Eric Suchyta

The Data and AI Systems Section of the Computer Science and Mathematics Division at Oak Ridge National Laboratory conducts research on the data and artificial intelligence foundations of scientific discovery, shortening and automating the path from instrument and simulation to insight at the scale of leadership computing facilities. This report collects 27 project highlights from fiscal year 2026, organized by the section's five groups, namely Data Engineering, Learning Systems, Performance Engineering, Visualization, and Workflow Systems, each introduced by its group leader. Every highlight is written by the people who did the work and names someone who can be contacted about it directly. The highlights cover AI methods co-designed with the platforms that run them, from spiking and neuromorphic models to energy-efficient large language models. They also cover data reduction and campaign management that make scientific datasets AI-ready, uncertainty-aware and AI-assisted visualization at leadership scale, and workflows that couple experiment, simulation, and AI into closed loops needing little human intervention. Reported applications span fusion energy, materials science, electron microscopy, cosmology, plant phenotyping, health analytics, and national security. Much of our current agenda runs through the Department of Energy's Genesis Mission, where we contribute to the American Science Cloud and to the Transformational AI Models Consortium.

We conduct a search for strong gravitational lenses in the Dark Energy Survey (DES) Year 6 imaging data. We implement a pre-trained Vision Transformer (ViT) for our machine learning (ML) architecture and adopt interactive machine learning to construct a training sample with multiple classes to address common types of false positives. Our ML model reduces ∼236 million DES cutout images to 22,564 targets of interest, including ∼85% of previously reported galaxy–galaxy lens candidates discovered in DES. These targets were visually inspected by citizen scientists, who ruled out ∼90% as false positives. Of the remaining 2618 candidates, 149 were expert-classified as “definite” lenses and 516 as “probable” lenses, for a total of 665 systems, with 147 of these candidates being newly identified. Additionally, we trained a second ViT to find double-source plane lens systems, finding at least one double-source system. Our main ViT excels at identifying galaxy–galaxy lenses, consistently assigning high scores to candidates with high expert assessments. The top 800 ViT-scored images include ∼100 of our “definite” lens candidates. This selection is an order of magnitude higher in purity than previous convolutional neural-network-based lens searches and demonstrates the feasibility of applying our methodology for discovering large samples of lenses in future surveys.

A typical Bayesian inference on the values of some parameters of interest q from some data D involves running a Markov Chain (MC) to sample from the posterior p ( q , n ∣ D ) ∝ L ( D ∣ q , n ) p ( q ) p ( n ) , where n are some nuisance parameters with a separable prior. In some cases, the nuisance parameters are high-dimensional, and their prior p ( n ) is itself defined only by a set of samples that have been drawn from some other MC. The MC for the posterior will typically require evaluation of p ( n ) at arbitrary values of n , i.e., one needs to provide a density estimator over the full n space from the provided samples. But the high dimensionality of n hinders both the density estimation and the efficiency of the MC for the posterior. We describe a solution to this problem: a linear compression of the n space into a much lower-dimensional space u , which projects away directions in n space that cannot appreciably alter L . The algorithm for doing so is a slight modification to principal components analysis, and is less restrictive on p ( n ) than other proposed solutions to this issue. We demonstrate this “mode projection” technique using the analysis of 2-point correlation functions of weak lensing fields and galaxy density in the Dark Energy Survey, where n is a binned representation of the redshift distribution n ( z ) of the galaxies.

Observations of density variations in stellar streams are a promising probe of low-mass dark matter substructure in the Milky Way. However, survey systematics such as variations in seeing and sky brightness can also induce artificial fluctuations in the observed densities of known stellar streams. These variations arise because survey conditions affect both object detection and star–galaxy misclassification rates. To mitigate these effects, we use Balrog synthetic source injections in the Dark Energy Survey (DES) Y3 data to calculate detection rate variations and classification rates as functions of survey properties. We show that these rates are nearly separable with respect to survey properties and can be estimated with sufficient statistics from the synthetic catalogs. Applying these corrections reduces the standard deviation of relative detection rates across the DES footprint by a factor of 5, and our corrections significantly change the inferred linear density of the Phoenix stream when including faint objects. Additionally, for artificial streams with DES-like survey properties we are able to recover density power spectra with reduced bias. We also find that uncorrected power-spectrum results for Legacy Survey of Space and Time (LSST)-like data can be around 5 times more biased, highlighting the need for such corrections in future ground-based surveys.

We present improved cosmological constraints from a re-analysis of the Dark Energy Survey (DES) 5-year sample of Type Ia supernovae (DES-SN5YR). This re-analysis includes an improved photometric cross-calibration, recent white dwarf observations to cross-calibrate between DES and low redshift surveys, retraining the SALT3 light curve model and fixing a numerical approximation in the host galaxy colour law. Our fully recalibrated sample, which we call DES-Dovekie, comprises ∼1600 likely Type Ia SNe from DES and ∼200 low-redshift SNe from other surveys. With DES-Dovekie, we obtain Ωm = 0.330 ± 0.015 in Flat ΛCDM which changes Ωm by −0.022 compared to DES-SN5YR. Combining DES-Dovekie with CMB data from Planck, ACT and SPT and the DESI DR2 measurements in a Flat w0waCDM cosmology, we find w0 = −0.803 ± 0.054, wa = −0.72 ± 0.21. Our results hold a significance of 3.2σ, reduced from 4.2σ for DES-SN5YR, to reject the null hypothesis that the data are compatible with the cosmological constant. This significance is equivalent to a Bayesian model preference odds of approximately 5:1 in favour of the Flat w0waCDM model. Using generally accepted thresholds for model preference, our updated data exhibits only a weak preference for evolving dark energy.

The properties of Milky Way satellite galaxies have important implications for galaxy formation, reionization, and the fundamental physics of dark matter. However, the population of Milky Way satellites includes the faintest known galaxies, and current observations are incomplete. To understand the impact of observational selection effects on the known satellite population, we perform rigorous, quantitative estimates of the Milky Way satellite galaxy detection efficiency in three wide-field survey datasets: the Dark Energy Survey Year 6, the DECam Local Volume Exploration Data Release 3, and the Pan-STARRS1 Data Release 1. Together, these surveys cover ∼13,600 deg ² to g ∼ 24.0 and ∼27,700 deg ² to g ∼ 22.5, spanning ∼91% of the high-Galactic-latitude sky (∣ b ∣ ≥ 15°). We apply multiple detection algorithms over the combined footprint and recover 49 known satellites above a strict census detection threshold. To characterize the sensitivity of our census, we run our detection algorithms on a large set of simulated galaxies injected into the survey data, which allows us to develop models that predict the detectability of satellites as a function of their properties. We then fit an empirical model to our data and infer the luminosity function, radial distribution, and size–luminosity relation of Milky Way satellite galaxies. Our empirical model predicts a total of 26 5 − 47 + 79 satellite galaxies with −20 ≤ M _V ≤ 0, half-light radii of 15 ≤ r _1/2 , (pc) ≤ 3000, and galactocentric distances of 10 ≤ D _GC (kpc) ≤ 300. We also identify a mild anisotropy in the angular distribution of the observed galaxies, at a significance of ∼2 σ , which can be attributed to the clustering of satellites associated with the LMC.

We report the discovery of three Milky Way satellite candidates: Carina IV, Phoenix III, and DELVE 7, in the third data release of the DECam Local Volume Exploration survey (DELVE). The candidate systems were identified by cross-matching results from two independent search algorithms. All three are extremely faint systems composed of old, metal-poor stellar populations ( τ ≳ 10 Gyr, [Fe/H] ≲−1.4). Carina IV ( M _V = −2.8; r _1/2 = 40 pc) and Phoenix III ( M _V = −1.2; r _1/2 = 19 pc) have half-light radii that are consistent with the known population of dwarf galaxies, while DELVE 7 ( M _V = 1.2; r _1/2 = 2 pc) is very compact and seems more likely to be a star cluster, though its nature remains ambiguous without spectroscopic follow-up. The Gaia proper motions of stars in Carina IV ( M ⋆ = 225 0 − 830 + 1180 M ⊙ ) indicate that it is unlikely to be associated with the LMC, while DECam CaHK photometry confirms that its member stars are metal poor. Phoenix III ( M ⋆ = 52 0 − 290 + 660 M ⊙ ) is the faintest known satellite in the extreme outer stellar halo ( D _GC > 100 kpc), while DELVE 7 ( M ⋆ = 6 0 − 40 + 120 M ⊙ ) is the faintest known satellite with D _GC > 20 kpc.

We describe the photometric dataset assembled from the full 6 yr of observations by the Dark Energy Survey (DES) in support of static-sky cosmology analyses. DES Y6 Gold is a curated dataset derived from DES Data Release 2 (DR2) that incorporates improved measurement, photometric calibration, object classification and value-added information. Y6 Gold comprises nearly 5000 deg ² of grizY imaging in the south Galactic cap and includes 669 million objects with a depth of i _AB ∼ 23.4 mag at a signal-to-noise ratio ∼ 10 for extended objects and a top-of-the-atmosphere photometric uniformity i _AB < 22.5. Additionally, it includes per-object quality information, and accompanying maps of the footprint coverage, masked regions, imaging depth, survey conditions, and astrophysical foregrounds that are used for cosmology analyses. After quality selections, benchmark samples contain 448 million galaxies and 120 million stars. This publication is complemented by data access and documentation.