innovative ML methodologies herald a paradigm shift in the processing of data and numerical models that represent inherent challenges in planetary and exoplanetary science, paving the way for revolutionary discoveries and ideas in this field.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

A descriptive review of NCCR PlanetS ML applications in exoplanet data that overstates its case without benchmarks or new results.

read the letter

This paper is a review chapter from the NCCR PlanetS group that walks through machine learning tools they have applied to planetary and exoplanet problems. It groups the work into sequence modeling for time series like radial velocities and light curves, pattern recognition using CNNs for feature extraction and VAEs for anomaly detection, and generative models with DNNs for planetary interior structure and formation emulation. The text correctly notes that these datasets are large, heterogeneous, and inconsistent in time and space, which is a real practical issue in the field. The examples drawn from their consortium give a sense of how standard ML methods can be adapted to mass spectrometry clustering or speeding up Bayesian interior calculations. That part is straightforward and useful as an overview. The central claim that these methods herald a paradigm shift does not hold up on the evidence presented. The manuscript stays at the level of high-level descriptions and intended use cases; it supplies no head-to-head accuracy numbers, discovery yields, false-positive rates, or computational cost comparisons against traditional pipelines. Without those, the transformative language reads as an extrapolation rather than a demonstrated result. As a review it could serve readers who want a quick map of ML examples from one active group, but anyone needing rigorous validation will have to turn to the cited original papers. I would bring it to a reading group only if the topic is applied ML in astronomy and the group already knows the underlying methods. I would not cite it for new findings. It could reasonably go to peer review for a methods-oriented journal, though the authors would likely be asked to add concrete performance data and moderate the conclusions.

Referee Report

1 major / 1 minor

Summary. The manuscript is a review chapter that describes machine learning methodologies developed and applied by NCCR PlanetS members to address three core challenges in (exo)planetary science: sequence modeling of time-series data such as radial velocities and light curves; pattern recognition via convolutional neural networks, variational autoencoders for anomaly detection, and unsupervised clustering of mass spectrometric data; and generative models including deep neural networks for predicting planetary interior structures and formation mechanisms. The central claim is that these approaches herald a paradigm shift in processing heterogeneous, high-dimensional datasets, thereby enabling revolutionary discoveries.

Significance. If the cited ML applications have been independently validated to deliver measurable improvements in accuracy, efficiency, or discovery yield over established non-ML pipelines, the review would usefully document collaborative progress in the field and could accelerate adoption of these tools. The manuscript's strength lies in its focused summary of NCCR PlanetS work across the three domains, providing a consolidated reference for the community. Absent quantitative benchmarks, however, its significance remains that of a descriptive overview rather than a demonstration of transformation.

major comments (1)

[Abstract] Abstract: The assertion that the described ML methodologies 'herald a paradigm shift' is not accompanied by any head-to-head performance metrics, accuracy gains, computational-cost reductions, or false-positive-rate comparisons against traditional methods in the sequence-modeling, pattern-recognition, or generative-model domains. Because this claim is load-bearing for the review's thesis and the text supplies only high-level descriptions of intended use cases, the manuscript requires either explicit inclusion of such benchmarks or a tempered statement of the claim's evidential basis.

minor comments (1)

[Abstract] Abstract: The sentence fragment 'mapping and cross correlation among other examples., anomaly detection' contains an extraneous period and comma that breaks grammatical flow and should be corrected for clarity.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive and detailed comments on our review manuscript. We agree that the abstract's claim of a 'paradigm shift' requires tempering to align with the high-level, descriptive nature of the chapter, which summarizes NCCR PlanetS contributions without new head-to-head benchmarks. We will revise the abstract accordingly in the resubmitted version.

read point-by-point responses

Referee: [Abstract] Abstract: The assertion that the described ML methodologies 'herald a paradigm shift' is not accompanied by any head-to-head performance metrics, accuracy gains, computational-cost reductions, or false-positive-rate comparisons against traditional methods in the sequence-modeling, pattern-recognition, or generative-model domains. Because this claim is load-bearing for the review's thesis and the text supplies only high-level descriptions of intended use cases, the manuscript requires either explicit inclusion of such benchmarks or a tempered statement of the claim's evidential basis.

Authors: We thank the referee for this observation. The manuscript is a review chapter focused on methodologies developed and applied by NCCR PlanetS members across the three domains, rather than a benchmark study introducing new quantitative comparisons. Individual performance metrics and validations against traditional methods are documented in the cited primary publications for each application. To address the concern directly, we will revise the abstract to temper the language (e.g., replacing 'herald a paradigm shift' with 'offer promising pathways toward transformative advances' or similar phrasing that reflects the review's scope and the evidential basis in the referenced works). This revision will be incorporated in the next manuscript version. revision: yes

Circularity Check

0 steps flagged

No circularity: descriptive review without derivations or self-referential reductions

full rationale

The manuscript is a review chapter summarizing existing ML applications (CNNs, VAEs, DNNs, sequence models) developed by NCCR PlanetS members for planetary data challenges. It contains no equations, fitted parameters, predictions, or derivation chains. The paradigm-shift statement is a qualitative assertion at the end of the abstract and does not reduce to any input by construction, self-definition, or self-citation loop. No load-bearing steps match the enumerated circularity patterns; the work is self-contained as a descriptive overview.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a review paper; the central claims rest on the existence and effectiveness of previously published ML methodologies by the NCCR PlanetS members. No new free parameters, axioms, or invented entities are introduced in the abstract.

pith-pipeline@v0.9.0 · 5578 in / 1113 out tokens · 30457 ms · 2026-05-10T17:22:51.489353+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

180 extracted references · 152 canonical work pages · 4 internal anchors

[1]

Abelson, Science149(3689), 1179 (1965)

P.H. Abelson, Science149(3689), 1179 (1965). DOI 10.1126/science.149.3689.1179

work page doi:10.1126/science.149.3689.1179 1965
[2]

Dunne, E

J.A. Dunne, E. Burgess,The voyage of Mariner 10 : mission to Venus and Mer- cury, vol. 424 (Washington : Scientific and Technical Information Division, National Aeronautics and Space Administration, 1978)

1978
[3]

Bailey, arXiv e-prints arXiv:1302.3675 (2013)

J. Bailey, arXiv e-prints arXiv:1302.3675 (2013). DOI 10.48550/arXiv.1302.3675

work page doi:10.48550/arxiv.1302.3675 2013
[4]

Abelson, Science197(4308), 1039 (1977)

P.H. Abelson, Science197(4308), 1039 (1977). DOI 10.1126/science.197.4308.1039

work page doi:10.1126/science.197.4308.1039 1977
[5]

Kohlhase, P.A

C.E. Kohlhase, P.A. Penzo, Space Science Reviews21(2), 77 (1977). DOI 10.1007/BF00200846

work page doi:10.1007/bf00200846 1977
[6]

Kepler Planet-Detection Mission: Introduction and First Results.Science2010,327, 977

W.J. Borucki, D. Koch, G. Basri, et al., Science327(5968), 977 (2010). DOI 10.1126/science.1185402

work page doi:10.1126/science.1185402 2010
[7]

R., Winn, J

G.R. Ricker, J.N. Winn, R. Vanderspek, et al., Journal of Astronom- ical Telescopes, Instruments, and Systems1, 014003 (2015). DOI 10.1117/1.JATIS.1.1.014003

work page internal anchor Pith review doi:10.1117/1.jatis.1.1.014003 2015
[8]

Bolton, J

S.J. Bolton, J. Lunine, D. Stevenson, et al., Space Science Reviews213(1-4), 5 (2017). DOI 10.1007/s11214-017-0429-6

work page doi:10.1007/s11214-017-0429-6 2017
[9]

, keywords =

J.P. Gardner, J.C. Mather, M. Clampin, et al., Space Science Reviews123(4), 485 (2006). DOI 10.1007/s11214-006-8315-7

work page doi:10.1007/s11214-006-8315-7 2006
[10]

Lauretta, S.S

D.S. Lauretta, S.S. Balram-Knutson, E. Beshore, et al., Space Science Re- views212(1-2), 925 (2017). DOI 10.1007/s11214-017-0405-1

work page doi:10.1007/s11214-017-0405-1 2017
[11]

Cheng, A.S

A.F. Cheng, A.S. Rivkin, P. Michel, et al., Planetary and Space Science157, 104 (2018). DOI 10.1016/j.pss.2018.02.015

work page doi:10.1016/j.pss.2018.02.015 2018
[12]

Walsh, A

K.J. Walsh, A. Morbidelli, S.N. Raymond, et al., Meteoritics & Planetary Science47(12), 1941 (2012). DOI 10.1111/j.1945-5100.2012.01418.x

work page doi:10.1111/j.1945-5100.2012.01418.x 1941
[13]

Gomes, H.F

R. Gomes, H.F. Levison, K. Tsiganis, A. Morbidelli, Nature435(7041), 466 (2005). DOI 10.1038/nature03676

work page doi:10.1038/nature03676 2005
[14]

J., Morbidelli, A., Raymond, S

K. Tsiganis, R. Gomes, A. Morbidelli, H.F. Levison, Nature435(7041), 459 (2005). DOI 10.1038/nature03539 22 Davoult et al

work page doi:10.1038/nature03539 2005
[15]

Morbidelli, H.F

A. Morbidelli, H.F. Levison, K. Tsiganis, R. Gomes, Nature435(7041), 462 (2005). DOI 10.1038/nature03540

work page doi:10.1038/nature03540 2005
[16]

Adcroft, J.M

A. Adcroft, J.M. Campin, C. Hill, J. Marshall, Monthly Weather Review 132(12), 2845 (2004). DOI 10.1175/MWR2823.1

work page doi:10.1175/mwr2823.1 2004
[17]

Richardson, A.D

M.I. Richardson, A.D. Toigo, C.E. Newman, Journal of Geophysical Research (Planets)112(E9), E09001 (2007). DOI 10.1029/2006JE002825

work page doi:10.1029/2006je002825 2007
[18]

Gilli, S

G. Gilli, S. Lebonnois, F. Gonz´alez-Galindo, et al., Icarus281, 55 (2017). DOI 10.1016/j.icarus.2016.09.016

work page doi:10.1016/j.icarus.2016.09.016 2017
[19]

Timpe, C

M. Timpe, C. Reinhardt, T. Meier, et al., The Astrophysical Journal959(1), 38 (2023). DOI 10.3847/1538-4357/acfc40

work page doi:10.3847/1538-4357/acfc40 2023
[20]

Meier, C

T. Meier, C. Reinhardt, M. Timpe, et al., The Astrophysical Journal978(1), 11 (2025). DOI 10.3847/1538-4357/ad9248

work page doi:10.3847/1538-4357/ad9248 2025
[21]

Weder, C

J. Weder, C. Mordasini, A. Emsenhuber, Astronomy & Astrophysics674, A165 (2023). DOI 10.1051/0004-6361/202243453

work page doi:10.1051/0004-6361/202243453 2023
[22]

McEwen, E.M

A.S. McEwen, E.M. Eliason, J.W. Bergstrom, et al., Journal of Geophysical Research (Planets)112(E5), E05S02 (2007). DOI 10.1029/2005JE002605

work page doi:10.1029/2005je002605 2007
[23]

2016 a , , 595, A1, 10.1051/0004-6361/201629272

Gaia Collaboration, T. Prusti, J.H.J. de Bruijne, et al., Astronomy & Astro- physics595, A1 (2016). DOI 10.1051/0004-6361/201629272

work page doi:10.1051/0004-6361/201629272 2016
[24]

Howell, R.T

S.M. Howell, R.T. Pappalardo, Nature Communications11, 1311 (2020). DOI 10.1038/s41467-020-15160-9

work page doi:10.1038/s41467-020-15160-9 2020
[25]

Grasset, M.K

O. Grasset, M.K. Dougherty, A. Coustenis, et al., Planetary and Space Sci- ence78, 1 (2013). DOI 10.1016/j.pss.2012.12.002

work page doi:10.1016/j.pss.2012.12.002 2013
[26]

2014, Experimental Astronomy, 38, 249, doi: 10.1007/s10686-014-9383-4

H. Rauer, C. Catala, C. Aerts, et al., Experimental Astronomy38(1-2), 249 (2014). DOI 10.1007/s10686-014-9383-4

work page doi:10.1007/s10686-014-9383-4 2014
[27]

Rauer, C

H. Rauer, C. Aerts, J. Cabrera, PLATO Team, Astronomische Nachrichten 337(8-9), 961 (2016). DOI 10.1002/asna.201612408

work page doi:10.1002/asna.201612408 2016
[28]

European Planetary Science Congress , year = 2022, month = sep, eid =

G. Tinetti, P. Eccleston, T. Lueftinger, et al., inEuropean Planetary Science Congress(2022), pp. EPSC2022–1114. DOI 10.5194/epsc2022-1114

work page doi:10.5194/epsc2022-1114 2022
[29]

D.G. York, J. Adelman, J.E. Anderson, Jr., et al., The Astronomical Jour- nal120(3), 1579 (2000). DOI 10.1086/301513

work page doi:10.1086/301513 2000
[30]

Gulati, L

R.K. Gulati, L. Altamirano, Astrophysics and Space Science273, 73 (2000). DOI 10.1023/A:1002699908879

work page doi:10.1023/a:1002699908879 2000
[31]

G. Li, Z. Lu, J. Wang, Z. Wang, arXiv e-prints arXiv:2502.15300 (2025). DOI 10.48550/arXiv.2502.15300

work page doi:10.48550/arxiv.2502.15300 2025
[32]

Bue, T.F

B.D. Bue, T.F. Stepinski, Computers and Geosciences32(5), 604 (2006). DOI 10.1016/j.cageo.2005.09.004

work page doi:10.1016/j.cageo.2005.09.004 2006
[33]

Stepinski, S

T.F. Stepinski, S. Ghosh, R. Vilalta, inDiscovery Science, ed. by L. Todor- ovski, N. Lavraˇc, K.P. Jantke (Springer Berlin Heidelberg, Berlin, Heidelberg, 2006), pp. 255–266

2006
[34]

Stepinski, R

T. Stepinski, R. Vilalta, S. Ghosh, IEEE Intelligent Systems22(6), 100 (2007). DOI 10.1109/MIS.2007.114

work page doi:10.1109/mis.2007.114 2007
[35]

Stepinski, M.P

T.F. Stepinski, M.P. Mendenhall, B.D. Bue, Icarus203(1), 77 (2009). DOI 10.1016/j.icarus.2009.04.026

work page doi:10.1016/j.icarus.2009.04.026 2009
[36]

Gilmore, R

M.S. Gilmore, R. Casta ˜no, T. Mann, et al., Journal of Geophysical Re- search105(E12), 29223 (2000). DOI 10.1029/2000JE001275 Machine Learning as a Transformative Tool for (Exo-)Planetary Science 23

work page doi:10.1029/2000je001275 2000
[37]

Bornstein, R

B. Bornstein, R. Castano, M. Gilmore, et al., in2005 IEEE Aerospace Con- ference(2005), pp. 378–384. DOI 10.1109/AERO.2005.1559330

work page doi:10.1109/aero.2005.1559330 2005
[38]

Gilmore, B

M.S. Gilmore, B. Bornstein, M.D. Merrill, et al., Icarus195(1), 169 (2008). DOI https://doi.org/10.1016/j.icarus.2007.11.025. URL https://www.sciencedirect.com/science/article/pii/S0019103507005982

work page doi:10.1016/j.icarus.2007.11.025 2008
[39]

Y. Zhao, X. Dumusque, M. Cretignier, et al., Astronomy & Astrophysics687, A281 (2024). DOI 10.1051/0004-6361/202450022

work page doi:10.1051/0004-6361/202450022 2024
[40]

E. Agol, J. Steffen, R. Sari, W. Clarkson, Monthly Notices of the Royal Astro- nomical Society359(2), 567 (2005). DOI 10.1111/j.1365-2966.2005.08922.x

work page doi:10.1111/j.1365-2966.2005.08922.x 2005
[41]

2012, , 761, 122, 10.1088/0004-637X/761/2/122

Y. Lithwick, J. Xie, Y. Wu, The Astrophysical Journal761(2), 122 (2012). DOI 10.1088/0004-637X/761/2/122

work page doi:10.1088/0004-637x/761/2/122 2012
[42]

2014, , 790, 58, 10.1088/0004-637X/790/1/58

D. Nesvorn´ y, D. Vokrouhlick´ y, The Astrophysical Journal790(1), 58 (2014). DOI 10.1088/0004-637X/790/1/58

work page doi:10.1088/0004-637x/790/1/58 2014
[43]

E. Agol, K. Deck, The Astrophysical Journal818(2), 177 (2016). DOI 10.3847/0004-637X/818/2/177

work page doi:10.3847/0004-637x/818/2/177 2016
[44]

2013, , 777, 3, 10.1088/0004-637X/777/1/3

D. Nesvorn´ y, D. Kipping, D. Terrell, et al., The Astrophysical Journal777(1), 3 (2013). DOI 10.1088/0004-637X/777/1/3

work page doi:10.1088/0004-637x/777/1/3 2013
[45]

J.W. Xie, Y. Wu, Y. Lithwick, The Astrophysical Journal789(2), 165 (2014). DOI 10.1088/0004-637X/789/2/165

work page doi:10.1088/0004-637x/789/2/165 2014
[46]

W. Zhu, C. Petrovich, Y. Wu, et al., The Astrophysical Journal860(2), 101 (2018). DOI 10.3847/1538-4357/aac6d5

work page doi:10.3847/1538-4357/aac6d5 2018
[47]

Leleu, G

A. Leleu, G. Chatel, S. Udry, et al., Astronomy & Astrophysics655, A66 (2021). DOI 10.1051/0004-6361/202141471

work page doi:10.1051/0004-6361/202141471 2021
[48]

Carter, E

J.A. Carter, E. Agol, W.J. Chaplin, et al., Science337(6094), 556 (2012). DOI 10.1126/science.1223269

work page doi:10.1126/science.1223269 2012
[49]

J ´egou, M

S. J ´egou, M. Drozdzal, D. Vazquez, et al., arXiv e-prints arXiv:1611.09326 (2016). DOI 10.48550/arXiv.1611.09326

work page doi:10.48550/arxiv.1611.09326 2016
[50]

U-Net: Convolutional Networks for Biomedical Image Segmentation

O. Ronneberger, P. Fischer, T. Brox, arXiv e-prints arXiv:1505.04597 (2015). DOI 10.48550/arXiv.1505.04597

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1505.04597 2015
[51]

Leleu, J.B

A. Leleu, J.B. Delisle, R. Mardling, et al., Astronomy & Astrophysics661, A141 (2022). DOI 10.1051/0004-6361/202142822

work page doi:10.1051/0004-6361/202142822 2022
[52]

Leleu, J.B

A. Leleu, J.B. Delisle, S. Udry, et al., Astronomy & Astrophysics669, A117 (2023). DOI 10.1051/0004-6361/202244132

work page doi:10.1051/0004-6361/202244132 2023
[53]

Leleu, J.B

A. Leleu, J.B. Delisle, R. Burn, et al., Astronomy & Astrophysics687, L1 (2024). DOI 10.1051/0004-6361/202450587

work page doi:10.1051/0004-6361/202450587 2024
[54]

Davoult, Y

J. Davoult, Y. Alibert, L. Mishra, Astronomy & Astrophysics689, A309 (2024). DOI 10.1051/0004-6361/202449330

work page doi:10.1051/0004-6361/202449330 2024
[55]

Davoult, R

J. Davoult, R. Eltschinger, Y. Alibert, Astronomy & Astrophysics696, A94 (2025). DOI 10.1051/0004-6361/202452434

work page doi:10.1051/0004-6361/202452434 2025
[56]

Emsenhuber, C

A. Emsenhuber, C. Mordasini, M. Mayor, et al., Astronomy & Astro- physics701, A64 (2025). DOI 10.1051/0004-6361/202452485

work page doi:10.1051/0004-6361/202452485 2025
[57]

Alibert, F

Y. Alibert, F. Carron, A. Fortier, et al., Astronomy & Astrophysics558, A109 (2013). DOI 10.1051/0004-6361/201321690

work page doi:10.1051/0004-6361/201321690 2013
[58]

2021a, Astronomy & Astrophysics, 656, A69, doi: 10.1051/0004-6361/202038553

A. Emsenhuber, C. Mordasini, R. Burn, et al., Astronomy & Astrophysics656, A69 (2021). DOI 10.1051/0004-6361/202038553 24 Davoult et al

work page doi:10.1051/0004-6361/202038553 2021
[59]

Attention Is All You Need

A. Vaswani, N. Shazeer, N. Parmar, et al., arXiv e-prints arXiv:1706.03762 (2017). DOI 10.48550/arXiv.1706.03762

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1706.03762 2017
[60]

Soummer, Astrophysical Journal Letters618, 161 (2005)

R. Soummer, Astrophysical Journal Letters618, 161 (2005). DOI 10.1086/427923. URL https://doi.org/10.1086/427923

work page doi:10.1086/427923 2005
[61]

Marois, D

C. Marois, D. Lafreniere, R. Doyon, et al., ApJ641(1), 556 (2006)

2006
[62]

Cantero, O

C. Cantero, O. Absil, C.H. Dahlqvist, M. Van Droogenbroeck, Astronomy & Astrophysics680, A86 (2023). DOI 10.1051/0004-6361/202346085. URL http://dx.doi.org/10.1051/0004-6361/202346085

work page doi:10.1051/0004-6361/202346085 2023
[63]

Cantalloube, C

F. Cantalloube, C. Gomez-Gonzalez, O. Absil, et al., inAdaptive Optics Systems VII, ed. by D. Schmidt, L. Schreiber, E. Vernet (SPIE, 2020), p. 321. DOI 10.1117/12.2574803. URL http://dx.doi.org/10.1117/12.2574803

work page doi:10.1117/12.2574803 2020
[64]

Desidera, G

S. Desidera, G. Chauvin, M. Bonavita, et al., Astronomy & Astro- physics651, A70 (2021). DOI 10.1051/0004-6361/202038806. URL http://dx.doi.org/10.1051/0004-6361/202038806

work page doi:10.1051/0004-6361/202038806 2021
[65]

2023 , note =

V. Christiaens, C.A.G. Gonzalez, R. Farkas, et al., Journal of Open Source Software8(81), 1 (2023). DOI 10.21105/joss.04774. URL https://doi.org/10.21105/joss.04774

work page doi:10.21105/joss.04774 2023
[66]

Bonse, T.D

M.J. Bonse, T.D. Gebhard, F.A. Dannert, et al., The Astronomical Jour- nal169(4), 194 (2025). DOI 10.3847/1538-3881/adab79

work page doi:10.3847/1538-3881/adab79 2025
[67]

, keywords =

M. Auvergne, P. Bodin, L. Boisnard, et al., Astronomy & Astrophysics506(1), 411 (2009). DOI 10.1051/0004-6361/200810860

work page doi:10.1051/0004-6361/200810860 2009
[68]

Gonzalez, Monthly Notices of the Royal Astronomical Society285(2), 403 (1997)

G. Gonzalez, Monthly Notices of the Royal Astronomical Society285(2), 403 (1997). DOI 10.1093/mnras/285.2.403

work page doi:10.1093/mnras/285.2.403 1997
[69]

Santos, G

N.C. Santos, G. Israelian, M. Mayor, arXiv e-prints astro-ph/0109018 (2001). DOI 10.48550/arXiv.astro-ph/0109018

work page internal anchor Pith review doi:10.48550/arxiv.astro-ph/0109018 2001
[70]

, year = 1996, month = nov, volume =

J.B. Pollack, O. Hubickyj, P. Bodenheimer, et al., Icarus 124(1), 62 (1996). DOI 10.1006/ICAR.1996.0190. URL https://www.sciencedirect.com/science/article/pii/S0019103596901906?via%3Dihub

work page doi:10.1006/icar.1996.0190 1996
[71]

, keywords =

R.I. Dawson, R.A. Murray-Clay, Astrophysical Journal Letters767(2), L24 (2013). DOI 10.1088/2041-8205/767/2/L24

work page doi:10.1088/2041-8205/767/2/l24 2013
[72]

, keywords =

J.A. Johnson, K.M. Aller, A.W. Howard, J.R. Crepp, Publications of the As- tronomical Society of the Pacific122(894), 905 (2010). DOI 10.1086/655775

work page doi:10.1086/655775 2010
[73]

Bonfils, X

X. Bonfils, X. Delfosse, S. Udry, et al., Astronomy & Astrophysics549, A109 (2013). DOI 10.1051/0004-6361/201014704

work page doi:10.1051/0004-6361/201014704 2013
[74]

E. Melo, D. Souto, K. Cunha, et al., The Astrophysical Journal973(2), 90 (2024). DOI 10.3847/1538-4357/ad5004

work page doi:10.3847/1538-4357/ad5004 2024
[75]

Yun, Y.S

S. Yun, Y.S. Lee, Y.K. Kim, et al., The Astrophysical Journal971(1), 35 (2024). DOI 10.3847/1538-4357/ad5722

work page doi:10.3847/1538-4357/ad5722 2024
[76]

Mishra, Y

L. Mishra, Y. Alibert, S. Udry, C. Mordasini, Astronomy & Astrophysics670, A69 (2023). DOI 10.1051/0004-6361/202244705

work page doi:10.1051/0004-6361/202244705 2023
[77]

2023, The European Physical Journal Plus, 138, 181, doi: 10.1140/epjp/s13360-023-03784-x 17

A. Emsenhuber, C. Mordasini, R. Burn, European Physical Journal Plus 138(2), 181 (2023). DOI 10.1140/epjp/s13360-023-03784-x

work page doi:10.1140/epjp/s13360-023-03784-x 2023
[78]

Bickel, C

V.T. Bickel, C. Lanaras, A. Manconi, et al., IEEE Transactions on Geoscience and Remote Sensing57(6), 3501 (2019). DOI 10.1109/TGRS.2018.2885280 Machine Learning as a Transformative Tool for (Exo-)Planetary Science 25

work page doi:10.1109/tgrs.2018.2885280 2019
[79]

Bickel, S.J

V.T. Bickel, S.J. Conway, P.A. Tesson, et al., IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing13, 2831 (2020). DOI 10.1109/JSTARS.2020.2991588

work page doi:10.1109/jstars.2020.2991588 2020
[80]

Bickel, J

V.T. Bickel, J. Aaron, A. Manconi, et al., Nature Communications11, 2862 (2020). DOI 10.1038/s41467-020-16653-3

work page doi:10.1038/s41467-020-16653-3 2020

Showing first 80 references.