The DOI matches its Crossref record; 105 of the 105 references it cites were found in a registry or an index.
The CAMELS Project: Cosmology and Astrophysics with Machine-learning Simulations
Open accessAbstract
We present the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project. CAMELS is a suite of 4233 cosmological simulations of 25 h − 1 Mpc 3 volume each: 2184 state-of-the-art (magneto)hydrodynamic simulations run with the AREPO and GIZMO codes, employing the same baryonic subgrid physics as the IllustrisTNG and SIMBA simulations, and 2049 N-body simulations. The goal of the CAMELS project is to provide theory predictions for different observables as a function of cosmology and astrophysics, and it is the largest suite of cosmological (magneto)hydrodynamic simulations designed to train machine-learning algorithms. CAMELS contains thousands of different cosmological and astrophysical models by way of varying Ω m , σ 8, and four parameters controlling stellar and active galactic nucleus feedback, following the evolution of more than 100 billion particles and fluid elements over a combined volume of ( 400 h − 1 Mpc ) 3 . We describe the simulations in detail and characterize the large range of conditions represented in terms of the matter power spectrum, cosmic star formation rate density, galaxy stellar mass function, halo baryon fractions, and several galaxy scaling relations. We show that the IllustrisTNG and SIMBA suites produce roughly similar distributions of galaxy properties over the full parameter space but significantly different halo baryon fractions and baryonic effects on the matter power spectrum. This emphasizes the need for marginalizing over baryonic effects to extract the maximum amount of information from cosmological surveys. We illustrate the unique potential of CAMELS using several machine-learning applications, including nonlinear interpolation, parameter estimation, symbolic regression, data generation with Generative Adversarial Networks, dimensionality reduction, and anomaly detection.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Planck 2018 results: VI. Cosmological parameters
Planck Collaboration, Aghanim, N., Akrami, Y., Ashdown, M., Aumont, J., Baccigalupi, C., Ballardini, M., Banday, A. J., Barreiro, R. B., Bartolo, N., et al. (2020) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201833910 · Cited by 14,258
The cosmological simulation code gadget-2
Springel, V. (2005) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2005.09655.x · Cited by 6,368
The Global Schmidt law in star forming galaxies
Kennicutt, R., & Jr. (1997) · The Astrophysical Journal · doi:10.1086/305588 · Cited by 4,027 · cited 1×
“Stars form from molecular gas at a rate given by the H2 density divided by the dynamical time: SFR= ∗ρH2/tdyn, where ∗ = 0.02 (Kennicutt 1998) and the H2 fraction is computed based on the metallicity and local column density following Krumholz & Gnedin (2011).”
MethodInfluentialThe EAGLE project: simulating the evolution and assembly of galaxies and their environments
Schaye, J., Crain, R. A., Bower, R. G., Furlong, M., Schaller, M., Theuns, T., Dalla Vecchia, C., Frenk, C. S., McCarthy, I. G., Helly, J. C., et al. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stu2058 · Cited by 3,601
The evolution of large-scale structure in a universe dominated by cold dark matter
Davis, M., Efstathiou, G., Frenk, C. S., & White, S. D. M. (1985) · The Astrophysical Journal · doi:10.1086/163168 · Cited by 3,397
Populating a cluster of galaxies - I. Results at \fontshape{it}{z}=0
Springel, V., White, S. D. M., Tormen, G., & Kauffmann, G. (2001) · Monthly Notices of the Royal Astronomical Society · doi:10.1046/j.1365-8711.2001.04912.x · Cited by 2,852
On Spherically Symmetrical Accretion
Bondi, H. (1952) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/112.2.195 · Cited by 2,465 · cited 2×
“SMBH growth by gas accretion follows the spherical Bondi (1952) parameterization, limited by the Eddington rate.”
BackgroundMethodE pur si muove: Galilean-invariant cosmological hydrodynamical simulations on a moving mesh
Springel, V. (2009) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2009.15715.x · Cited by 2,427 · cited 3×
“Simulations CAMELS is a suite of 4,233 numerical simulations, including both N-body simulations run with GadgetIII (Springel 2005) and state-of-the-art (magneto)hydrodynamic simulations run with AREPO (Springel 2010) and GIZMO (Hopkins 2015).”
MethodStatistical Properties of X‐Ray Clusters: Analytic and Numerical Comparisons
Bryan, G. L., & Norman, M. L. (1998) · The Astrophysical Journal · doi:10.1086/305262 · Cited by 2,372
Self-citation
Cited by
Sorted by citations
Items 201–300 of 302
Compressed 3D Lyman- α forest bispectrum
de Belsunce, R., Sullivan, J. M., & McDonald, P. (2026) · Physical review. D/Physical review. D. · doi:10.1103/7167-57fs · Cited by 3
Strong Evidence for Cosmic-Ray-supported ∼ L * Galaxy Halos via X-Ray and tSZ Constraints
Ponnada, S. B., Hopkins, P. F., Lu, Y. S., Silich, E. M., Butsky, I. S., & Kereš, D. (2026) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/ae2fd9 · Cited by 3
Cosmological back-reaction of baryons on dark matter in the CAMELS simulations
Gebhardt, M., Anglés‐Alcázar, D., Genel, S., Nagai, D., Oh, B. K., Medlock, I., Mercedes-Feliz, J., Sutherland, S., Lee, M. E., Sims, X., et al. (2026) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stag525 · Cited by 3
Self-citationLilie, E., Rose, J. C., Lisanti, M., Garcia, A. M., Torrey, P., Kollmann, K. E., Li, J., Mostow, O., Wang, B. Y., O’Neil, S., et al. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae5c9b · Cited by 3
“The two parameters κ w strongly influence the stellar mass of a galaxy ( A. Pillepich et al. 2018; F. Villaescusa-Navarro et al. 2021; A. M. Garcia et al. 2025; J. C. Rose et al. 2025a ) .”
Self-citationExploring the halo-galaxy connection with probabilistic approaches
Rodrigues, N. V. N., de Santi, N. S. M., Abramo, R., & Montero-Dorta, A. D. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202453284 · Cited by 3
“Comparisons between simulations with di ff erent galaxy formation models should be helpful and informative to evaluate (and possibly extend) the range of applicability of our models (e.g. di ff erent sub-grid physics as explored in CAMELS (Villaescusa-Navarro et al. 2021)).”
Essay: Mapping Luminous and Dark Matter in the Universe
Chisari, N. E. (2025) · Physical Review Letters · doi:10.1103/physrevlett.134.080001 · Cited by 3
Cosmology with One Galaxy: Autoencoding the Galaxy Properties Manifold
Lue, A., Genel, S., Villaescusa-Navarro, F., & Ho, M. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/add724 · Cited by 3
“The CAMELS project (Villaescusa-Navarro et al. 2021) investigates the link between cosmological parameters and astrophysical observations through a suite of cosmological simulations containing hundreds of thousands of galaxies, each characterized by various internal properties.”
InfluentialSelf-citationCosmology with Topological Deep Learning
Lee, J.-Y., & Villaescusa-Navarro, F. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/ade806 · Cited by 3
“The CAMELS suite comprises both cosmological N - body simulations and (magneto-)hydrodynamic simulations (Villaescusa-Navarro et al. 2021, 2023; Ni et al. 2023).”
Self-citationA differentiable model of the evolution of dark matter halo concentration
Stevanovich, D., Hearin, A. P., & Nagai, D. (2023) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stad2854 · Cited by 3
Kinematic Sunyaev-Zel′dovich pairwise velocity reconstruction with machine learning
Gong, Y., & Bean, R. (2024) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.109.123525 · Cited by 3
A neural network model for the cosmic dispersion measure in the CAMELS simulations
Guo, Q., & Lee, K. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf730 · Cited by 3
Anisotropic cosmology using observational datasets: Exploring via machine learning approaches
Bhardwaj, V. K., Kalra, M., Garg, P., & Ray, S. (2025) · Physics of the Dark Universe · doi:10.1016/j.dark.2025.102012 · Cited by 3
On the Effects of Parameters on Galaxy Properties in CAMELS and the Predictability of Ωm
Contardo, G., Trotta, R., Gioia, S. D., Hogg, D. W., & Villaescusa-Navarro, F. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/addd08 · Cited by 2
“We first focus our analysis on CAMELS-IllustrisTNG (Villaescusa-Navarro et al. 2021, 2023), a suite of hydrodynamic simulations using the moving-mesh AREPO code (Springel 2010; Weinberger et al. 2020) and based on the IllustrisTNG framework (Weinberger et al. 2017; Springel et al. 2018; Pillepich et al. 2018b; Nelson…”
InfluentialSelf-citationEmulating dark matter halo merger trees with graph generative models
Nguyên, T., Modi, C., Mishra-Sharma, S., Yung, L. Y. A., & Somerville, R. S. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf1487 · Cited by 2
Chowdhary, A., & Chatterjee, S. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/adfb6d · Cited by 2
A Gigaparsec-scale Hydrodynamic Volume Reconstructed with Deep Learning
Jacobus, C., de Belsunce, R., Chabanier, S., Harrington, P., Emberson, J. D., Lukić, Z., & Habib, S. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/ae0720 · Cited by 2
Liu, R. H., Hadzhiyska, B., Ferraro, S., Bose, S., & Hernández‐Aguayo, C. (2026) · Physical review. D/Physical review. D. · doi:10.1103/3vzd-hxg1 · Cited by 4
Krywonos, J., Kvasiuk, Y., Johnson, M. C., & Münchmeyer, M. (2025) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/03/037 · Cited by 3
“Finally, we summarize our results in Section (9) and discuss future avenues to apply this to real data.”
AI for science: Progress, challenges, and perspectives
Xu, Y., Shao, Z., Liu, X., Li, Y., An, Z., Fu, C., Huang, C., Zhang, L., Gao, F., Li, J., et al. (2026) · The Innovation · doi:10.1016/j.xinn.2026.101530 · Cited by 6
Self-citationMap Reconstruction of Radio Observations with Conditional Invertible Neural Networks
Zhang, H., Zuo, S., & Zhang, L. (2023) · Research in Astronomy and Astrophysics · doi:10.1088/1674-4527/acd0ee · Cited by 2
Gluck, N., Oppenheimer, B. D., Nagai, D., Villaescusa-Navarro, F., & Anglés‐Alcázar, D. (2023) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stad3784 · Cited by 2
Self-citationRissaki, A., Pavlou, O., Fotakis, D. A., Lesta, V. P., & Efstathiou, A. (2024) · Astronomy and Computing · doi:10.1016/j.ascom.2024.100823 · Cited by 2
A self-similar model of galaxy formation and dark halo relaxation
Velmani, P., & Paranjape, A. (2024) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2024/05/080 · Cited by 2
GAINN: The Galaxy Assembly and Interaction Neural Networks for High-redshift JWST Observations
Santos-Olmsted, L., Barrow, K. S. S., & Hartwig, T. (2024) · The Astrophysical Journal · doi:10.3847/1538-4357/ad46fd · Cited by 2
Martin-Alvarez, S., Iršič, V., Koudmani, S., Bourne, M. A., Bigwood, L., & Sijacki, D. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf470 · Cited by 2
Probabilistic Lagrangian bias estimators and the cumulant bias expansion
Stücker, J., Pellejero-Ibáñez, M., Angulo, R. E., Maion, F., & Voivodic, R. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202451176 · Cited by 2
“The results of such simulations depend strongly on the associated parameters and are therefore severely limited in their predictive ability (e.g. Genel et al. 2019; Villaescusa-Navarro et al. 2021).”
On the impacts of halo model implementations in Sunyaev-Zeldovich cross-correlation analyses
Popik, C., Battaglia, N., Kusiak, A., Bolliet, B., & Hill, J. C. (2025) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2025/10/051 · Cited by 2
Self-citationInferring Halo Masses with Graph Neural Networks
Villanueva-Domingo, P., Villaescusa-Navarro, F., Anglés‐Alcázar, D., Genel, S., Marinacci, F., Spergel, D. N., Hernquist, L., Vogelsberger, M., Davé, R., & Narayanan, D. (2022) · The Astrophysical Journal · doi:10.3847/1538-4357/ac7aa3 · Cited by 2
“For instance, if the errors are much smaller than the mean, the loss will be dominated by the mean and the errors may not be accurately computed (see Villaescusa-Navarro et al. 2021b, for further details).”
BackgroundMethodInfluentialSelf-citationMaitra, S., Cristiani, S., Viel, M., Trotta, R., & Cupani, G. (2024) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202450259 · Cited by 2
Galaxy 3D shape recovery using mixture density network
Yong, S. Y., Harborne, K. E., Foster, C., Bassett, R., Poole, G. B., & Cavanagh, M. K. (2024) · Publications of the Astronomical Society of Australia · doi:10.1017/pasa.2024.32 · Cited by 1
On the Significance of Covariance for Constraining Theoretical Models from Galaxy Observables
Jo, Y., Genel, S., Leja, J., & Wandelt, B. D. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae19e4 · Cited by 1
“Our study focuses on stellar mass functions as the observable, with varying degrees of correlation between the mass bins, and six cosmological and astrophysical parameters from the CAMELS simulations as the parameters of interest ( details in Section 2.3; F. Villaescusa-Navarro et al. 2021a ) .”
InfluentialSelf-citationEMBER-2: emulating baryons from dark matter across cosmic time with deep modulation networks
Bernardini, M., Feldmann, R., Gensior, J., Anglés‐Alcázar, D., Bassini, L., Bieri, R., Cenci, E., Tortora, L., & Faucher‐Giguère, C. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf341 · Cited by 1
Self-citationCosmological multifield emulator
Andrianomena, S., Hassan, S., & Villaescusa-Navarro, F. (2024) · Astrophysics and Space Science · doi:10.1007/s10509-025-04440-9 · Cited by 2
“The main desire to marignalize over astro-physics is that different subgrid models of astrophysics (e.g. such as the recipes to form stars and AGNs as well as their driven feedback) are degenerate and tend to reproduce similar observations (e.g. see [14, 15]).”
InfluentialSelf-citationUchida, S.-Y. S., Cooray, S., Nishizawa, A. J., Takeuchi, T. T., & Behroozi, P. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf1453 · Cited by 1
Liao, S., Irodotou, D., Maltz, M. G. A., Lovell, C. C., Jiang, Z., Newman, S., Vijayan, A. P., Punyasheel, P., Roper, W. J., Seeyave, L. T. C., et al. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf1642 · Cited by 1
One Latent to Fit Them All: A Unified Representation of Baryonic Feedback on Matter Distribution
Lin, S., Li, Y., Genel, S., Villaescusa-Navarro, F., Dai, B., 罗, W. 文. L., & 汪, Y. 洋. W. (2026) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/ae3084 · Cited by 1
“For a detailed description of the above simulations, we refer the reader to F. Villaescusa-Navarro et al. ( 2021 ) and Y. Ni et al. ( 2023 ) .”
Self-citationDetecting model misspecification in cosmology with scale-dependent normalizing flows
Akhmetzhanova, A., Cuesta-Lazaro, C., & Mishra-Sharma, S. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae107d · Cited by 1
Denario Project: Deep Knowledge Artificial Intelligence Agents for Scientific Discovery
Villaescusa-Navarro, F., Bolliet, B., Villanueva-Domingo, P., Bayer, A. E., Acquah, A., Amancharla, C., Barzilay-Siegal, A., Bermejo, P., Bilodeau, C., Cárdenas, P., et al. (2026) · PRX Intelligence · doi:10.1103/kk55-gc95 · Cited by 42
Self-citationDeriving accurate galaxy cluster masses using X-ray thermodynamic profiles and graph neural networks
Iqbal, A., Majumdar, S., Rasia, E., Pratt, G. W., de Andrés, D., Melin, J.-B., & Cui, W. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202555691 · Cited by 1
Yang, H. B., Pellejero-Ibáñez, M., Peacock, J. A., & Davé, R. (2026) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stag314 · Cited by 1
Foreground removal in HI 21 cm intensity mapping under frequency-dependent beam distortions
Gkogkou, A., Bonjean, V., Starck, J., Spinelli, M., & Tsakalides, P. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202557229 · Cited by 1
From redshift to real space: Combining linear theory with neural networks
Maragliano, E., Veena, P. G., Degni, G., & Branchini, E. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202556679 · Cited by 1
Sims, X., Anglés‐Alcázar, D., Oh, B. K., Nagai, D., Mercedes-Feliz, J., Medlock, I., Ni, Y., Lovell, C. C., & Villaescusa-Navarro, F. (2026) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stag1529 · Cited by 1
Self-citationSáez-Casares, I., Calabrese, M., Bianchi, D., Cagliari, M. S., Chiarenza, M., Christille, J. M., & Guzzo, L. (2026) · Astronomy and Computing · doi:10.1016/j.ascom.2026.101067 · Cited by 1
Intrinsic galaxy alignments in CAMELS simulations and the significant impact of baryon model
Bilsborrow, D. J. L., & Jeffrey, N. (2026) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stag229 · Cited by 1
Rojas, L. (2025) · Avances en Ciencia e Ingeniería · doi:10.65093/aci.v16.n4.2025.44 · Cited by 1
Introducing RAFIKI: Refining Active Galactic Nuclei Feedback in Kinetic Implementations
Grayson, S., Scannapieco, E. S., Davé, R., Babul, A., & Hough, R. T. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae3dac · Cited by 1
“The Cosmology and Astrophysics with MachinE Learning Simulations ( CAMELS ) consists of over 4000 runs varying the parameters of the IllustrisTNG and SIMBA subgrid physics ( F. Villaescusa-Navarro et al. 2021 ) .”
Farsian, F., Schillirò, F., Bulgarelli, A. A., Burigana, C., Cardone, V. F., Cappelli, L., Graziotti, I., Meneghetti, M., Murante, G., Parmiggiani, N., et al. (2026) · Astronomy and Computing · doi:10.1016/j.ascom.2026.101095 · Cited by 5
Mainly on the Plane: Observing the Extended, Ionized Disks of Milky Way Analogs in IllustrisTNG
Messere, M., Tchernyshyov, K., Putman, M. E., Bryan, G. L., Werk, J. K., Zheng, Y., & Schiminovich, D. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae48e8 · Cited by 1
“…to large-scale cosmological simulations that explore different star-formation and feedback models (Hopkins et al. 2014; Schaye et al. 2015; Crain et al. 2015; Tremmel et al. 2017; Nelson et al. 2019a; Peeples et al. 2019; Dav´e et al. 2019; Smith et al. 2024; Villaescusa-Navarro et al. 2021).”
Self-citationQuantum computing for astrophysics and cosmology: Results from the INAF activities
Bulgarelli, A. A., Burigana, C., Cappelli, L., Cardone, V. F., Cavuoti, S., Farsian, F., Graziotti, I., Macaluso, A., Meneghetti, M., Murante, G., et al. (2026) · Astronomy and Computing · doi:10.1016/j.ascom.2026.101108 · Cited by 1
Predicting galaxy bias using machine learning
Riveros-Jara, C., Montero-Dorta, A. D., Rodrigues, N. V. N., Amigo, P., de Santi, N. S. M., Balaguera-Antolínez, A., Abramo, R., Guzmán, N., & Artale, M. C. (2026) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202659262 · Cited by 1
Stiskalek, R., Perez, L. A., Genel, S., Somerville, R. S., Angulo, R. E., & Contreras, S. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae878b · Cited by 1
“The CAMELS project (Villaescusa-Navarro et al. 2021) represents a leading effort to address this challenge, providing thousands of hydrodynamical simulations that systematically sample two cosmological parameters (Ω m , σ 8 ) and four astrophysical feedback parameters across multiple galaxy…”
Self-citationMoser, E., Battaglia, N., Nagai, D., Lau, E. T., Valle, L. F. M. P., Villaescusa-Navarro, F., Amodeo, S., Anglés‐Alcázar, D., Bryan, G. L., Davé, R., et al. (2022) · The Astrophysical Journal · doi:10.3847/1538-4357/ac70c6 · Cited by 38
“An ambitious effort to this end has begun through the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project (Villaescusa-Navarro et al. 2021, 2022).”
BackgroundMethodSelf-citationRigo, M., Trotta, R., & Viel, M. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf948 · Cited by 1
Ullmo, M., Aghanim, N., Decelle, A., & Aragón-Calvo, M. A. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202449845 · Cited by 1
Moser, E., Amodeo, S., Battaglia, N., Alvarez, M. A., Ferraro, S., & Schaan, E. (2021) · eScholarship (California Digital Library) · Cited by 1
Self-citationA Multi-Wavelength, Multi-Model Exploration of How Feedback Disrupts Gaseous Atmospheres
Oppenheimer, B. D., Nagai, D., Lau, E. T., Singh, P., Contreras, A. B., Gluck, N., Jones, J. D., Medlock, I., & Villaescusa-Navarro, F. (2022) · doi:10.3847/25c2cfeb.84739b61 · Cited by 1
Self-citationProbabilistic Galaxy Field Generation with Diffusion ModelsPreprint
Sether, T., Giusarma, E., & Reyes-Hurtado, M. (2025) · Qeios · doi:10.32388/4ix01n · Cited by 1
Mimicking the halo–galaxy connection using machine learning
de Santi, N. S. M., Rodrigues, N. V. N., Montero-Dorta, A. D., Abramo, L. R., Tucci, B., & Artale, M. C. (2022) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stac1469
Ferragamo, A., de Andrés, D., Sbriglio, A., Cui, W., Petris, M. D., Yepes, G., Dupuis, R., Jarraya, M., Lahouli, I., Luca, F. D., et al. (2024) · EPJ Web of Conferences · doi:10.1051/epjconf/202429300019
guppy i : a code for reducing the storage requirements of cosmological simulations
Mansfield, P., & Abel, T. (2024) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stae894
Wu, Y.-D., Hong, W., & Zhang, T.-J. (2026) · Research in Astronomy and Astrophysics · doi:10.1088/1674-4527/ae4bb3 · Cited by 4
“…to estimate stellar ages [22], L (Lick Indices) analyzes specific absorption lines to determine age [23], D (D4000) measures the 4000 ˚A break to estimate stellar age [24], and ML (Machine Learning) applies algorithms to large datasets for estimating stellar ages and cosmological parameters [25].”
MethodInterpretability of deep-learning methods applied to large-scale structure surveys
Aymerich, G., Kacprzak, T., Refregier, A. R., & Thomsen, A. (2026) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202553963
DeepBench: A simulation package for physical benchmarking data
Voetberg, M., Livaudais, A., Nevin, R., Paul, O., & Nord, B. (2025) · The Journal of Open Source Software · doi:10.21105/joss.06774
Deep learning generated observations of galaxy clusters from dark-matter-only simulations
Caro, A., de Andres, D., Cui, W., Yepes, G., Petris, M. D., Ferragamo, A., Schiltz, F., & Nef, A. (2024) · RAS Techniques and Instruments · doi:10.1093/rasti/rzaf007
Predicting halo formation time using machine learning
Srivastava, A., Cui, W., de Andrés, D., Golden-Marx, J. B., Rasia, E., & Zu, Y. (2025) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202453165 · Cited by 1
Much ado about nothing: galaxy formation and galactic outflows in cosmic voids
Pan, Y. X., Teyssier, R., Steinwandel, U. P., & Pisani, A. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf1112
The evolving role of astrophysical modelling in dark matter halo relaxation response
Velmani, P., & Paranjape, A. (2025) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2025/07/026
“This allows us to examine the effects of baryonic processes on dark matter halo properties across different scales and epochs.”
Probabilistic cosmological inference on HI tomographic data
Andrianomena, S. (2025) · Astrophysics and Space Science · doi:10.1007/s10509-025-04470-3
“As the objective of our study is a robust retrieval of cosmological information from HI tomographic data, we make use of the 3D grids of the multifield dataset (Villaescusa-Navarro et al. 2022b) of the CAMELS Project (Villaescusa-Navarro et al. 2021b, 2022a).”
Large language models – the future of fundamental physics?
Heneka, C. S., Nieser, F., Ore, A., Plehn, T., & Schiller, D. (2026) · SciPost Physics · doi:10.21468/scipostphys.20.3.070 · Cited by 13
Variational autoencoder for generating realistic N -body simulations for dark matter halos
Chacón, J., Gómez-Vargas, I., Menchaca-Méndez, R., & Vazquez, J. A. (2026) · Physical review. D/Physical review. D. · doi:10.1103/b6lj-rlff · Cited by 1
“Numerical simulations such as Illustris [30], Millennium [31], and CAMELS [14] are widely employed, offering a controlled environment to model the non-linear dynamics of dark matter.”
Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation
Ma, C., Sun, Z., Tao, J., Cai, Z., Ting, Y.-S., Huang, S., & Li, M. (2026) · The Astrophysical Journal Supplement Series · doi:10.3847/1538-4365/ae1f10
“The performance of ML models is often limited by the representativeness and quality of the training data, which are usually from simulations or human annotations (e.g., Hart et al. 2016; Hausen & Robertson 2020; Villaescusa-Navarro et al. 2021; Wang et al. 2022; Ono et al. 2024).”
Low, R., Adhikari, R., Rose, J. C., O’Neil, S., Medvedev, M. V., Torrey, P., & Vogelsberger, M. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf2259
Self-citationInterpreting atmospheric neural networks: insights from explainable AI
Vojtekova, A., Νικολάου, Ν., Yip, K. H., Vénot, O., Al-Refaie, A. F., Merín, B., & Waldmann, I. P. (2026) · RAS Techniques and Instruments · doi:10.1093/rasti/rzag002
Spatially resolved stellar-to-total dynamical mass relation
Scholz-Díaz, L., Gallazzi, A., Zibetti, S., & Mattolini, D. (2026) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202556706
Forecasts and simulations for relativistic corrections to the Sunyaev-Zeldovich effect
Kuhn, L., Li, Z., & Coulton, W. R. (2026) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/02/059
“Unfortunately hydrodynamical simulations are too expensive to use directly for simulating sky maps for large-area surveys [however; see 45, 46, for work in that direction].”
Li, H., Li, W., Wu, Q., & Niu, Z.-M. (2026) · Chinese Physics C · doi:10.1088/1674-1137/ae50e6
The baryon budget of galaxies across the first billion years
Maio, U., & Péroux, C. (2026) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202557624
Shi, H., Huang, Z., Yan, Q., Zhou, J., Lü, G., & Chen, X. (2026) · Physics Letters B · doi:10.1016/j.physletb.2026.140371
A New Method to Simulate Dark Matter–Baryon Interactions and Application to an Isolated Disk Galaxy
Hainje, C., & Farrar, G. R. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae95f2
“…2020 ) find that small-scale suppression of the matter power spectrum varies widely among galaxy formation models and can reach up to 30%, while F. Villaescusa-Navarro et al. ( 2021 ) find that varying feedback parameters within a single model by a factor of a few can have a comparably large…”
Emulation and prediction of cosmic web simulations through deep learning
Ullmo, M. (2022) · theses.fr (ABES) · doi:10.70675/573f6397z1449z43b8z9139z7de47c7a67c5
On galaxy cluster modelling in the context of cosmological analyses
Gallo, S. (2024) · theses.fr (ABES) · doi:10.70675/fcf9d2d1zb332z4d9azae94z170d5e60471e
Multiscale Modelling of Galaxy Collisions with Integrated Resistive MHD and Stellar Feedback
Khalili, M. N. (2026) · Indian Journal of Advanced Physics · doi:10.54105/ijap.a1073.06010426
Pirecki, M., Tillman, M., Burkhart, B., Tonnesen, S. K., & Bird, S. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae589d
“This work uses data from the CAMELS project ( F. Villaescusa-Navarro et al. 2021; Y. Ni et al. 2023 ) .”
Self-citationNuclear β -decay half-life predictions with a physics-information machine learning approach
Li, W. F., Sun, T., Niu, Z.-M., & Liang, H. (2026) · Physical Review C · doi:10.1103/klkv-vk36
Tillman, M., Burkhart, B., Mingarelli, C. M. F., Casey-Clyde, J. A., Hernquist, L., Bose, S., Regős, E., & Hernández‐Aguayo, C. (2026) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/ae6fbc
“The Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project consists of thousands of N-body and state-of-the-art hydrodynamic simulations that span a vast cosmological and astrophysical parameter space (Villaescusa-Navarro et al. 2021, 2023).”
Self-citationAssembly bias and local Primordial non-Gaussianity from DESI DR1 quasars
Fondi, E., Verde, L., Chaussidon, E., Aguilar, J., Ahlen, S. P., BenZvi, S., Bianchi, D., Brooks, D., Claybaugh, T., Cuceu, A., et al. (2026) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/06/062
“Motivated by these considerations, in this paper we use the state-of-the-art IllustrisTNG [49, 50] hydrodynamical simulations and the CAMELS simulations [51] to construct a QSO sample reflecting the selection properties of the DESI survey.”
Li, W. C., Niu, Z.-M., Liang, H. Z., Niu, Y. F., & Sun, B.-H. (2026) · Physics Letters B · doi:10.1016/j.physletb.2026.140696
Linking Warm Dark Matter to Merger Tree Histories via Deep Learning Networks
Leisher, I., Torrey, P., Garcia, A. M., Rose, J. C., Villaescusa-Navarro, F., Lubberts, Z., Farahi, A., O’Neil, S., Shen, X., Mostow, O., et al. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae7bec
“For example, the CAMELS project (Villaescusa-Navarro et al. 2021a, 2023, 2022b) and the DREAMS project (Rose et al. 2025) both employ ML methods in simulation suites tracking DM particles to study structure evolution as a function of cosmology and astrophysics.”
Self-citationSahyadri : a simulation suite for the cosmology dependence of the cosmic web
Dhawalikar, S., Alam, S., Paranjape, A., & Banerjee, A. (2026) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/07/028
“The CAMELS suite [16] bridges these categories by varying both cosmological and astrophysical parameters at a mass resolution comparable to that considered in the present work, but with volumes limited to (50 h − 1 Mpc) 3 Conversely, simulation suites designed explicitly for cosmological…”
Replicating weak-lensing summary-statistic covariances with normalizing flows
Anonymous, Thiele, L., & Liu, J. (2026) · Physical review. D/Physical review. D. · doi:10.1103/lbb5-2kbt
Srinivasan, S., Prabhu, S., Lehman, K., Ajiv Krishnan, V., & Weller, J. (2026) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/07/058
Machine Learning in Molecular Dynamics from Reactive Chemistry to Astrophysical Systems
Shukla, N., Changmai, G., Paul, A. K., Shukla, S., Ahmed, G. A., & Mahanta, H. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10757-7
“Reproduced with permission from [101] environments.”
Path measures for stochastic galaxy formation on layered halo graphs
Yang, D. (2026) · Physical review. D/Physical review. D. · doi:10.1103/nmd6-zkc1
“CAMELS-style benchmark suites motivate robust cross-model evaluation by exposing subgrid and domain shift in a controlled setting [28, 29].”
APOSTLE versus AURIGA Simulations: How Subgrid Models Shape Milky Way Analogs
Hu, J., Yang, H., & Gao, L. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae8a48
“A cleaner separation of feedback and hydrodynamic effects would require controlled experiments in which feedback prescriptions are varied within a same numerical framework, such as the CAMELS simulation ( F. Villaescusa-Navarro et al. 2021 ) .”
Gas reservoirs predict future galaxy growth beyond halo assembly history in CAMELS
Bhatia, K. (2026) · New Astronomy · doi:10.1016/j.newast.2026.102638
Multiscale Rotational–Compressive Organization in Cosmological Baryonic Flows
Mouhali, W. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae9bba
“The present analysis is based on publicly available hydrodynamic grids extracted from the CAMELS ( Cosmology and Astrophysics with Machine Learning Simulations ) project ( F. Villaescusa-Navarro et al. 2021 ) .”
Introducing sapphire : Towards Hybrid Physics-informed, Data-driven Modeling of Galaxy Formation
Pandya, V., Bryan, G. L., Makinen, T. L., Gabrielpillai, A., Carr, C., Fielding, D. B., Hernquist, L., Ho, M., Iyer, K. G., Jespersen, C. K., et al. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/aea55e
“This is slowly changing thanks to expensive simulation suites like AGORA (Kim et al. 2014), CAMELS (Villaescusa-Navarro et al. 2021) and FLAMINGO (Schaye et al. 2023; Kugel et al. 2023) as well as the recent proliferation of machine learning techniques, which enable the training of emulators for…”
InfluentialSelf-citation
Metadata
- Authors
- Villaescusa-Navarro, F., Anglés-Alcázar, D., Genel, S., Spergel, D. N., S. Somerville, R., Dave, R., Pillepich, A., Hernquist, L., Nelson, D., Torrey, P., Narayanan, D., Li, Y., Philcox, O., La Torre, V., Maria Delgado, A., Ho, S., Hassan, S., Burkhart, B., Wadekar, D., Battaglia, N., Contardo, G., & Bryan, G. L.
- Affiliations
- Princeton University (US)
- Flatiron Institute (US)
- Royal Observatory (GB)
- Max Planck Institute for Astronomy (DE)
- Center for Astrophysics Harvard & Smithsonian (US)
- Heidelberg University (DE)
- University of Florida (US)
- Rutgers, The State University of New Jersey (US)
- New York University (US)
- Cornell University (US)
- ORCID
- Venue
- The Astrophysical Journal
- Publisher
- American Astronomical Society
- Published
- 2021-07-01
- Volume
- 915
- Issue
- 1
- Pages
- 71
- ISSN
- 0004-637X (ISSN-L)
- 1538-4357
- OpenAlex
- W3090580769
- Cited by
- 304
- References
- 105
- Citations by year
- 2026: 52 · 2025: 80 · 2024: 61 · 2023: 60 · 2022: 42 · 2021: 9
- FWCI
- 23.11
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- The Astrophysical Journal (publishedVersion)
- arXiv (Cornell University) (publishedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Science and Technology Facilities Council (ST/R000972/1)
- Topics
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Galaxies: Formation, Evolution, Phenomena
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Cosmology and Gravitation Theories
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Stellar, planetary, and galactic studies
- Keywords
- cosmological hydrodynamical simulations, machine learning training data, stellar feedback, AGN feedback, matter power spectrum, galaxy stellar mass function, galaxy scaling relations, star formation rate density, cosmological parameter space, baryonic effects, nonlinear interpolation, parameter estimation, symbolic regression, generative adversarial networks, anomaly detection, dimensionality reduction, IllustrisTNG, SIMBA, AREPO, GIZMO
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
