DeepDISC on LSST Data Preview 1: Scene-Level Detection, Deblending, and Star/Galaxy Classification in the ECDFS and EDFS Fields
Year: 2026
Type: preprint
Abstract: We present the first application of DeepDISC, a scene-level deep-learning framework, to real LSST data, using the Data Preview 1 (DP1) coadded images of the Extended Chandra Deep Field-South and the Euclid Deep Field-South fields. In a single pass, DeepDISC jointly detects, segments, and classifies sources as stars or galaxies, rather than treating these tasks as separate steps as in traditional pipelines. We warm-start from a model pretrained on LSST simulations and fine-tune it on DP1 six-band images, using the DP1 catalog's extendedness flag (point-like versus extended) as provisional class labels. The classification part of the network is then fine-tuned alone on a curated sample of stars and galaxies with spectroscopic, Gaia, and photometric identifications, so the final output is a star/galaxy classification. Fine-tuning on real DP1 observations substantially improves source recovery relative to the un-fine-tuned model, raising galaxy and star completeness from 40.2% and 13% to 84.2% and 49.1% under strict class-aware matching; under class-agnostic matching the fine-tuned model reaches 84.9% and 74.3%. On a common sample of sources that neither classifier saw in training, DeepDISC classifies to within about one percentage point of a published photometry-based Random Forest for the same field (97.4% vs. 98.5%); at fainter magnitudes DeepDISC labels more sources as stars than the Random Forest, and independent labels favor the Random Forest in most of these disagreements. Cross-matching to deeper HST/CANDELS imaging on a held-out footprint gives an unrecognized-blend fraction for DeepDISC of 14.9% (95% CI 12.5-17.8%), consistent with or modestly below the 18.0% we measure for the production DP1 catalog. This work establishes a baseline for DeepDISC on real LSST data and a foundation for self-supervised pretraining and for LSST Data Preview 2.
Source: arXiv (Cornell University)
Language: English
Subfield: Astronomy and Astrophysics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
Funders: National Science Foundation, U.S. Department of Energy, National Aeronautics and Space Administration, National Centre for Supercomputing Applications, National Energy Research Scientific Computing Center, Centre National de la Recherche Scientifique, Office of Science, Science and Technology Facilities Council, Institut National de Physique Nucléaire et de Physique des Particules, Office of Advanced Cyberinfrastructure, SLAC National Accelerator Laboratory
Awards: G1141912172, G122673668, G1229526393, G1286236842, G1353381076, G1451874870, G1453181110, G1503004319, NSF's National Optical-Infrared Astronomy Research Laboratory (NOIRLab): Management and Operations of Vera C. Rubin Observatory, G1632040200, G1677143136, G1863003419, Track 4: Advanced CI Coordination Ecosystem: Monitoring and Measurement Services, Construction of Vera C. Rubin Observatory under the Major Research Equipment and Facilities Construction (MREFC) Account, Final Design, Construction and Operations of Vera C. Rubin Observatory, G2371548206, G262532246, G298330452, G303061748, G3562386289, Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS), G4010157413, G419881185, G4235786860, G42916606, G4403015908, G4501827968, G4654690619, ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI), NSF's National Optical-Infrared Astronomy Research Laboratory (NOIRLab) as a Federally Funded Research and Development Center (FFRDC), G495301720, G498139845, G5076365615, Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT), G5367127336, G5438923238, G5464919783, G5570207115, G6447494072, G6652958823, CDS&E: Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC), G8108599699, Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI, G8382000481, G8726098666
OpenAlex ID: W7221196730