SEARCH · Search NASA

Results for “Continuous Optimization”

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.

SourceResearch connectionFrom yearThrough year

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

At least 451 records · Page 25

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Stability and Performance of 3d Transition Metal Carbo‐Sulfides: A Density Functional Theory Exploration for Li‐Ion Battery Anodes

As the demand for high-performance and reliable energy storage devices continues to rise, identifying new anode materials is crucial for advancing Li-ion battery (LIB) technology. Inspired by recent experimental breakthroughs in synthesizing two-dimensional transition metal carbo-chalcogenides (2D-TMCCs), density functional theory calculations are performed to systematically explore their sulfide variants (TM 2 S 2 C) spanning all 3d transition metals in three possible phases. Through comprehensive evaluations of thermodynamic, dynamic, mechanical, and thermal stabilities, seven stable 2D-TMCC candidates are identified, four of which exhibit superior battery performance. Notably, V-based 2D-TMCCs across all three phases deliver moderate open-circuit voltages (OCV), efficient Li diffusion, and substantial capacities, making them promising candidates for industrial applications without requiring specific phase controls. A Cr-based 2D-TMCC (with sulfur atoms above carbon atoms) offers the highest capacity of 515.40 mAh g −1 , the lowest Li diffusion barrier, and an optimal OCV, highlighting its appealing potential as an anode material for LIBs. Furthermore, significant Li–Li spacing and pronounced electron delocalization in these four 2D-TMCCs suggest a reduced risk of dendrite formation. This work expands the 2D-TMCC family and identifies up-and-coming candidates for next-generation LIB anodes.

anode materials↗

DOE OSTI2025

Optimizing Alabama’s CO 2 Storage in Shelby County (Project OASIS): Task 4.0 Deliverable – Geologic Analysis Report

Project OASIS (Optimizing Alabama’s CO 2 Storage in Shelby County) is a geologic and reservoir characterization study designed to evaluate deep saline formations for potential long-term carbon dioxide (CO 2 ) storage in central Alabama near the National Carbon Capture Center (NCCC) and Alabama Power’s Plant Gaston. The project centers on the Cambro-Ordovician Knox Group and underlying strata such as the Conasauga and Rome Formations, which were investigated through the drilling of two stratigraphic test wells to obtain electronic well logs, core, and sidewall core plugs. These data provide direct measurements of porosity, permeability, and lithologic variability critical for reservoir characterization. Complementing the well program, a limited 2D seismic survey was acquired to help select the site for Westover #2, and a more regional Seismic Exchange (SEI) seismic survey was licensed and interpreted to define structural and stratigraphic frameworks in a new Static Earth Model (SEM), map reservoir continuity, and identify potential sealing intervals. Integrated with geologic and reservoir modeling, these datasets form the basis for evaluating storage capacity, injectivity, and containment.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2025

Advancing Grid Resilience through Smart Charge Management: Findings from Maryland’s Pilot

This report presents research findings from a four-year Smart Charge Management (SCM) pilot program conducted by Maryland’s largest electric utilities—Baltimore Gas and Electric (BGE), Potomac Electric Power Company (Pepco), and Delmarva Power & Light (DPL)—to evaluate strategies for optimizing electric vehicle (EV) charging loads and enhancing grid stability. Supported by the U.S. Department of Energy (DOE), Argonne National Laboratory collaborated with all project partners and examined the effectiveness of Time-of-Use (TOU) and Load Balancing (LB) strategies in managing peak demand, deferring costly infrastructure upgrades, and reducing grid constraints at the feeder level. Using charging data from over 4,600 EV drivers, the study analyzed SCM’s impact on the distribution systems of BGE and Pepco, which consists of over 2000 feeders. Unlike prior research that focused on system-wide trends or synthetic feeders, this analysis offers granular, feeder-level insights based on real-world operational data. It highlights how transformer density, load profiles, and infrastructure constraints influence smart charging performance. Results show feeder-level conditions play a crucial role in SCM effectiveness, with most feeders benefiting more from LB, while TOU-based SCM may be sufficient for others. By 2035, LB reduced peak charging loads by 27% on average, compared to 23% under TOU-based SCM, though some feeders saw reductions exceeding 35%, while others experienced minimal impact. Feeders with higher transformer utilization and limited capacity benefited more from LB, which more effectively distributed charging demand during off-peak hours. Beyond reducing grid constraints, SCM offers long-term operational and financial benefits. By shifting EV charging demand strategically, utilities can optimize asset utilization, delay infrastructure investments, and enhance grid performance. In terms of infrastructure upgrade deferrals, at the feeder level, LB consistently reduced peak charging loads and resulting infrastructure upgrade costs, particularly in high EV enrollment areas, decreasing the number of overloaded transformers by up to 35%, while TOU-based SCM achieved 20-30% reductions depending on feeder characteristics. At the system level, LB has the potential to defer total upgrade costs by $\$$186 million for BGE, compared to $\$$159 million under TOU-based SCM. For Pepco, TOU-based SCM performed slightly better, deferring upgrade costs by $\$$30 million, compared to $\$$29 million under LB. Section 4.5 reviews some of the system differences between BGE and Pepco. However, as EV adoption scales, TOU-based SCM will introduce secondary peak charging loads, reinforcing the need for more advanced, adaptive SCM approaches to prevent new grid challenges. As EV adoption continues to grow, feeder-level managed charging strategies will be essential for mitigating grid stress, improving infrastructure efficiency, and maintaining energy affordability for consumers. This report provides critical insights for utilities, Public Utility Commissions (PUCs), and state agencies on the role of feeder-specific smart charging in infrastructure planning, policy development, and grid modernization. The findings underscore the importance of tailored, data-driven SCM solutions that align with local grid conditions, ensuring a resilient, cost-effective transition to increasing EV adoption while safeguarding distribution system performance.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

RAP: Resource-aware Automated GPU Sharing for Multi-GPU Recommendation Model Training and Input Preprocessing

Ensuring high-quality recommendations for newly onboarded users requires the continuous retraining of Deep Learning Recommendation Models (DLRMs) with freshly generated data. To serve the online DLRM retraining, existing solutions use hundreds of CPU computing nodes designated for input preprocessing, causing significant power consumption that surpasses even the power usage of GPU trainers. To this end, we propose RAP, an end-to-end DLRM training framework that supports Resource-aware Automated GPU sharing for DLRM input Preprocessing and Training. The core idea of RAP is to accurately capture the remaining GPU computing resources during DLRM training for input preprocessing, achieving superior training efficiency without requiring additional resources. Specifically, RAP utilizes a co-running cost model to efficiently assess the costs of various input preprocessing operations, and it implements a resource-aware horizontal fusion technique that adaptively merges smaller kernels according to GPU availability, circumventing any interference with DLRM training. In addition, RAP leverages a heuristic searching algorithm that jointly optimizes both the input preprocessing graph mapping and the co-running schedule to maximize the end-to-end DLRM training throughput. The comprehensive evaluation shows that RAP achieves 78.3× speedup on average over CPU-based DLRM input preprocessing frameworks. In addition, the end-to-end training throughput of RAP is only 2.04% lower than the ideal case, which has no input preprocessing overhead.

Wang, Zheng↗

DOE OSTI2025

Integrating Safety, Security, and Nuclear Operations for Advanced Reactors

The traditional separation between safety, security, and operations teams has created significant barriers to achieving optimal outcomes. When security considerations are introduced late in the design process, they often conflict with already-established architectural, operational, or engineering parameters. Retrofitting security measures can lead to increased costs, schedule delays, and compromises in security effectiveness. For instance, the need to retrofit physical barriers or surveillance systems often results in trade-offs that could have been avoided with earlier input from security professionals. Delayed integration can also affect regulatory processes and result in licensing delays. Security reviews conducted at later stages frequently identify gaps that necessitate significant redesign efforts, impacting not only scope, schedule, and budget, but also adding risk and lowering stakeholder confidence in the project. This paper aims to address these challenges by identifying practical opportunities for integrating security considerations seamlessly with design and operations teams throughout the entire lifecycle of nuclear facilities—from conceptual design to commissioning and beyond. The research emphasizes the value of early and continuous collaboration among stakeholders to ensure that security measures are robust, operationally effective, and cost-efficient. By examining case studies, analyzing past incidents, and leveraging best practices from other high-security industries, this study highlights actionable strategies for bridging the gap between safety, security, and operations teams.

Zineddin, Dr. Z. [ORNL] (ORCID:0009000848740725)↗

DOE OSTI2024

An electrochemical generator for the continual supply of 213 Bi from 225 Ac for use in targeted alpha therapy applications

Bismuth-213 is a radionuclide of interest for targeted alpha therapy and is supplied via a radiochemical generator system through the decay of 225 Ac. Radionuclide generators employ longer lived “parent” radionuclides to routinely supply shorter-lived “daughter” radionuclides. The traditional 225 Ac/ 213 Bi radiochemical generator relies on an organic cation exchange resin where 225 Ac binds to the resin and 213 Bi is routinely eluted. These resins degrade when they absorb large doses of ionizing radiation (>1 × 10 6 Gy/mg), which has been observed when the loading activity of 225 Ac exceeds 2.59*10 9 Bq (70 mCi). Herein we report the development of an electrochemical generator for the supply of 213Bi that has the potential to overcome this limitation. Bismuth-213 spontaneously electrodeposits onto nickel foils in 0.1 M hydrochloric acid at 70 °C. Using this method, we were able to plate an average of 73 ± 4 % of the 213 Bi in solution and obtain a final 213 Bi recovery of 65 ± 8 % in 0.1 M citrate pH 4.5 via reverse electrolysis using titanium as the cathode. The recovered 213Bi had an average radiochemical purity of >99.8 % and was successfully used to radiolabel DOTATATE with an average radiochemical yield of 85.1 % (not optimized).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

DS-GL: Advancing Graph Learning via Harnessing the Power of Nature within Dynamic Systems

With the rapid digitization of the world, an increasing number of real-world applications are turning to nonEuclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising machines, i.e., dynamic systems composed of CMOS components, have emerged as a new approach that harnesses the inherent power of natural annealing within dynamic systems to efficiently resolve binary optimization problems and have been adopted for traditional graph computation, such as max-cut. However, when performing complex Graph Learning (GL) tasks, Ising machines face significant hurdles: (i) they are inherently binary and thus ill-suited for real-valued problems; (ii) their expensive all-to-all coupling network that guarantees effective natural annealing poses daunting scalability concerns. To address these challenges, this paper proposes a nature-powered graph learning framework dubbed DS-GL, which is the first effort to transform the process of solving graph learning problems into the natural annealing process within a parameterized dynamic system embodied as a CMOS chip. To tackle the two major hurdles, DS-GL first augments the Ising machine architecture to modify the self-reaction term of its Hamiltonian function from linear to quadratic, effectively serving as an energy regulator. This adjustment maintains the system’s original physical interpretation while enabling it to process continuous, real-valued data. Second, to address the scaling issue, DS-GL further upgrades the real-valued dense Ising machine by decomposing it into a mesh-based multi-PE dynamic system that supports efficient distributed spatial-temporal co-annealing across different PEs through sparse interconnects. By exploiting the inherent sparsity and component structures in real-world graphs, DS-GL is able to map complex graph learning tasks onto the scalable dynamic system while maintaining high accuracy. Evaluations with three diverse GL applications across six real-world datasets, including traffic flow and COVID-19 prediction, show that DS-GL can deliver from 102× to 106× speedups and 500× energy reduction over Graph Neural Networks on GPUs, with 5% - 20% accuracy enhancement.

Song, Ruibing↗

DOE OSTI2026

Online LIBS–ML Framework for Dynamic Characterization of Heterogeneous Waste-Derived Gasification Feedstocks

LIBS−ML framework for real time feedstock characterization during continuous conveyor transport Heterogeneous waste derived feedstocks (e.g., waste coal, biomass and blends) introduce rapid variability in heating value and ash chemistry that affect gasifier operation, yet conventional laboratory characterization techniques are too slow to support proactive control. To address this gap, this study reports on an online, in situ, dynamic characterization framework that couple’s laser-induced breakdown spectroscopy (LIBS) with leakage safe machine learning (ML) regression to deliver real time, decision quality predictions of gasifier relevant properties. A controlled sample matrix spanning two different waste coals, two different biomasses, and engineered blends under two particle size conditions were constructed and benchmarked using standardized laboratory analyses for proximate/ultimate properties and ash composition. LIBS spectra were acquired dynamically as material flowed on a conveyor belt, using high energy 1064 nm laser ablation and shot averaging to improve repeatability and precision. Supervised regression models (multi layer perceptron (MLP) /artificial neural network (ANN), random forest (RF), and support vector regression (SVR)) and an optimized weighted ensemble were trained on emission line feature sets using nested cross validation with Bayesian hyperparameter tuning and validated against an independent hold out set. The proposed LIBS−ML workflow achieves near laboratory predictive fidelity across parametric targets (including higher heating value (HHV), ash content, fixed carbon, sulfur, major ash forming oxides, and initial deformation temperature (IDT)), with the weighted ensemble providing a robust default predictor under dynamic measurement conditions. These results demonstrate a practical pathway for real time feedstock characterization that can enable feedforward adjustments and more resilient gasifier operation for variable quality waste derived fuels.

Biomass↗

DOE OSTI2027

Conceptual design of highly-constrained splitters for the FFA@CEBAF energy upgrade study

The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab is investigating a significant energy upgrade utilizing Fixed-Field Alternating-gradient (FFA) recirculating arcs. This upgrade requires the design of complex horizontal beam splitters to manage up to six concurrent beam passes. This paper presents the conceptual design of these splitters, which are subject to severe physical constraints imposed by the existing accelerator tunnel and multifaceted beam dynamics requirements for matching into the permanent-magnet FFA arcs. The design methodology, centered on multi-pass simulations in the Bmad toolkit, is detailed from the initial geometric layout through the advanced optics matching. Key results include a robust geometric arrangement that fits within the spatial boundaries and the development of multiple, flexible optics matching solutions. Furthermore, the design integrates a viable scheme for extracting high-energy beams for the experimental halls, a critical operational requirement. This work establishes a comprehensive and viable conceptual design, forming a baseline for future engineering and performance optimization studies.

Bodenstein, R.M. [Thomas Jefferson National Accele↗

DOE OSTI2025

Electric Drive Technologies Consortium (EDTC)/ Cost competitive, high-Performance, highly Reliable (CPR) Power Devices on 4H-SiC (Final Report)

4H-Silicon carbide (4H-SiC) is a wide bandgap semiconductor that offers superior material properties over silicon, including higher critical electric field, thermal conductivity, and electron saturation velocity. These advantages make 4H-SiC highly attractive for high-voltage, high-efficiency power electronics. However, realizing the full potential of SiC requires device technologies that are not only high-performing but also manufacturable and reliable under real-world operating conditions. This report summarizes the outcomes of a five-year R&D effort funded by the U.S. Department of Energy (DOE) under the Electric Drive Technologies Consortium (EDTC), focused on developing cost-competitive, high-performance, and highly reliable (CPR) power devices on 4H-SiC substrates. The program targeted scalable and manufacturable 1.2 kV-class SiC MOSFETs optimized for next-generation electric vehicles, renewable energy systems, and industrial power conversion. The project delivered transformative advancements in SiC power device performance and ruggedness. Particularly, Specific on-resistance (R on,sp ) was reduced by up to 37%, from ~4.0 m$\Omega \cdot$cm 2 in earlier designs to an industry-leading 2.40 m$\Omega \cdot$cm 2 , driven by optimized doping, refined JFET widths, and layout engineering. Breakdown voltages (BV) exceeded 1600 V, marking improvement over legacy baselines, and demonstrating the robustness of newly implemented junction profiles and edge terminations. Short-circuit withstand time (SCWT) saw a remarkable 4$\times$ increase, from ~2 $\mu$s to over 8 $\mu$s, achieved through the successful deployment of deep P-well structures (~1.8–2.0 $\mu$m) via channeling implantation. This innovative process breakthrough enabled precise junction formation without MeV-class implantation tools, reduced leakage under high field stress, and allowed even the shortest-channel devices (down to 0.3 $\mu$m) to achieve both high BV and excellent ruggedness—breaking the traditional trade-off between conduction efficiency and blocking capability. Several novel architectures pushed the performance envelope further. JBSFETs—featuring embedded Schottky portions—eliminated bipolar degradation and drastically reduced third-quadrant leakage, while Ladder MOSFETs introduced a clever orthogonal conduction path that achieved a 15.4% reduction in R on,sp over standard linear designs. Switching performance reached new benchmarks: short-channel devices showed a 31% reduction in total switching energy compared to 0.5 $\mu$m counterparts, while maintaining manageable gate drive requirements. Layout-optimized structures not only improved transconductance but also accelerated switching transitions, pointing to real-world benefits in converter-level efficiency. The devices also passed rigorous reliability validation. Stress-tested across TDDB, HTGB, HTRB, HVP, and burn-in, the devices screened under 30 V/10 hr and 43 V/1 s protocols consistently exhibited tighter lifetime distributions and long-term oxide robustness. These screening techniques proved effective in identifying latent defects and ensuring deployment-grade reliability. Meanwhile, advanced 3D TCAD simulations revealed and resolved electric field hotspots—particularly in HEXFET corners—where fields exceeding 4.8 MV/cm were mitigated through geometry-aware layout corrections. Overall, the results of this project demonstrate a manufacturable and scalable SiC power device platform that addresses key DOE performance targets for efficient, robust, and reliable 1.2kV 4H-SiC Power Devices. The developed technologies represent a meaningful step forward in the commercial readiness of high-voltage SiC solutions and provide a strong foundation for continued advancement in wide bandgap power electronics.

42 ENGINEERING↗

DOE OSTI2025

Solving k –SAT problems with generalized quantum measurement

We generalize the projection–based quantum measurement–driven k –SAT algorithm of Benjamin, Zhao, and Fitzsimons to arbitrary strength quantum measurements, including the limit of continuous monitoring. In doing so, we clarify that this algorithm is a particular case of the measurement–driven quantum control strategy elsewhere referred to as “Zeno dragging”. We argue that the algorithm is most efficient with finite time and measurement resources in the continuum limit, where measurements have an infinitesimal strength and duration. Moreover, for solvable k -SAT problems, the dynamics generated by the algorithm converge deterministically towards target dynamics in the long–time (Zeno) limit, implying that the algorithm can successfully operate autonomously via Lindblad dissipation, without detection. We subsequently study both the conditional and unconditional dynamics of the algorithm implemented via generalized measurements, quantifying the advantages of detection for heralding errors. These strategies are investigated first in a computationally–trivial 2-qubit 2-SAT problem to build intuition, and then we consider the scaling of the algorithm on 3-SAT problems encoded with 4–10 qubits. We numerically investigate the scaling of 3-SAT with respect to algorithmic runtime and find that the optimized time to solution scales with qubit number n as λ n , where λ is slightly larger than $\sqrt{2}$ for unconditional dynamics and less than $\sqrt{2}$ for conditional dynamics. We assess the implications for using this analog measurement–driven approach to quantum computing in practice.

quantum information↗

DOE OSTI2024

Biophysical and Structural Features of αβT ‐Cell Receptor Mechanosensing: A Paradigmatic Shift in Understanding T‐Cell Activation

ABSTRACT αβT cells protect vertebrates against many diseases, optimizing surveillance using mechanical force to distinguish between pathophysiologic cellular alterations and normal self‐constituents. The multi‐subunit αβT‐cell receptor (TCR) operates outside of thermal equilibrium, harvesting energy via physical forces generated by T‐cell motility and actin‐myosin machinery. When a peptide‐bound major histocompatibility complex molecule (pMHC) on an antigen presenting cell is ligated, the αβTCR on the T cell leverages force to form a catch bond, prolonging bond lifetime, and enhancing antigen discrimination. Under load, the αβTCR undergoes reversible structural transitions involving partial unfolding of its clonotypic immunoglobulin‐like (Ig) domains and coupled rearrangements of associated CD3 subunits and structural elements. We postulate that transitions provide critical energy to initiate the signaling cascade via induction of αβTCR quaternary structural rearrangements, associated membrane perturbations, exposure of CD3 ITAMs to phosphorylation by non‐receptor tyrosine kinases, and phase separation of signaling molecules. Understanding force‐mediated signaling by the αβTCR clarifies long‐standing questions regarding αβTCR antigen recognition, specificity and affinity, providing a basis for continued investigation. Future directions include examining atomistic mechanisms of αβTCR signal initiation, performance quality, tissue compliance adaptability, and T‐cell memory fate. The mechanotransduction paradigm will foster improved rational design of T‐cell based vaccines, CAR‐Ts, and adoptive therapies.

Immunology↗

DOE OSTI2024

Vacuum-assisted extrusion to reduce internal porosity in large-format additive manufacturing

Large-scale 3D printing of polymer composite structures has gained popularity and seen extensive use over the last decade. Much of the research related to improving the mechanical properties of 3D-printed parts has focused on exploring new materials and optimizing print parameters to improve geometric control and minimize voids between printed beads. However, porosity at the microstructural level (within the printed bead) has been much less studied although it is almost universally observed at levels of 4 %-10 % when using fiber reinforced materials. This study introduces a vacuum-assist approach that minimizes internal porosity by removing ambient air from the interstitial space between pellets in the hopper and acts as a negative pressure vent for gases that evolve during the initial stages of single-screw extrusion. Vacuum-assisted extrusion was able to reduce porosity below 2 % across a wide range of processing parameters, moisture content, fiber reinforcements, and printing platforms. Specifically, when printing on a large-format extruder (Strangpresse Model-30), the vacuum-assisted extrusion reduced internal porosity by 35–75 % compared to conventional non-vacuum extrusion, and only pores with length scale > 2 microns are affected. The success of this approach prompted the design of a patent-pending continuous vacuum hopper relevant for large-scale 3D printing on commercial systems.

36 MATERIALS SCIENCE↗

DOE OSTI2026

F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding

Interactive time-varying volume visualization is challenging due to its complex spatiotemporal features and sheer size of the dataset. Recent works transform the original discrete time-varying volumetric data into continuous Implicit Neural Representations (INR) to address the issues of compression, rendering, and super-resolution in both spatial and temporal domains. However, training the INR takes a long time to converge, especially when handling large-scale time-varying volumetric datasets. In this work, we proposed F-Hash, a novel feature-based multi-resolution Tesseract encoding architecture to greatly enhance the convergence speed compared with existing input encoding methods for modeling time-varying volumetric data. The proposed design incorporates multi-level collision-free hash functions that map dynamic 4D multi-resolution embedding grids without bucket waste, achieving high encoding capacity with compact encoding parameters. Our encoding method is agnostic to time-varying feature detection methods, making it a unified encoding solution for feature tracking and evolution visualization. Experiments show the F-Hash achieves state-of-the-art convergence speed in training various time-varying volumetric datasets for diverse features. We also proposed an adaptive ray marching algorithm to optimize the sample streaming for faster rendering of the time-varying neural representation.

deep learning↗

DOE OSTI2024

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗

DOE OSTI2026

Progress Towards Synthesis of Uranium Chloride Fuel Salts Using Zinc Chloride

Reliable, scalable methods for producing high-purity actinide chloride salts are needed to support molten salt reactor fuel development and deployment. This report describes the continued development and demonstration of a bench-scale chlorination and purification apparatus using a zinc chloride-based method for synthesizing uranium chloride fuel salts. In this approach, uranium metal is chlorinated by ZnCl2 to produce LiCl-KCl-UCl3. Reaction with three aliquots of added uranium metal was used to generate a target uranium concentration of 30 wt %. While this concentration was chosen for initial testing of the apparatus and method, the final uranium concentration is not limited to 30 wt %. The zinc metal generated in the reaction forms an immiscible layer that was removed by volatilization at moderately high temperatures. Electrochemical measurements confirmed the removal of zinc and applied sensing methods indicated the uranium concentration to be approximately 25 wt %. These initial results demonstrate that the bench-scale chlorination apparatus is an effective platform for the synthesis and purification of uranium chloride salts using ZnCl2. This method shows promise for application to industry-relevant salt systems such as NaCl-UCl3. Further development is recommended to optimize reagent loading, zinc removal, and avoid possible U-Zn alloy formation.

Dulovic, Stephanie↗

DOE OSTI2025

Defining quantum-ready primitives for hybrid HPC-QC supercomputing: a case study in Hamiltonian simulation

As computational demands in scientific applications continue to rise, hybrid high-performance computing (HPC) systems integrating classical and quantum computers (HPC-QC) are emerging as a promising approach to tackling complex computational challenges. One critical area of application is Hamiltonian simulation, a fundamental task in quantum physics and other large-scale scientific domains. This paper investigates strategies for quantum-classical integration to enhance Hamiltonian simulation within hybrid supercomputing environments. By analyzing computational primitives in HPC allocations dedicated to these tasks, we identify key components in Hamiltonian simulation workflows that stand to benefit from quantum acceleration. To this end, we systematically break down the Hamiltonian simulation process into discrete computational phases, highlighting specific primitives that could be effectively offloaded to quantum processors for improved efficiency. Our empirical findings provide insights into system integration, potential offloading techniques, and the challenges of achieving seamless quantum-classical interoperability. We assess the feasibility of quantum-ready primitives within HPC workflows and discuss key barriers such as synchronization, data transfer latency, and algorithmic adaptability. These results contribute to the ongoing development of optimized hybrid solutions, advancing the role of quantum-enhanced computing in scientific research.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Error and Correction Analysis for the FFA@CEBAF Energy Upgrade

An energy upgrade design for the Continuous Electron Beam Accelerator Facility (CEBAF) is under development, using fixed field alternating gradient (FFA) return arcs to recirculate electron beam up to an additional five times through the accelerating structures at CEBAF. A necessary component of any large accelerator is a beam steering and optical correction system. Small environmental changes and system errors can lower beam quality or even shut down the machine; and in pursuit of the scientific mission of JLab, high quality electron beams must be delivered to the experimental halls on a predictable schedule. Correction in the novel FFA arcs of the current upgrade design is complicated by several factors. These complexities inform the choice of correction algorithm structure and parameter values. A baseline algorithm in addition to diagnostic and correction hardware configuration is presented. The effect of this correction protocol is shown with respect to estimated errors, and several possible extensions of the algorithm are discussed. This work presents an important proof of concept for the FFA@CEBAF design effort, and provides a functional correction strategy which may be simply adjusted and optimized for future design changes.

Coxe, Alex [Old Dominion Univ., Norfolk, VA (Unite↗