model-of-perception
Algorithms for perceptually grounded evaluation of scientific visualizations, using neural reconstruction and embedding models to quantify clarity and interpretability.
Bujack, Roxana↗
SEARCH · Engineering Papers
Results for “embedding model”
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.
Towards a Methodology and Tooling for Model-Based Probabilistic Risk Assessment (PRA)
A Probabilistic Risk Assessment (PRA) aims to identify and assess potential risks to system technical performance requirements for the purpose of furnishing risk insights into project decisions. PRAs have traditionally been conducted manually using software with an isolated data model. As system complexity rises it becomes difficult to ensure consistency between a PRA, the evolving system design, and other engineering analyses; the techniques for conducting PRAs must evolve to meet this challenge. This work presents progress towards a methodology and tooling for conducting a PRA by leveraging data in the system model, embedded for other purposes and analyses, to conduct a PRA. An approach for identifying the appropriate probabilistic equation for each risk scenario from a standard library is presented, which is a significant step towards the quantification of the likelihood of a risk scenario occurrence. The final calculation of the likelihood of occurrence is left as an item of future work. We also present the development of preliminary tooling to carry out the methodology on a well-formed system model. The information needed to conduct the PRA is embedded in a consistent manner in a system model, so the model-based PRA can be regularly executed as the system model changes. The ability to modify the PRA in concert with lifecycle evolution affords a project the opportunity to track the extent to which system modification impacts compliance with requirements. These aspects of this model-based PRA methodology make it capable of managing risk in increasingly complex technical systems.
Schreiner, Samuel S.↗
Machine learning prediction of enzyme optimum pH
The relationship between pH and enzyme catalytic activity, especially the optimal pH (pH opt ) at which enzymes function, is critical for biotechnological applications. Hence, computational methods to predict pH opt will enhance enzyme discovery and design by facilitating accurate identification of enzymes that function optimally at specific pH levels, and by elucidating sequence-function relationships. Here, in this study, we proposed and evaluated various machine learning methods for predicting pH opt , conducting extensive hyperparameter optimization and training over 11,000 model instances. Our results demonstrate that models utilizing language model embeddings markedly outperform other methods in predicting pHopt. We present EpHod, the best-performing model, to predict pHopt, making it publicly available to researchers. From sequence data, EpHod directly learns structural and biophysical features that relate to pH opt , including proximity of residues to the catalytic centre and the accessibility of solvent molecules. Overall, EpHod presents a promising advancement in pH opt prediction and will potentially speed up the development of enzyme technologies.
97 MATHEMATICS AND COMPUTING↗
Dynamical models of highly flattened oblate elliptical galaxies with De Vaucouleurs' surface-brightness profiles
Two surveys of dynamical models of E6 elliptical galaxies were constructed with de Vaucouleurs'surface-brightness distributions. One set of models has a constant mass-to-light ratio. The other set consists of models embedded in oblate isothermal gravitational potentials. In both sets, the observed axis ratio of the models is 0.55 when viewed edge-on. When viewed edge-on, it is possible to construct models in either potential that have velocity-dispersion profiles that increase or decrease with radius along either or both principal axes. The observational data seem to indicate that dispersion profiles decrease or remain constant as function of radius. The most surprising result of this work is that in order for a model to have velocity-dispersion profiles that decrease with radius out to 1.5 r(e) along both principal axes, it must be dominated by fairly thin-walled tube orbits at large radii. This is very different from the spherical case, where radial orbits dominate at large radii.
Fillmore, James A.↗
Plastics Environmental Risk Calculator
SF-24-074 The Plastics Environmental Risk Calculator (PERC) was developed in Microsoft Excel and estimates the environmental distribution and lifetime of new biobased and conventional plastics from commonly measured properties of the plastics. A Random Forest regression model embedded in the calculator calculates plastic degradation rates and lifetimes as a proxy for environmental risk. Model default assumptions may be overwritten by the user.
Beckman, Kevin [Argonne National Laboratory (ANL),↗
Processing MCNP Elemental Edit Outputs
The Monte Carlo N-Particle (MCNP) transport code version 6 (also known as MCNP6) has the capability for tracking particles on unstructured mesh (UM) geometry models embedded into constructive solid geometry (CSG) cells. A UM geometry is a collection of elements representing a solid geometry. The first step of MCNP UM modeling is using other software packages to create a finite element mesh representation of a solid 3D geometry. Computer-aided design (CAD) or computer-aided manufacturing (CAM) software is typically used to create a solid geometry model, which is later imported into mesh generation software to create a UM model. The MCNP UM feature was originally designed for models generated by the Abaqus/CAE software. The MCNP code version 6.0 and later can process UM models formatted as Abaqus input files. MCNP can process a UM model consisting of several different element types including linear tetrahedral or hexahedral elements and calculate quantities of interest such as flux and energy deposition at elements. An MCNP UM simulation provides high-fidelity elemental edit (i.e., tally) outputs, which can be further used in multiphysics calculations. The MCNP UM feature was used for multiphysics simulations where quantities of interest calculated by MCNP are used as inputs for heat transfer calculations in Abaqus. MCNP6.3 can produce two types of elemental edit output (EEOUT) file formats: ASCII and HDF5. An EEOUT file type must be requested on an EMBED card while output type (flux or energy deposition) must be requested on an EMBEE card. We wrote Python3 scripts to extract energy deposition values in an ASCII or HDF5 EEOUT file and compute a heat flux profile for an Abaqus heat transfer calculation.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
Hierarchical Simulation to Assess Hardware and Software Dependability
This thesis presents a method for conducting hierarchical simulations to assess system hardware and software dependability. The method is intended to model embedded microprocessor systems. A key contribution of the thesis is the idea of using fault dictionaries to propagate fault effects upward from the level of abstraction where a fault model is assumed to the system level where the ultimate impact of the fault is observed. A second important contribution is the analysis of the software behavior under faults as well as the hardware behavior. The simulation method is demonstrated and validated in four case studies analyzing Myrinet, a commercial, high-speed networking system. One key result from the case studies shows that the simulation method predicts the same fault impact 87.5% of the time as is obtained by similar fault injections into a real Myrinet system. Reasons for the remaining discrepancy are examined in the thesis. A second key result shows the reduction in the number of simulations needed due to the fault dictionary method. In one case study, 500 faults were injected at the chip level, but only 255 propagated to the system level. Of these 255 faults, 110 shared identical fault dictionary entries at the system level and so did not need to be resimulated. The necessary number of system-level simulations was therefore reduced from 500 to 145. Finally, the case studies show how the simulation method can be used to improve the dependability of the target system. The simulation analysis was used to add recovery to the target software for the most common fault propagation mechanisms that would cause the software to hang. After the modification, the number of hangs was reduced by 60% for fault injections into the real system.
Ries, Gregory Lawrence↗
The effects of streamline curvature and swirl on turbulent flows in curved ducts
A technique for improving the numerical predictions of turbulent flows with the effect of streamline curvature is developed. Separated flows, the flow in a curved duct, and swirling flows are examples of flow fields where streamline curvature plays a dominant role. A comprehensive literature review on the effect of streamline curvature was conducted. New algebraic formulations for the eddy viscosity incorporating the kappa-epsilon turbulence model are proposed to account for various effects of streamline curvature. The loci of flow reversal of the separated flows over various backward-facing steps are employed to test the capability of the proposed turbulence model in capturing the effect of local curvature. The inclusion of the effect of longitudinal curvature in the proposed turbulence model is validated by predicting the distributions of the static pressure coefficients in an S-bend duct and in 180 degree turn-around ducts. The proposed turbulence model embedded with transverse curvature modification is substantiated by predicting the decay of the axial velocities in the confined swirling flows. The numerical predictions of different curvature effects by the proposed turbulence models are also reported.
Cheng, Chih-Hsiung↗
An Embedded Bottom Boundary Layer Formulation for Z-Coordinate Ocean Models
An embedded bottom boundary layer (EBBL) scheme is developed to improve the bottom topographic representation in z-coordinate ocean general circulation models.
embedded bottom boundary layer ocean circulation o↗
Convergent Manufacturing of Large-Scale Components for Nuclear Applications, via Additive Manufacturing and Powder Metallurgy Hot Isostatic Pressing
Powder metallurgy (PM)–hot isostatic pressing (PM-HIP) has long been recognized as a powerful route for producing fully dense, near net shape metallic components. By consolidating powders under high temperature and pressure, HIP provides isotropic properties, uniform microstructures, and scalability to complex geometries that are vital for sectors such as aerospace, energy, and nuclear power. Yet despite these advantages, the technology has remained constrained by costly trial and error canister fabrication, limitations of conventional forging, and incomplete knowledge about how the canister design influences final part properties. Additive manufacturing (AM), by contrast, thrives on design freedom and geometric flexibility but struggles with speed, scalability, and cost when applied to very large structures. The research presented in this report investigated how a convergent manufacturing approach, combining AM with PM-HIP, can merge the strengths of both technologies, leveraging AM’s flexibility for canister design and HIP’s consolidation capability to deliver reliable, large, and complex parts. The work progressed through three case studies that built on one another in scale and complexity. Small cylindrical canisters fabricated by conventional methods, laser powder bed fusion, and directed energy deposition were filled with stainless steel powders and subjected to HIP. The resulting parts demonstrated near-full density and mechanical properties on par with wrought stainless steel, showing for the first time that AM canisters can be a direct substitute for conventional ones without sacrificing quality. The next step involved a medium-scale, noncentrosymmetric T-valve, which is an enclosed, multibranch geometry that tested the limits of AM + PM-HIP integration. The T-valve achieved predictable shrinkage and uniform densification, confirming feasibility for enclosed designs. However, this study also revealed oxide inclusions and interfacial challenges at the AM + HIP boundary, underscoring the critical importance of controlling interface chemistry and employing robust, in situ strategies, such as melt pool monitoring and thermal monitoring, coupled with nondestructive evaluation techniques such as x-ray computed tomography. Finally, the effort culminated in fabricating a large-scale impeller weighing nearly 2000 lb and spanning 5 ft in diameter. Produced via multirobot wire arc AM and hot isostatic pressed to near-full density, the impeller validated industrial-scale feasibility. Predictive models closely matched experimental shrinkage, tensile properties were spatially uniform across the component, and the AM + PM-HIP interface proved mechanically sound despite the presence of oxide-decorated prior particle boundaries. This large-scale demonstration is a major milestone, showing that hybrid AM + PM‑HIP can reliably deliver components at reactor-relevant scales. Collectively, these studies charted a logical pathway: small-scale work built scientific confidence, medium-scale work highlighted opportunities and challenges, and large-scale work proved industrial impact. The overarching conclusion of this report is that AM + PM-HIP should not be seen as a replacement for forging but as a complementary pathway that provides the US with flexibility, resilience, and new options for manufacturing nuclear-grade components. Looking ahead, several directions emerge as critical to sustaining progress. Predictive modeling must become faster, more accessible, and more accurate, with digital twins and machine learning reducing reliance on trial and error. Powders and alloys must be optimized for HIP, with improved cleanliness, reduced oxides, and tailored chemistries that enhance creep, fatigue, and irradiation resistance. Interfaces between AM and HIP regions must be better engineered through coatings, machining strategies, and surface treatments to mitigate oxide formation and ensure reliable bonding to explore opportunities for HIP of targeted compositional parts, as well as multimaterial HIP cladding applications. Monitoring and nondestructive evaluation need to expand, incorporating multimodal sensors, x-ray computed tomography, and real-time data integration through platforms such as Pelican. At the same time, the pathway to industrial adoption requires techno-economic analysis, machinability studies, and qualification frameworks aligned with industry and regulatory standards. Finally, workforce and academic engagement must be strengthened. Programs that train technicians and engineers for US Navy and US Department of Energy manufacturing challenges should be paired with academic partnerships to support fundamental research, with open sharing of non-export-controlled data to accelerate innovation and build the next generation of experts. In conclusion, this report demonstrates that hybrid AM + PM-HIP is scientifically viable and strategically important. By combining the design agility of AM with the consolidation strength of HIP and embedding modeling, monitoring, and workforce development, this approach provided a transformative new capability for US manufacturing. The path forward is clear: hybrid AM + PM-HIP is not just a promising research direction but is also potentially an industrially relevant pathway that can reshape how nuclear-grade components are designed, qualified, and deployed.
36 MATERIALS SCIENCE↗
Bayesian Estimation of Precipitation from Satellite Passive Microwave Observations Using Combined Radar-Radiometer Retrievals
Precipitation estimation from satellite passive microwave radiometer observations is a problem that does not have a unique solution that is insensitive to errors in the input data. Traditionally, to make this problem well posed, a priori information derived from physical models or independent, high-quality observations is incorporated into the solution. In the present study, a database of precipitation profiles and associated brightness temperatures is constructed to serve as a priori information in a passive microwave radiometer algorithm. The precipitation profiles are derived from a Tropical Rainfall Measuring Mission (TRMM) combined radar radiometer algorithm, and the brightness temperatures are TRMM Microwave Imager (TMI) observed. Because the observed brightness temperatures are consistent with those derived from a radiative transfer model embedded in the combined algorithm, the precipitation brightness temperature database is considered to be physically consistent. The database examined here is derived from the analysis of a month-long record of TRMM data that yields more than a million profiles of precipitation and associated brightness temperatures. These profiles are clustered into a tractable number of classes based on the local sea surface temperature, a radiometer-based estimate of the echo-top height (the height beyond which the reflectivity drops below 17 dBZ), and brightness temperature principal components. For each class, the mean precipitation profile, brightness temperature principal components, and probability of occurrence are determined. The precipitation brightness temperature database supports a radiometer-only algorithm that incorporates a Bayesian estimation methodology. In the Bayesian framework, precipitation estimates are weighted averages of the mean precipitation values corresponding to the classes in the database, with the weights being determined according to the similarity between the observed brightness temperature principal components and the brightness temperature principal components of the classes. Because the classes are stratified by the sea surface temperature and the echo-top-height estimator, the number of classes that are considered for retrieval is significantly smaller than the total number of classes, making the algorithm computationally efficient. The radiometer-only algorithm is applied to TMI observations, and precipitation estimates are compared with combined TRMM precipitation radar (PR) TMI reference estimates. The TMI-only algorithm, supported by the empirically derived database, produces estimates that are more consistent with the reference values than the precipitation estimates from the version-6 TRMM facility TMI algorithm. Cloud-resolving model simulations are used to assign a latent heating profile to each precipitation profile in the empirically derived database, making it possible to estimate latent heating using the radiometer-only algorithm. Although the evaluation of latent heating estimates in this study is preliminary, because realistic conditional probability distribution functions are attached to latent heating structures in the algorithm s database, a generally positive impact on latent heating estimation from passive microwave observations is expected.
Grecu, Mircea↗
Frictionless knowledge injection for few-shot learning
Cutting-edge machine learning methods often require large volumes of curated training data, precluding their use in national security problems with rare events in massive datasets. We present a method for incorporating abstract knowledge into models tailored for sparse data. A subject matter expert defines salient concepts using data examples, which are encoded in the model’s embedding space. Models are then trained to respect these concepts. This method enables knowledge injection, yielding effective models with limited labeled data and the ability to assess model sensitivity for subject matter expertise across the nonproliferation mission space, as demonstrated with Raman spectra analysis.
Stomps, Jordan [ORNL] (ORCID:0000000178114479)↗
Probing multi-dimensional composition spaces in search of strong metallic alloys
Refractory complex concentrated alloys (RCCA) offer exceptionally high-temperature strength compared to pure metals and dilute alloys, but predictive theory for RCCA design is lacking. We present large-scale molecular Dynamics (MD) simulations of crystal plasticity to explore alloy compositions for maximum mechanical strength, focusing on Fe-Ta-W and Nb-Ta-Mo-W alloy families modeled with Embedded Atom Model (EAM) and Spectral Neighbor Analysis Potentials (SNAP). To efficiently guide the search for strong alloy compositions, we employ iterative optimization using Gaussian process regression. Many simulated RCCA compositions exhibit pronounced cocktail strengthening, with strengths surpassing their strongest constituent metal, tungsten. Contrary to expectations, the highest strength is found on binary edges of the RCCA composition space. Detailed analyses of atomistic simulations reveal that, similar to pure BCC metals, plastic response in RCCA is primarily governed by screw dislocations. However, at large strains, dislocation multiplication and interactions (Taylor hardening) become the dominant mechanisms contributing to RCCA strength.
Materials science↗
Deviations from the Isobaric Multiplet Mass Equation due to Threshold States
Recent studies have completed the A=16 isospin quintets for states with J π =0 + and 2 + . The dependence of their masses as a function of isospin projection shows evidence for deviations from quadratic behavior indicating isospin violation beyond the expectation from two-body forces. The deviation is most pronounced for the 2 + states. Predictions from the shell model embedded in the continuum (SMEC) allow us to explain that this isospin violation is associated with a modification of the nuclear structure due to the open-quantum-system nature of the proton-rich members of the quintet. In particular, the 0 + and 2 + states in 16 Ne and the 2 + state in 16 F are threshold resonances located just above a proton-decay threshold where s-wave coupling to the continuum is expected. The measured deviations of these threshold states from the quadratic behavior of the remaining members of the multiplets makes it possible to obtain information on the magnitude and the energy dependence of the continuum-coupling energy correction. Finally, continuum coupling is also indicated for the ground state of 8 C, but this time through p-wave coupling
coulomb energies & analogue states↗
Machine learning approaches for integrating multi-omics data to expand microbiome annotation (Final Technical Report)
We fulfilled all original three aims of the proposal. Following the earlier release (during the first phase of the project at Montana) of software that identifies and fills gaps in the annotation of metabolic proteins within bacterial genomes, we have nearly completed a second gap-filling tool that improves accuracy and explainability. We completed software for alignment-based annotation of protein coding DNA, allowing for coding frameshifts caused by sequencing error. Finally, we completed a neural embedding model for identifying similarities between protein sequences based on amino-wise latent vectors.
59 BASIC BIOLOGICAL SCIENCES↗
Facial Named Entity Recognition by Attention-Based Graph Convolutional Neural Network
In the realm of facial recognition and analysis, the ability to accurately cluster large datasets of facial images stands as a cornerstone for various applications, ranging from security surveillance to user biometric identification. This project evolves a novel approach to facial data clustering by embedding facial images into a high-dimensional vector space using an advanced embedding model trained on separate data and assumes a graph-like structure on the high-dimensional vectors. We find our method works significantly better than common shallow methods.
97 MATHEMATICS AND COMPUTING↗
Knowledge Graph Entity Linking using Graph Embeddings
Details the use of a custom embedding model on knowledge graphs to aid in downstream natural language processing (NLP) models for Derivative Classification Assist. Motivations, algorithms, and results were discussed.
Mahesh, Aarav [Sandia National Laboratories (SNL-N↗
FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging
We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.
47 OTHER INSTRUMENTATION↗