Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

Journal Article · Tue Jan 20 00:00:00 EST 2026 · No journal information

DOI:https://doi.org/10.5281/zenodo.18319953· OSTI ID:3014041

Aubourg, Eric ^[1]; Avestruz, Camille ^[2]; Becker, Matthew R. ^[3]; Biswas, Biswajit ^[3]; Biswas, Rahul ^[4]; Bolliet, Boris ^[5]; Bolton, Adam S. ^[6]; Bom, Clecio R. ^[7]; Bonnet-Guerrini, Raphaël ^[8]; Boucaud, Alexandre ^[1]; Campagne, Jean-Eric ^[9]; Chang, Chihway ^[10]; Ćiprijanović, Aleksandra ^[11]; Cohen-Tanugi, Johann ^[12]; Coughlin, Michael W. ^[13]; Crenshaw, John Franklin ^[14]; Cuevas-Tello, Juan C. ^[15]; de Vicente, Juan ^[16]; Digel, Seth W. ^[17]; Dillmann, Steven ^[18] ; de León Dominguez Romero, Mariano Javier ^[19]; Drlica-Wagner, Alex ^[20]; Erickson, Sydney ^[21]; Gagliano, Alexander T. ^[22]; Georgiou, Christos ^[23]; Ghosh, Aritra ^[24]; Grayling, Matthew ^[25]; Grishin, Kirill A. ^[1]; Heavens, Alan ^[26]; House, Lindsay R. ^[27]; Ishak, Mustapha ^[28]; Kabalan, Wassim ^[1]; Kannawadi, Arun ^[29]; Lanusse, François ^[30]; Leonard, C. Danielle ^[31]; Léget, Pierre-François ^[32]; Lochner, Michelle ^[33]; Mao, Yao-Yuan ^[34]; Melchior, Peter ^[35]; Merz, Grant ^[36]; Millon, Martin ^[37]; Möller, Anais ^[38]; Narayan, Gautham ^[39]; Omori, Yuuki ^[10]; Peiris, Hiranya ^[25]; Perreault-Levasseur, Laurence ^[40]; Plazas Malagón, Andrés A. ^[41]; Ramachandra, Nesar ^[3]; Remy, Benjamin ^[42]; Roucelle, Cécile ^[1]; Ruiz-Zapatero, Jaime ^[43]; Schuldt, Stefan ^[44]; Sevilla-Noarbe, Ignacio ^[16]; Shah, Ved G. ^[45]; Starkenburg, Tjitske ^[45]; Thorp, Stephen ^[25]; San Cipriano, Laura Toribio ^[16]; Tröster, Tilman ^[37]; Trotta, Roberto ^[46]; Venkatraman, Padma ^[36]; Wasserman, Amanda ^[39]; White, Tim ^[47]; Zeghal, Justine ^[40]; Zhang, Tianqing ^[48]; Zhang, Yuanyuan ^[49]

---

1. APC, Paris
2. U. Michigan, Ann Arbor; Michigan U., LCTP
3. Argonne (main)
4. Unlisted
5. Cambridge U.; Cambridge U., Inst. of Astron.
6. SLAC
7. Rio de Janeiro, CBPF
8. Milan Bicocca U.
9. IJCLab, Orsay
10. Chicago U., Astron. Astrophys. Ctr.; Chicago U., KICP; SkAI, Chicago
11. Fermilab; Chicago U., Astron. Astrophys. Ctr.; SkAI, Chicago
12. LPC, Clermont-Ferrand
13. Minnesota U.
14. KIPAC, Menlo Park; Stanford U.; SLAC
15. San Luis Potosi U.
16. Madrid, CIEMAT; Madrid, Escuela Tec. Sup. Ing. Ind.
17. SLAC; KIPAC, Menlo Park
18. KIPAC, Menlo Park; Stanford U., ITP; SLAC
19. Cordoba U.
20. Fermilab; Chicago U., Astron. Astrophys. Ctr.; Chicago U., EFI; Chicago U., KICP; SkAI, Chicago
21. Stanford U.; SLAC
22. Harvard U.; IAIFI, Cambridge; Harvard-Smithsonian Ctr. Astrophys.; MIT, MKI
23. Barcelona, IFAE
24. Washington U., Seattle
25. Cambridge U., KICC
26. Imperial Coll., London
27. SkAI, Chicago; Chicago U.
28. U. Texas, Dallas
29. Duke U.
30. AIM, Saclay
31. Newcastle upon Tyne U.
32. Princeton U.
33. Western Cape U.
34. Utah U.
35. Princeton U., Astrophys. Sci. Dept.
36. Illinois U., Urbana, Astron. Dept.
37. ETH, Zurich (main)
38. Swinburne U. Tech., Hawthorn
39. Illinois U., Urbana, Astron. Dept.; SkAI, Chicago
40. Montreal U.; U. Montreal (main)
41. KIPAC, Menlo Park; SLAC; Princeton U., Astrophys. Sci. Dept.
42. Chicago U., Astron. Astrophys. Ctr.; SkAI, Chicago
43. University Coll. London
44. Milan U.; Turku U.; Helsinki U.; IASF, Milan
45. Florida U.; Northwestern U. (main); SkAI, Chicago
46. SISSA, Trieste; INFN, Trieste; Imperial Coll., London
47. U. Michigan, Ann Arbor
48. Pittsburgh U.
49. Natl. Solar Observ., Tucson

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

• Research Organization: APC, Paris; AIM, Saclay; MIT, MKI; San Luis Potosi U.; Montreal U.; Helsinki U.; Swinburne U. Tech., Hawthorn; Chicago U., EFI; Milan U.; Barcelona, IFAE; Cambridge U., Inst. of Astron.; Madrid, CIEMAT; Harvard-Smithsonian Ctr. Astrophys.; Rio de Janeiro, CBPF; Imperial Coll., London; LPC, Clermont-Ferrand; ETH, Zurich (main); Stanford U., ITP; U. Michigan, Ann Arbor; SkAI, Chicago; Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Florida U.; Western Cape U.; Milan Bicocca U.; Natl. Solar Observ., Tucson; SISSA, Trieste; Cambridge U., KICC; Harvard U.; Michigan U., LCTP; Unlisted; IJCLab, Orsay; Stanford U.; Chicago U., KICP; U. Texas, Dallas; Duke U.; Illinois U., Urbana, Astron. Dept.; Princeton U.; Turku U.; INFN, Trieste; Northwestern U. (main); Chicago U., Astron. Astrophys. Ctr.; Argonne National Laboratory (ANL), Argonne, IL (United States); Minnesota U.; IAIFI, Cambridge; Newcastle upon Tyne U.; Princeton U., Astrophys. Sci. Dept.; IASF, Milan; Utah U.; Madrid, Escuela Tec. Sup. Ing. Ind.; U. Montreal (main); University Coll. London; SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States); Cordoba U.; Washington U., Seattle; Pittsburgh U.; Cambridge U.; Chicago U.
• Sponsoring Organization: US Department of Energy
• DOE Contract Number: 89243024CSC000002
• OSTI ID: 3014041
• Report Number(s): FERMILAB-PUB-25-0886-CSAID-PPD; oai:inspirehep.net:3109591; arXiv:2601.14235
• Journal Information: No journal information, Journal Name: No journal information
• Country of Publication: United States
• Language: English