Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “benchmark dataset”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 793 records · Page 44

Towards interpretable Cryo-EM: disentangling latent spaces of molecular conformations

Molecules are essential building blocks of life and their different conformations (i.e., shapes) crucially determine the functional role that they play in living organisms. Cryogenic Electron Microscopy (cryo-EM) allows for acquisition of large image datasets of individual molecules. Recent advances in computational cryo-EM have made it possible to learn latent variable models of conformation landscapes. However, interpreting these latent spaces remains a challenge as their individual dimensions are often arbitrary. The key message of our work is that this interpretation challenge can be viewed as an Independent Component Analysis (ICA) problem where we seek models that have the property of identifiability. That means, they have an essentially unique solution, representing a conformational latent space that separates the different degrees of freedom a molecule is equipped with in nature. Thus, we aim to advance the computational field of cryo-EM beyond visualizations as we connect it with the theoretical framework of (nonlinear) ICA and discuss the need for identifiable models, improved metrics, and benchmarks. Moving forward, we propose future directions for enhancing the disentanglement of latent spaces in cryo-EM, refining evaluation metrics and exploring techniques that leverage physics-based decoders of biomolecular systems. Moreover, we discuss how future technological developments in time-resolved single particle imaging may enable the application of nonlinear ICA models that can discover the true conformation changes of molecules in nature. The pursuit of interpretable conformational latent spaces will empower researchers to unravel complex biological processes and facilitate targeted interventions. This has significant implications for drug discovery and structural biology more broadly. More generally, latent variable models are deployed widely across many scientific disciplines. Thus, the argument we present in this work has much broader applications in AI for science if we want to move from impressive nonlinear neural network models to mathematically grounded methods that can help us learn something new about nature.

59 BASIC BIOLOGICAL SCIENCES↗

Comprehensive Fuel Performance Model Development and Simulation for TRISO Fuel

High Temperature Gas Reactor (HTGR), widely recognized as one of the top candidates for the Next Generation Nuclear Power-plant (NGNP) fleet, has received ever-increasing interest due to its superior safety and many other desirable features. TRISO fuel particles are the basic form of the fuel used in both pebble-bed and prismatic reactors. Since they are a key component of the HTGR core design, the success of the reactor depends on the safety and quality of the TRISO particles. During operation, a TRISO particle undergoes complex thermo-mechanical processes. Fission gases accumulate inside the kernel and the buffer layer, and lead to buildup of internal pressure. Uneven thermal conditions lead to asymmetric thermal expansion. The pyrolytic carbon, in both the IPyC and OPyC layers, is known to experience dimensional change (shrinkage or swelling) under fast neutron irradiation. In the mean time, both the IPyC and OPyC layers creep as a function of stress and fast neutron fluence. Macro cracks in the IPyC layer, corrosion in the SiC layer due to chemical attack, and debonding at the interface between IPyC and SiC, have been observed in post-irradiation examinations. All these processes further complicate the stress states in a TRISO particle, and might lead to failure of a single coating layer or the particle as a whole. It is very difficult to duplicate the actual environment that a particle is exposed to in experiments. It is even more difficult to isolate one process from another, thus making it nearly impossible to evaluate the impacts that a particular process has on the fuel particle by conducting experiments. The problem can however at least partially be addressed by modeling and simulation. Hence, multi-dimensional, multi-physics and comprehensive models are greatly needed to simulate and evaluate the performance of a TRISO particle under normal and accidental conditions. Existing models are inadequate as they are usually one-dimensional models that over-simplified these processes or do not include all the main physics. The goal of this thesis is to develop a comprehensive, multi-dimensional and multi-physics model to simulate and evaluate TRISO fuel performance. It includes all the main processes taking place in the fuel particle. Three equally important components of this modeling exercise are: 1) 3D heat transfer and temperature distribution analysis; 2) 3D neutronics, heat generation, and fission gas generation and release analysis; 3) 3D stress analysis and failure prediction of the TRISO particle. The 3D thermal model consists of the solution of the heat conduction equation using the finite difference technique. The temperature calculated using this model is compared to analytical solutions and to the results reported in literature. Good agreements are observed. Thermal models are developed to calculate temperature distribution in a pebble under different power and asymmetric convective boundary conditions caused by, for example, contacts with other pebbles. Three-dimensional temperature distribution in a TRISO particle is also calculated under various conditions such as in the presence of an off-center gas bubble. Three-dimensional neutronics models are developed using MCNP5/X. Burnup calculations are performed to track the number densities of a few important isotopes and to calculate gas production. The fractional gas release on both intra- and inter-granular level are calculated using the White and Tucker’s model. The gas pressure inside the buffer layer is also quantified. Finally, 3D axisymmetric stress models are developed using an open-source finite element code, FEAP. Modifications are introduced to FEAP to include PyC shrinkage and creep, etc. The modified code is benchmarked against Miller’s results, and good agreements are observed. A number of variables are studied to evaluate their impacts on stresses and failure probabilities. These variables include creep constant, creep Poisson’s ratio, irradiation temperature, BAF, layer thickness, etc. Some transient thermal conditions such as power surge, and defective cases such as a radial crack in IPyC, debonding and corrosion to SiC, are also studied. Among all, a few variables/conditions have significant impacts on stresses and failure probabilities, namely: shrinkage strain, creep constant, creep Poisson’s ratio, particle size, irradiation temperature, BAF and cracked IPyC. Order of magnitude of stresses resulting from temperature changes, pressure buildup due to gas generation, and due to PyC shrinkage/creep show that in the case of TRISO particle (when using specific empirical constants or existing dataset found in literature to calculate shrinkage/creep strains), stresses due to temperature changes and internal gas pressure are orders of magnitude lower than those resulting from shrinkage/creep. Failure probabilities of both IPyC and SiC are also calculated. The failure probability of IPyC under most conditions borderlines with the design requirement (1E-4) except under low irradiation temperature. The failure probability of SiC under normal conditions is minimal because it is always under compression; except when there is a radial crack in IPyC, in which case the stress in part of SiC becomes tensile and the failure probability is higher than 1E-4, and increases at higher burnup. The comprehensive fuel performance model developed in this work and implemented in a suite of computer codes simulates the thermo-mechanical behavior of a TRISO fuel particle under irradiation. This work leads to a better understanding of TRISO fuel particle evolution over its lifetime, and provides insights in how to improve the safety and reliability of TRISO fuel. The models developed here can be useful for other purposes related to TRISO fuel or for fuel performance evaluation of other forms of nuclear fuels. (author)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Less is more: Sampling chemical space with active learning

We present the development of accurate and transferable machine learning (ML) potentials for predicting molecular energetics is a challenging task. The process of data generation to train such ML potentials is a task neither well understood nor researched in detail. In this work, we present a fully automated approach for the generation of datasets with the intent of training universal ML potentials. It is based on the concept of active learning (AL) via Query by Committee (QBC), which uses the disagreement between an ensemble of ML potentials to infer the reliability of the ensemble’s prediction. QBC allows the presented AL algorithm to automatically sample regions of chemical space where the ML potential fails to accurately predict the potential energy. AL improves the overall fitness of ANAKIN-ME (ANI) deep learning potentials in rigorous test cases by mitigating human biases in deciding what new training data to use. AL also reduces the training set size to a fraction of the data required when using naive random sampling techniques. To provide validation of our AL approach, we develop the COmprehensive Machine-learning Potential (COMP6) benchmark (publicly available on GitHub) which contains a diverse set of organic molecules. Active learning-based ANI potentials outperform the original random sampled ANI-1 potential with only 10% of the data, while the final active learning-based model vastly outperforms ANI-1 on the COMP6 benchmark after training to only 25% of the data. Finally, we show that our proposed AL technique develops a universal ANI potential (ANI-1x) that provides accurate energy and force predictions on the entire COMP6 benchmark. Finally, this universal ML potential achieves a level of accuracy on par with the best ML potentials for single molecules or materials, while remaining applicable to the general class of organic molecules composed of the elements CHNO.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

First Search for Dark-Trident Processes Using the MicroBooNE Detector

We present a first search for dark-trident scattering in a neutrino beam using a dataset corresponding to 7.2 × 10 20 protons on target taken with the MicroBooNE detector at Fermilab. Proton interactions in the neutrino target at the main injector produce π 0 and η mesons, which could decay into dark-matter (DM) particles mediated via a dark photon A ′ . A convolutional neural network is trained to identify interactions of the DM particles in the liquid-argon time projection chamber (LArTPC) exploiting its imagelike reconstruction capability. In the absence of a DM signal, we provide limits at the 90% confidence level on the squared kinematic mixing parameter ϵ 2 as a function of the dark-photon mass in the range 10 ≤ M A ′ ≤ 400 MeV . The limits cover previously unconstrained parameter space for the production of fermion or scalar DM particles χ for two benchmark models with mass ratios M χ / M A ′ = 0.6 and 2 and for dark fine-structure constants 0.1 ≤ α D ≤ 1 . Published by the American Physical Society 2024

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

The high explosives & affected targets (HEAT) dataset

Artificial Intelligence (AI) surrogate models offer a computationally efficient alternative to full-physics simulations, yet no existing datasets are publicly available for training, testing, and validation of machine learning models of the dynamics of high-explosive driven shocks through multiple materials. Shock propagation through materials is a computationally challenging problem because simulations must include material-specific equations of state (EOS) along with descriptions of other physical processes such as plastic deformation, phase change, damage processes, fluid instabilities, and multi-material interactions. Shocks are typically initiated by high-velocity impacts or explosive loading. The latter case necessitates the addition of models of reactive materials to represent high-explosive (HE) detonation. Here, to address the lack of an expansive dataset for multi-material shock propagation in the AI/ML community, we present the High-Explosives and Affected Targets (HEAT) Dataset. HEAT is a physics-rich collection of two-dimensional, cylindrically symmetric, simulations generated using an Eulerian, multi-material, shock-propagation code developed at Los Alamos National Laboratory. The dataset includes two partitions: (1) the expanding shock-cylinder (CYL) simulations, Figs. 1, and (2) the Perturbed Layered Interface (PLI) simulations, Fig. 2. Entries in both partitions consist of time series of arrays of thermodynamic fields (pressure, density, and temperature), kinematic fields (position and velocity), and additional fields that depend on thermodynamic and/or kinematic fields (e.g., material stress). Materials in the CYL partition include solids (aluminium, copper, depleted uranium, stainless steel, tantalum, and a generic polymer), a liquid (water), gases (air, nitrogen), and a generic detonating material (high explosive, HE). The PLI partition spans a highly varying geometry but consists of fixed materials across entries: Copper, aluminium, stainless steel, generic polymer, and generic HE. HEAT captures critical phenomena such as momentum transfer, shock propagation, plastic deformation, and thermal effects, making HEAT a valuable benchmark for development of AI/ML emulation of multi-material shock propagation.

36 MATERIALS SCIENCE↗

Calculating Free Energy Changes in Continuum Solvation Models

We recently showed for a large dataset of pK a s and reduction potentials that free energies calculated directly within the SMD continuum model compares very well with corresponding thermodynamic cycle calculations in both aqueous and organic solvents (Phys. Chem. Chem. Phys. 2015, 17, 2859). In this paper, we significantly expand the scope of our study to examine the suitability of this approach for the calculation of general solution phase kinetics and thermodynamics, in conjunction with several commonly used solvation models (SMDM062X, SMD-HF, CPCM-UAKS, and CPCM-UAHF) for a broad range of systems and reaction types. This includes cluster-continuum schemes for pK a calculations, as well as various neutral, radical and ionic reactions such as enolization, cycloaddition, hydrogen and chlorine atom transfer, and bimolecular SN2 and E2 reactions. On the basis of this benchmarking study, we conclude that the accuracies of both approaches are generally very similar – the mean errors for Gibbs free energy changes of neutral and ionic reactions are approximately 5 kJ mol -1 and 25 kJ mol -1 respectively. In systems where there are significant structural changes due to solvation, as is the case for certain ionic transition states and amino acids, the direct approach generally afford free energy changes that are in better agreement with experiment. The results indicate that when appropriate combinations of electronic structure methods are employed, the direct approach provides a reliable alternative to the thermodynamic cycle calculations of solution phase kinetics and thermodynamics across a broad range of organic reactions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Systematic Assessment of Terrestrial Biogeochemistry in Coupled Climate-Carbon Models

With representation of the global carbon cycle becoming increasingly complex in climate models, it is important to develop ways to quantitatively evaluate model performance against in situ and remote sensing observations. Here we present a systematic framework, the Carbon-LAnd Model Intercomparison Project (C-LAMP), for assessing terrestrial biogeochemistry models coupled to climate models using observations that span a wide range of temporal and spatial scales. As an example of the value of such comparisons, we used this framework to evaluate two biogeochemistry models that are integrated within the Community Climate System Model (CCSM) - Carnegie-Ames-Stanford Approach (CASA) and carbon-nitrogen (CN). Both models underestimated the magnitude of net carbon uptake during the growing season in temperate and boreal forest ecosystems, based on comparison with atmospheric CO{sub 2} measurements and eddy covariance measurements of net ecosystem exchange. Comparison with MODerate Resolution Imaging Spectroradiometer (MODIS) measurements show that this low bias in model fluxes was caused, at least in part, by 1-3 month delays in the timing of maximum leaf area. In the tropics, the models overestimated carbon storage in woody biomass based on comparison with datasets from the Amazon. Reducing this model bias will probably weaken the sensitivity of terrestrial carbon fluxes to both atmospheric CO{sub 2} and climate. Global carbon sinks during the 1990s differed by a factor of two (2.4 Pg C yr{sup -1} for CASA vs. 1.2 Pg C yr{sup -1} for CN), with fluxes from both models compatible with the atmospheric budget given uncertainties in other terms. The models captured some of the timing of interannual global terrestrial carbon exchange during 1988-2004 based on comparison with atmospheric inversion results from TRANSCOM (r=0.66 for CASA and r=0.73 for CN). Adding (CASA) or improving (CN) the representation of deforestation fires may further increase agreement with the atmospheric record. Information from C-LAMP has enhanced model performance within CCSM and serves as a benchmark for future development. We propose that an open source, community-wide platform for model-data intercomparison is needed to speed model development and to strengthen ties between modeling and measurement communities. Important next steps include the design and analysis of land use change simulations (in both uncoupled and coupled modes), and the entrainment of additional ecological and earth system observations. Model results from C-LAMP are publicly available on the Earth System Grid.

09 BIOMASS FUELS↗

matsim-agents v1.0

matsim-agents is a multi-agent AI framework for atomistic materials simulation and discovery. It orchestrates large language models (LLMs), machine-learned interatomic potentials (MLIPs), and DFT codes into a single agentic loop running on laptops and DOE leadership-class supercomputers. MULTI-AGENT ORCHESTRATION A LangGraph state machine with three nodes: a Planner that converts a natural-language research objective into structured tasks; an Executor that dispatches atomistic tools and loops until the queue is empty; and an Analyst that summarizes results into a human-readable report. State is checkpointed after every step and human-in-the-loop gates can be inserted at any edge. HYPOTHESIS-DRIVEN DISCOVERY CHAT An interactive REPL (matsim-agents chat) that couples LLM dialogue with atomistic simulation. Chemical formulas are automatically detected in conversation turns and trigger a full crystal-phase exploration: structure generation → relaxation → stability scoring → result injection back into the conversation, creating a closed hypothesis-refinement loop. CRYSTAL PHASE ENUMERATION Given a composition, the phase explorer enumerates prototypes by stoichiometry: elemental (fcc/bcc/hcp/sc/diamond), binary 1:1 (rocksalt/CsCl/zincblende/ wurtzite/fluorite/rutile), ternary 1:1:3 (cubic perovskite), ternary 1:2:4 (perovskite + spinel), quaternary 1:1:2:6 (Fm-3m double perovskite). 2-D prototypes (graphene, h-BN, MoS2 2H/1T) and multilayer stacking are also supported via --include-2d and --num-layers. SUPERCELL GENERATION AND SITE DECORATION Auto-tiling to a minimum atom count (--min-atoms), explicit NxNxN tiling (--supercell), symmetry-distinct site decorations (--n-orderings), and isotropic lattice-scale sweeps (--lattice-scales) for volume bracketing. MLFF RELAXATION AND STABILITY SCORING HydraGNN (multi-headed GNN) drives structure relaxation via ASE with FIRE, BFGS, or BFGSLineSearch. Stability output: delta-E/atom ranking across phases and a max-residual-force dynamical-stability proxy. Other MLIPs (MACE, NequIP, Orb) can be plugged in through the same interface. DFT BACKENDS Quantum ESPRESSO pw.x and VASP 6.6 are first-class labellers. Both have validated GPU builds and SLURM/PBS launchers for three DOE platforms: Frontier (AMD MI250X, ROCm), Aurora (Intel PVC, oneAPI), Perlmutter (NVIDIA A100, CUDA). QE produces ~100 binaries (pw.x, ph.x, epw.x, ...). VASP supports scf, relax, vc-relax, and vc-relax-shape run types. ACTIVE-LEARNING LOOP matsim-agents al run CONFIG.yaml drives an iterative HydraGNN-DFT loop: MD generates candidates → ensemble/MC-dropout uncertainty selects the most informative → DFT labels them in parallel inside one allocation → dataset grows → HydraGNN retrains → repeat. DFT backend is a single YAML toggle (dft.backend: vasp | qe). LLM-generated seed structures are supported (no curated POSCAR library needed). Config uses ${VAR}, ${VAR:-default}, ${VAR:?msg} shell-style substitution for cross-user/cross-site portability. LLM BACKENDS Ollama (local, default), vLLM (HPC multi-GPU serving), OpenAI, Anthropic, HuggingFace Transformers+Accelerate. Selected at runtime via flag or env var with no code changes. HPC PORTABILITY Same Python entry points run on Frontier (ROCm 7.2), Aurora (oneAPI), and Perlmutter (CUDA 12). DFT and ML stacks are never co-loaded in the same shell; they couple through the scheduler and filesystem. Advanced multi-node launchers (serve, discovery-chat, single-relaxation, active-learning, QE warm-start) are provided for all three platforms. CODABENCH COMPETITION BUNDLE A self-contained benchmark: 159 atomistic test structures across 11 material classes, 5 tasks (formation energy, forces, ML relaxation, AI-DFT relaxation, phase stability ranking), public/private leaderboard split (30/70), and four ready-to-run baselines: MACE-MP-0, HydraGNN, UMA, AllScAIP.

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗

V-HAMSTeR v1.0.0

V-HAMSTeR is a bioinformatics software tool designed to predict the hosts of viruses directly from genomic sequences. It can be used by researchers to predict animal, prokaryotic, plant, protist or fungal viral hosts including viruses that may be fragmented or discovered in environmental metagenomic datasets. Features & Uses: The software employs a novel dual-stream deep learning architecture that dynamically fuses implicit sequence embeddings from a genomic foundation model with 13 explicit, handcrafted biological features (e.g., coding density and strand switch rates). To ensure maximum reliability, V=HAMSTeR deploys a 5-fold deep ensemble calibrated via Joint Temperature Scaling, providing users with statistically rigorous confidence probabilities. It also features an automated sequence chunking and mean-pooling module to seamlessly process variable-length contigs. Advantages Over Similar Technologies: Existing tools (e.g., IPEV, RNAVirHost) typically rely on either basic k-mers or isolated neural networks. V-HAMSTeR's hybrid architecture captures both broad genomic context and specific biological motifs that standalone foundation models often miss. Furthermore, unlike competitor tools that struggle with incomplete data or exhibit extreme overconfidence, V-HAMSTeR is explicitly benchmarked and mathematically calibrated for fragmented assemblies (1kb–10kb). This makes it uniquely robust, accurate, and trustworthy for the messy reality of real-world environmental viromics.

Grigson, Susie [Lawrence Berkeley National Laborat↗

A Big Problem for Small Earthquakes: Benchmarking Routine Magnitudes and Conversion Relationships with Coda Envelope-Derived Mw in Southern Kansas and Northern Oklahoma

Earthquake magnitudes are widely relied upon measures of earthquake size. Although moment magnitude (M w ) has become the established standard for moderate and large earthquakes, difficulty in reliably measuring seismic moments for small (generally M w <4) earthquakes has meant that magnitudes for these events remain plagued by a patchwork of inconsistent measurement scales. Because of this, magnitudes of small earthquakes and statistics derived from them can be biased. Furthermore, because small earthquakes are much more numerous than large ones, many applications, such as seismic hazard modeling, depend critically on analysis of events characterized by magnitudes other than M w . Therefore, to assess this problem, we apply coda envelope analysis to reliably determine moment magnitudes for a case study of small earthquakes from northern Oklahoma and southern Kansas. Not surprisingly, we find significant differences among M L , m bLg , and M w for M ~2–4 earthquakes examined here. More troublingly, we find that relations designed to convert other magnitudes to M w , which are relied upon for important applications such as seismic hazard analysis, often increase rather than decrease this bias for our dataset. In our case study, we find that converted magnitudes can result in a systematic bias sometimes exceeding 0.5 magnitude units, a difference that typically corresponds to a factor of ~3 in seismicity rate. Moreover, we find a correspondingly large bias in Gutenberg–Richter b-values, controlled primarily by inaccurate magnitude scaling in the conversion relationships. Although this study focuses on a relatively small geographic area, we can expect that similar issues exist with varying severity in other regions. Therefore, magnitudes of small earthquakes and their associated statistics, including seismicity rates and b-values, should be treated with caution.

58 GEOSCIENCES↗

Tracking vegetation phenology across diverse North American biomes using PhenoCam imagery

Vegetation phenology controls the seasonality of many ecosystem processes, as well as numerous biosphere-atmosphere feedbacks. Phenology is also highly sensitive to climate change and variability. Here we present a series of datasets, together consisting of almost 750 years of observations, characterizing vegetation phenology in diverse ecosystems across North America. Our data are derived from conventional, visible-wavelength, automated digital camera imagery collected through the PhenoCam network. For each archived image, we extracted RGB (red, green, blue) colour channel information, with means and other statistics calculated across a region-of-interest (ROI) delineating a specific vegetation type. From the high-frequency (typically, 30 min) imagery, we derived time series characterizing vegetation colour, including "canopy greenness", processed to 1- and 3-day intervals. For ecosystems with one or more annual cycles of vegetation activity, we provide estimates, with uncertainties, for the start of the "greenness rising" and end of the "greenness falling" stages. Lastly, the database can be used for phenological model validation and development, evaluation of satellite remote sensing data products, benchmarking earth system models, and studies of climate change impacts on terrestrial ecosystems.

54 ENVIRONMENTAL SCIENCES↗

Physics-based reward driven image analysis in microscopy

The rise of electron microscopy has expanded our ability to acquire nanometer and atomically resolved images of complex materials. The resulting vast datasets are typically analyzed by human operators, an intrinsically challenging process due to the multiple possible analysis steps and the corresponding need to build and optimize complex analysis workflows. We present a methodology based on the concept of a Reward Function coupled with Bayesian Optimization, to optimize image analysis workflows dynamically. The Reward Function is engineered to closely align with the experimental objectives and broader context and is quantifiable upon completion of the analysis. Here, cross-section, high-angle annular dark field (HAADF) images of ion-irradiated (Y, Dy)Ba 2 Cu 3 O 7–δ thin-films were used as a model system. The reward functions were formed based on the expected materials density and atomic spacings and used to drive multi-objective optimization of the classical Laplacian-of-Gaussian (LoG) method. These results can be benchmarked against the DCNN segmentation. This optimized LoG* compares favorably against DCNN in the presence of the additional noise. We further extend the reward function approach towards the identification of partially-disordered regions, creating a physics-driven reward function and action space of high-dimensional clustering. We pose that with correct definition, the reward function approach allows real-time optimization of complex analysis workflows at much higher speeds and lower computational costs than classical DCNN-based inference, ensuring the attainment of results that are both precise and aligned with the human-defined objectives.

47 OTHER INSTRUMENTATION↗

Edge ML for CAN bus intrusion detection in AVs

Autonomous Vehicles (AVs) are revolutionizing transportation, but their reliance on interconnected cyber-physical systems exposes them to unprecedented cybersecurity risks. This study addresses the critical challenge of detecting real-time cyber intrusions in self-driving vehicles by leveraging a dataset from the Udacity self-driving car project. We simulate four high-impact attack vectors, Denial of Service (DoS), spoofing, replay, and fuzzy attacks, by injecting noise into spatial features (e.g., bounding box coordinates) to replicate adversarial scenarios. We develop and evaluate two lightweight neural network architectures (NN-1 and NN-2) alongside a logistic regression baseline (LG-1) for intrusion detection. The models achieve exceptional performance, with NN-2 attaining an AUC score of 93.15% and 93.15% accuracy, demonstrating their suitability for edge deployment in AV environments. Through explainable AI techniques, we uncover unique forensic fingerprints of each attack type, such as spatial corruption in fuzzy attacks and temporal anomalies in replay attacks, offering actionable insights for feature engineering and proactive defense. Visual analytics, including confusion matrices, ROC curves, and feature importance plots, validate the models' robustness and interpretability. This research sets a new benchmark for AV cybersecurity, delivering a scalable, field-ready toolkit for Original Equipment Manufacturers (OEMs) and policymakers. By aligning intrusion fingerprints with SAE J3061 automotive security standards, we provide a pathway for integrating machine learning into safety-critical AV systems. Our findings underscore the urgent need for security-by-design AI, ensuring that AVs not only drive autonomously but also defend autonomously. This work bridges the gap between theoretical cybersecurity and life-preserving engineering, offering a leap toward safer, more secure autonomous transportation.

97 MATHEMATICS AND COMPUTING↗

Experimental Benchmarking for High-Reproducibility, Cross-Institutional Evaluation of Iron Redox Electrochemistry

We present a practical case study standardizing experimental protocols between collaborators with the goal of understanding ferrous iron (Fe 2+ ) chemistry and improving the iron deposition reaction for energy-efficient, electrochemical iron production. The study of iron reactions can be difficult, as aqueous iron electrolytes exhibit complex behaviors that can lead to differing interpretation of ostensibly similar experiments. The question we want to answer: are we studying the same chemistry? Our protocols address inherent challenges such as the tendency for Fe 2+ to spontaneously oxidize to ferric iron (Fe 3+ ) and the production of hydrogen at the potentials of interest. Our standardized protocol, executed by four collaborators in different labs and institutions, yields high-reproducibility results, and identified glassy carbon electrode surface quality and Fe 3+ impurities in the salt as key factors with outsized effects on cyclic voltammetry measurements. The process of developing the protocols helped to troubleshoot underlying issues that created poorer reversibility and reproducibility. This study highlights the fact that even nominally straightforward electrochemical systems can yield vastly different outcomes due to small differences in experimental preparation and serves as a useful example for creating transparent and achievable standards for the generation of reliable datasets that can be widely used and shared.

Ketter, Benjamin [Argonne National Laboratory (ANL↗

Dark Energy Survey Year 6 Results: Photometric Dataset for Cosmology

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 <2 mmag. Y6 Gold augments DES DR2 with simultaneous fits to multiepoch photometry for more robust galaxy shapes, colors, and photometric redshift estimates. Y6 Gold features improved morphological star–galaxy classification with an efficiency of 98.6% and a contamination of 0.8% for galaxies with 17.5 < 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.

79 ASTRONOMY AND ASTROPHYSICS↗

Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales

As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.

Houben, Nikolaus↗

Roadmap and Benchmarking: Privacy in Federated Load Forecasting

Data-driven techniques for energy demand forecasting continue to emerge with promising impacts on distribution grid planning. However, the development of robust and generalizable machine learning models requires that representative high quality training data are available. Distributed energy resources have begun to embed intelligence, gathering large amounts of data on customer demand, behavior, and household devices that are connected to the grid. Though utilities aggregate meter-level demand data for load shaping, demand response, outage management, reliability planning, and billing applications, there lies an inherent privacy concern in sharing consumption data that may identify individual consumer behavioral patterns. Hence, while sharing the data is crucial, the private sensitive customer data must be safeguarded from being exposed or manipulated. In this study, we propose a roadmap for implementing a based privacy preserving framework to support the advancement of data-driven analytics in data-sensitive distributed energy resources environments. The roadmap incorporates federated learning–a distributed training framework, differential privacy–a statistical framework that provides guarantees to safeguard the leakage of sensitive data, secure multiparty computation and homomorphic encryption– techniques for encrypting model gradients and applying secure aggregation on the server. Moreover, we perform baseline experiments on the federated short-term load forecasting (STLF) task using open-source residential load profile datasets, offering insights into the challenges of integrating differential privacy into federated learning.

Abebe, Waqwoya [Oak Ridge National Laboratory (ORN↗

The New Landsat Image Mosaic of Antarctica; A Part of Your World You've Never Seen Before

The first-ever true-color, high-resolution digital mosaic of Antarctica has been produced from nearly 11 00 Landsat-7 ETM+ images. This project is an early 1999-2001 benchmark data set of the International Polar Year and represents a close and successful collaboration between NASA, USGS, the British Antarctic Survey and the National Science Foundation. The production of the mosaic required the development of new procedures for treating sensor saturation, adjusting for non-diffusive reflectance and for balancing color between images to remove distracting image edges. All adjustments were physically based to achieve the goal that each pixel's value is surface reflectance. This makes this mosaic more than just a pretty picture to guide users to individual scenes, but one where the mosaics can be used directly for quantitative research. The 15-m resolution, pan-sharpened mosaic, numerous derivative mosaics that enhance various ice sheet features, and the individual scenes are all served to the public via a web site hosted by the USGS. This site also enables on-line exploration of the various mosaics, including panning and zooming functions. Datasets can be customized by the user and downloaded. An associated web site, hosted by NASA, uses the mosaic as a means to demonstrate the value of satellite imagery of Antarctica. It is hoped this data set will enable the public and researcher alike a new and realistic view of the seventh continent.

Bindschadler, Robert↗