Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Generative models”

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 1,657 records · Page 92
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Model Package Report: Composite Analysis Solid Waste Release Model (CASWR Model)

This document describes the implementation of a solid waste form release model in GoldSim for the Hanford Site Composite Analysis (CA) Update. This Composite Analysis Solid Waste Release model (CASWR model) was designed to generate deterministic radionuclide release rates for Hanford’s Central Plateau solid waste disposal sites using single realizations of release model coefficients. Five generalized waste form types are used for the conceptual model of waste release: surplus reactor block, cement, soil-debris, grouted residual waste, and ancillary equipment. The surplus reactor block waste form consists of radionuclide leaching from surplus production graphite reactor core blocks via unspecified processes (White et al., 1984 as cited in PNNL-15965). The cement waste form represents solidified wastes whose permeability is much lower than that of the surrounding soil. The soil-debris waste form type is defined as unconsolidated waste mixed with soil material. Tanks and canyon complexes comprise the grouted residual waste form such that their solid waste will be grouted and capped with a surface barrier at the completion of their cleanup. Finally, the ancillary equipment waste form constitutes contaminant releases from ancillary and auxiliary waste form residues associated with tank farms at closure. Individual sub-models are implemented to numerically represent a respective waste form within the CASWR Model: Surplus Reactor Block Sub-model, Cement Sub-model, SoilDebris Sub-model, Grouted Residual Waste Sub-model, and Ancillary Equipment Submodel. Advection is assumed to be the primary transport process governing the release of radionuclides in the Ancillary Equipment and Soil-Debris Sub-models. Diffusion is assumed to be the primary release process in the Grouted Residual Waste and Cement Sub-models. An unspecified zero-order release process is considered in the Surplus Reactor Block Sub-model due to the lack of information regarding actual processes involved in irradiated graphite leaching. The Surplus Reactor Block, Cement, and SoilDebris Sub-models were compared against analytical solutions (PNNL-11800, Composite Analysis for Low-Level Waste Disposal in the 200 Area Plateau of the Hanford Site). The agreement between results of these analytical solutions and the corresponding waste form models verified their correct implementation in GoldSim. A 1-D modeling abstraction approach for the Grouted Residual Waste and Ancillary Equipment Sub-models was adopted from existing Performance Assessment (PA) models. Despite the simplifications made in these sub-models, they were found to be appropriate representations of the waste forms, similar to what was used in the Waste Management Area C PA model (RPP-ENV-58782, Performance Assessment of Waste Management Area C, Hanford Site, Washington, Rev. 0). A sensitivity analysis was conducted to identify the most influential parameters in each waste form sub-model. Suggestions for considering pH-dependent and redox-dependent release mechanisms are formulated through the development of a conditional constant approach in GoldSim.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2020

Solar Potential Analysis for the MISO Region

As part of the Minnesota Solar Pathways project, funded in part by the Department of Energy’s Solar Energy Technologies Office, Clean Power Research completed a scenario-based analysis that estimates and optimizes the levelized cost of capacity for high renewables penetrations across the entirety of the Midcontinent Independent System Operator (MISO) region. The analysis concludes that it can be cheaper to overbuild solar + wind and curtail surplus than to store all generation. The analysis described in this report was preceded by an analysis completed in 2018 that used the same modeling framework to optimize generation resources located only in Minnesota.

14 SOLAR ENERGY↗
DOE OSTI2022

Predicting failure parameters of semiconductor devices subjected to stress conditions

A method for predicting failure parameters of semiconductor devices can include receiving a set of data that includes (i) characteristics of a sample semiconductor device, and (ii) parameters characterizing a stress condition. The method further includes extracting a plurality of feature values from the set of data and inputting the plurality of feature values into a trained model executing on the one or more processors, wherein the trained model is configured according to an artificial intelligence (AI) algorithm based on a previous plurality of feature values, and wherein the trained model is operable to output a failure prediction based on the plurality of feature values. Further, the method includes generating, via the trained model, a predicted failure parameter of the sample semiconductor device due to the stress condition.

Ahmed, Moinuddin↗
DOE OSTI2023

Generating MCNP Input Files for Unstructured Mesh Geometries

The Los Alamos National Laboratory’s (LANL) Monte Carlo N-Particle (MCNP)1 transport code version 6.3 (also known as MCNP6.3) has the capability for tracking particles on unstructured mesh (UM) geometry models embedded into constructive solid geometry (CSG) cells. This feature has been developed for performing calculations of complex geometry models because manually creating CSG models is time-consuming and error-prone as the complexities of geometries increase. A UM geometry model is a collection of finite elements representing a solid geometry. The first step of the MCNP UM calculation is using other software packages to create a finite element mesh representation of a solid 3D geometry because the MCNP code cannot be used to generate a UM model. Computer-aided design (CAD) software is typically used to create a solid geometry model, which is later imported into mesh generation software to create a UM model. Some mesh generation software packages may also be used to create solid geometries and thus CAD files are not needed. The MCNP UM feature was originally designed for models generated by the Abaqus/CAE software suite. The MCNP code version 6.0 and later can process UM models formatted as Abaqus input files. Starting with a 6.3 version, the MCNP code can process HDF5 mesh input files. We only focus on the UM models formatted as Abaqus input files in this report since currently no external software can be used to generate HDF5 mesh input files for MCNP UM calculations. The MCNP code version 6.3 can be used to convert the Abaqus mesh input files into the HDF5 mesh input files, but this option is typically used by the MCNP code development team to test the HDF5 mesh input file feature. Several software packages (such as Abaqus, Attila4MC, or Cubit) can be used to create the Abaqus input files for MCNP UM calculations. An MCNP UM calculation using an Abaqus model requires two input file types: MCNP and Abaqus input files. The Abaqus input files needed for MCNP UM calcu lations must have the correct Abaqus syntax and meet the additional requirements by the MCNP code. The MCNP code can process only Abaqus input files that make use of part and assembly definitions, where elements in each part must be grouped into one or more element sets (i.e., elset) using *Elset keyword lines with specified naming formats. The MCNP and Abaqus input files required for MCNP UM simulations must be related; pseudo-cells in an MCNP input file must be constructed from mesh model data from an Abaqus input file. For large complex UM models, it is tedious to manually create MCNP UM input files. The um pre op (unstructured mesh pre operations) program with the -m option can be used to create a skeleton MCNP input file from an Abaqus input file [6]. Since the um pre op program was written in Fortran and was not written for optimized performance, this program is a deprecated feature in the MCNP code version 6.3 and may be removed in the next release of the code. To improve calculation flow of multiphysics calculations, a Python3 code called write mcnp um input has been developed to generate an MCNP input file instead of using the um_pre_op -m option. This Python code was initially released to the public in 2020. We have updated this Python code for MCNP6.3 and it was used to generate the MCNP input files used to verify the MCNP6.3 code. The write_mcnp_um_input code is included with the MCNP6.3 code package which will be released to the public through the Radiation Safety Information Computational Center (RSICC) at Oak Ridge National Laboratory. This report is a revision of LA-UR-20-27139 report.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

ATS (Advanced Terrestrial Simulator) integrated hydrology and reactive transport model output in Copper Creek, Colorado

This dataset is generated using the ATS (Advanced Terrestrial Simulator) model at Copper Creek, Colorado, the largest catchment in the East River watershed. ATS is an integrated hydrology and reactive transport model to simulate the Concentration-Discharge (C-Q) relationship, and is used to quantify the geochemical export and understand how watersheds respond to climate disturbances. Key hydrogeochemical variables, including discharge, precipitation, evapotranspiration, and geochemical concentrations, were simulated and output at a daily frequency at the Copper Creek outlet. A group of hydrology and geochemical model variables over the spatial domain are output at a bi-monthly frequency. The model used 1-km resolution daily frequency Daymet meteorological forcing, and mineral composition from previous studies. The simulations are performed on NERSC. The datasets include the input files for running the ATS (Advanced Terrestrial Simulator) simulation, including the mesh file, input script and geochemical model files. The output files from the ATS (Advanced Terrestrial Simulator) are the daily time-series discharge and geochemical concentration simulated at the outlet of Copper Creek, and the bi-monthly spatial output over the simulation domain.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Phases of confining SU(5) chiral gauge theory with three generations

We explore the possible low energy phases of the confining non-supersymmetric SU(5) chiral gauge theory with three generations of fermions in the (10+ $\bar{5}$) representations. This theory has the same fermion and gauge matter content as the simplest Georgi-Glashow grand unified theory of the Standard Model and has an SU(3) × SU(3) × U(1) global symmetry. Using ’t Hooft anomaly matching, most attractive channel, and soft SUSY breaking approaches, we outline a number of possible consistent low energy vacua including one with a remnant SO(3) × U(1) symmetry that is analogous to the one-generation model. For the soft SUSY breaking approach, we find that as one extrapolates to large SUSY breaking to recover the original theory, a phase transition is possible. We show that such a phase transition is guaranteed if SUSY breaking is communicated via anomaly mediation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Western Interconnection Baseline Study

The purpose of the baseline study is to evaluate the degree to which current industry planning processes meet the national 2035 decarbonization goals for the Western Interconnection. This analysis serves as a comparative baseline for the scenario analysis conducted in the NTP Study using a Western Interconnection dataset that is readily available to industry. This baseline analysis differs from the production cost modeling analysis and power flow analysis in the main NTP Study report (forthcoming). In particular, the analysis presented in this report reflects a business-as-usual future with an optimistic build out of specific planned transmission projects and foreseeable generation. In contrast, the NTP Study models a future generation and transmission expansion based on optimization from a capacity expansion model. The analysis presented herein also reflects a 2030 timeframe, whereas the main NTP Study production cost modeling analysis and power flow analysis reflect a 2035 time frame. This baseline analysis utilizes industry’s most reliable data to account for future transmission projects across various stages of development, with a particular focus on those in the permitting stage. Additionally, it incorporates projections for changes in generation capacity (both additions and retirements). This baseline analysis outlines a probable trajectory, given current process and practice, for the future of the bulk power system with a horizon extending to 2030.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Deep learning to estimate permeability using geophysical data

Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.

58 GEOSCIENCES↗
DOE OSTI2020

SUGAR: An improved empirical model of Type Ia supernovae based on spectral features

Type Ia supernovae (SNe Ia) are widely used to measure the expansion of the Universe. Improving distance measurements of SNe Ia is one technique to better constrain the acceleration of expansion and determine its physical nature. This document develops a new SNe Ia spectral energy distribution (SED) model, called the SUpernova Generator And Reconstructor (SUGAR), which improves the spectral description of SNe Ia, and consequently could improve the distance measurements. This model was constructed from SNe Ia spectral properties and spectrophotometric data from the Nearby Supernova Factory collaboration. In a first step, a principal component analysis-like method was used on spectral features measured at maximum light, which allowed us to extract the intrinsic properties of SNe Ia. Next, the intrinsic properties were used to extract the average extinction curve. Third, an interpolation using Gaussian processes facilitated using data taken at different epochs during the lifetime of an SN Ia and then projecting the data on a fixed time grid. Finally, the three steps were combined to build the SED model as a function of time and wavelength. This is the SUGAR model. Results. The main advancement in SUGAR is the addition of two additional parameters to characterize SNe Ia variability. The first is tied to the properties of SNe Ia ejecta velocity and the second correlates with their calcium lines. The addition of these parameters, as well as the high quality of the Nearby Supernova Factory data, makes SUGAR an accurate and efficient model for describing the spectra of normal SNe Ia as they brighten and fade. The performance of this model makes it an excellent SED model for experiments like the Zwicky Transient Facility, the Large Synoptic Survey Telescope, or the Wide Field Infrared Survey Telescope.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Linear simulation of magnetohydrodynamic plasma response to three-dimensional magnetic perturbations in high-β P plasmas

In this work, we report the numerical analyses of linear magnetohydrodynamics (MHD) plasma response to applied three-dimensional magnetic perturbations (MPs) in a joint DIII-D/EAST collaboration on high-β P (poloidal beta) plasmas, utilizing the extended-MHD code M3D-C1, with the purpose of realizing a better understanding of the existing experiment in which the n=3 MPs were applied to such high-β P plasmas attempting to control large amplitude type-I ELMs. Such high-β P plasmas obtained at the DIII-D tokamak feature an upper-biased double null configuration, a high edge safety factor q 95 ~6.4, and a stable internal transport barrier (ITB) leading to relatively high core pressures. Single-fluid simulations show that the plasma response to n=3 MPs, including both non-resonant/kinking and resonant components, is significantly weaker than that to n=1 or 2 MPs. To survey the impact of q 95 on plasma response to applied MPs, the SEGWAY (Self-consistent Equilibrium Generating Workflow for AnalYsis) module, developed in the OMFIT integrated modelling framework, is employed to generate a series of equilibria with a wide range of q 95 while other key parameters including the normalized beta, electron density at pedestal top, and plasma shape are kept fixed. Compared to the vacuum response, single-fluid M3D-C1 simulations predict a much more significant decrease of resonant plasma response to the applied n=3 MPs at the maximum penetration radii as q 95 increases. In contrast to single-fluid simulation results showing resonant penetration occurs only near the pedestal top where the E×B toroidal rotation frequency is zero, two-fluid simulations show two comparable resonant penetrations locating near the pedestal top and the ITB foot, where the perpendicular electron rotation frequency is zero. Such resonant field penetration near the ITB foot may be responsible for the observed formation of a staircase structure in both electron density and temperature profiles and thereby a considerable deterioration of global plasma performance when MPs are applied in high-β P plasmas. Motivated by this numerical work, we provide some ideas for the future research, with the purpose of realizing effective ELM control in such high-β P plasmas on the DIII-D and EAST devices.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Co-Optimization Scheme for Hybrid Electric Vehicles Powertrain and Exhaust Emission Control System Using Future Speed Prediction

Hybrid electric vehicles (HEVs) have been an effective solution for improved vehicle fuel efficiency and reduced emission pollution. In this paper, a co-optimization scheme is proposed to optimize fuel efficiency for HEVs. Here, the proposed optimization scheme uses obtainable future speed prediction as the basis to optimally tune control parameters for the existing powertrain control system. The ramp-up time of the catalyst temperature to reach its light-off level in the exhaust emission system is also considered as an additional optimization constraint to reduce emission. The Toyota Prius Hybrid Simulink model which is an integrated model for a powertrain and exhaust emission system is validated using real data from several real driving cycle scenarios. Then, to simplify the formulation of the proposed algorithm, the model for the optimization for powertrain and exhaust emission systems is represented by a set of equivalent neural network (NN) models learned using the data generated from the well-validated Toyota Prius Hybrid Simulink model. Using NN models, a co-optimization algorithm is established that provides an optimal tuning of some fuel-sensitive powertrain control parameters using future speed prediction, leading to a novel co-optimization algorithm, achieving on average a further 9.22% fuel savings for the Toyota Prius Hybrid Simulink model.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2023

A Process Model for ITCZ Narrowing under Warming Highlights Clear-Sky Water Vapor Feedbacks and Gross Moist Stability Changes in AMIP Models

Tropical areas with mean upward motion—and as such the zonal-mean intertropical convergence zone (ITCZ)—are projected to contract under global warming. To understand this process, a simple model based on dry static energy and moisture equations is introduced for zonally symmetric overturning driven by sea surface temperature (SST). Processes governing ascent area fraction and zonal mean precipitation are examined for insight into Atmospheric Model Intercomparison Project (AMIP) simulations. Bulk parameters governing radiative feedbacks and moist static energy transport in the simple model are estimated from the AMIP ensemble. Uniform warming in the simple model produces ascent area contraction and precipitation intensification—similar to observations and climate models. Contributing effects include stronger water vapor radiative feedbacks, weaker cloud-radiative feedbacks, stronger convection-circulation feedbacks, and greater poleward moisture export. The simple model identifies parameters consequential for the inter-AMIP-model spread; an ensemble generated by perturbing parameters governing shortwave water vapor feedbacks and gross moist stability changes under warming tracks inter-AMIP-model variations with a correlation coefficient ~0.46. Here, the simple model also predicts the multimodel mean changes in tropical ascent area and precipitation with reasonable accuracy. Furthermore, the simple model reproduces relationships among ascent area precipitation, ascent strength, and ascent area fraction observed in AMIP models. A substantial portion of the inter-AMIP-model spread is traced to the spread in how moist static energy and vertical velocity profiles change under warming, which in turn impact the gross moist stability in deep convective regions—highlighting the need for observational constraints on these quantities.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Videos, photos, and AI-derived grain size data associated with “High-throughput AI Video Surveys Enable Reproducible Multiscale Sediment Size Mapping, with Implications for Hydrobiogeochemical Parameterization”

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “High-throughput AI Video Surveys Enable Reproducible Multiscale Sediment Size Mapping, with Implications for Hydrobiogeochemical Parameterization” under review. This data package includes five data types: 1) raw photos and videos from drone survey and walking smartphone surveys; 2) images derived from raw videos; 3) manual labeling of reference scales; 4) metadata for all images and photo resolution derived from artificial intelligence (AI) models or manual labels, 5) grain size data obtained from AI models for all photos, 6) metadata and grain size data after quality control, 7) summaries of sample efficiency for all data, and 8) computational fluid dynamics (CFD) data used to support hydro-biogeochemical (HBGC) parameter estimation. Such data is used to 1) demonstrate significant improvements in accuracy, efficiency, and quality control for grain size data collection with the help of AI models, 2) study the spatial heterogeneity of grain size and observation reproducibility based on tens of thousands of data points generated by the AI models, and 3) evaluate the impacts of grain size heterogeneity on key HBGC parameters across sediment-to-reach and hourly-to-yearly scales. In particular, the data package contains 116 folders and 179696 files. The files include 41 videos in .mov format, 64047 photos in .jpg format, 13541 video-derived photos in .png format, 12747 segmentation mask data in .tif format, 12747 segmentation data in .json format, 24771 .csv files that with metadata and grain size for each individual photo as well as water depth and velocity data from CFD and observation, 51791 .txt files of raw AI predicted labels, and 11 flight record data in .srt format. The summary for all metadata and grain size statistics information is included in “Scales_V3_NG.csv” and “Statistics_V3_NG.csv”. The summary for data that pass data quality control (QC) level 0-2 is included in “QCStatistics_V3_NG.csv”. The QC level 0 represents photos whose photo resolution is positive, excluding photos that miss reference scale. The QC level 1 means reference scale circularity uncertainty is less than 5% for smartphone images while representing photo resolution is larger than 0.44 mm/pixel for drone images. The QC level 2 means excluding photos whose grain number is less than 100, a minimum number of grains recommended by classic literature. The summary for each video’s name, length, frame rates, survey area, grain number, survey efficiency, etc. can be found in “QCSummary_V3_NG.csv”. The summary for site name, GPS coordinates, and number of images at each site can be found in “SitesSummary_V3_*.csv” files. Overall computational efficiency summary is reported in Table 4 of accompanying manuscript. Additionally, the nitrate concentration data used in this work was downloaded from an existing dataset published on ESS-DIVE (Boat-Dragged Sensor Hanford Reach.csv; Conner A. et al., 2020). We thank the United States Forest Service, Washington Department of Fish and Wildlife, Washington Department of Natural Resources, Cowiche Canyon Conservatory, Port of Benton, and the Confederated Tribes and Bands of the Yakama Nation for access to field locations where the data were collected. We also thank the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate data collection and optimization of data usage according to their values and worldview.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Systems and methods for active learning from sparse training data

A method for active learning using sparse training data can include training a machine learning model using less than ten first training data points to generate a candidate machine learning model. The method can include performing a Monte Carlo process to sample one or more first outputs of the candidate machine learning model. The method can include testing the one or more first outputs to determine if each of the one or more first outputs satisfy a respective convergence condition. The method can include, responsive to at least one first output not satisfying the respective convergence condition, training the candidate machine learning model using at least one second training data point corresponding to the at least one first output. The method can include, responsive to the one or more first outputs each satisfying the respective convergence condition, outputting the candidate machine learning model.

Sankaranarayanan, Subramanian↗
DOE OSTI2025

LLMs for Mfg.—On the State of Large Language Models and Applications to Manufacturing

Additive Manufacturing (AM), referred to as 3D printing, has emerged as a key pillar of Industry 4.0 enabling layer-by-layer fabrication of intricate geometries from CAD models. In parallel, Large Language Models (LLMs), deep learning models for natural language generation trained on vast text corpora, have demonstrated unprecedented capabilities in understanding and generating human-like text. The convergence of these trends opens new opportunities at the intersection of AM and AI/ML, where LLMs can assist engineers and researchers in design, manufacture planning, and knowledge discovery. Recent academic work has begun to explore LLM applications in AM and adjacent fields, such as material science, mechanical engineering, and design for additive manufacturing. This exploration ranges from intelligent process planning to domain-specific knowledge retrieval. This survey provides a comprehensive review of current developments, focusing on peer-reviewed literature contributions that apply, adapt, and advance LLMs in general and domain-specific domains. We analyze state-of-the-art (SOTA) techniques, such as fine-tuning foundational models for specific domains, retrieval-augmented generation (RAG) pipelines, knowledge graph integration, and delve into the architectures and evaluation methods employed. The goal of this survey is to inform researchers and practitioners of the current capabilities and limitations of LLMs in general and in domain-specific applications, and to outline how these models are being tailored to meet the requirements of these applications.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Evaluating power grid model hydropower feasibility with a river operations model

Production cost models (PCMs) simulate dispatch of generators across a large power grid and are used widely by planners to study the reliability of electricity supply. As energy systems transition away from the thermoelectric technologies that have traditionally balanced electricity supply and demand, hydropower and its representation in PCMs is of increasing importance. A limitation of PCMs applied to continental power grids with diverse generation portfolios is that hydropower generation is simulated without full consideration of complex river dynamics, leading to possible misrepresentation of grid flexibility and performance. In addition, data used in PCMs may reflect outdated operating policies. In this paper we propose a hydropower generation feasibility test for PCMs. The approach uses a detailed hydropower model to determine whether the hourly hydropower schedule from a PCM with simplified monthly parameterization can be attained after accounting for realistic river dynamics and operating policies, such as spill requirements and general water movement and balance through a cascade reservoir system. We perform this hydropower generation test for the ‘Big 10’ hydropower system on the Columbia River (part of the Western Interconnect of the United States), revealing 9% overestimation of available hydropower generation in a PCM solution in an average hydrologic year. Our evaluation provides insight on the cost and opportunities for better representing hydropower in PCMs.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Neural Scaling Laws for Jet Generation

Recently observed empirical scaling laws describe the performance of foundation-type models as three independent key quantities -- dataset size, compute, and model parameters -- are modified. Extracting these scaling laws informs the training of large complex models for which the tuning of hyperparameters in traditional ways is not feasible. This work for the first time explores if scaling laws can also be observed for the task of particle jet generation -- both relevant as a pre-training objective for foundation models and as in-situ simulation by itself. We indeed replicate the key logarithmic scaling law behavior for model-size scaling. Beyond studying the next token prediction validation loss of the generative model, we also study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training. Our study shows that this quantity is monotonically related to the next token prediction validation loss, meaning that this loss is indeed a good proxy for the physics performance. For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance. We analyze this behavior by introducing the concept of a learnable window, and argue that autoregressive next token prediction on jet constituents exhibits comparatively rapid saturation relative to language-model studies. We discuss possible origins of this behavior, including the stochastic nature of QCD radiation and differences between generative and supervised learning tasks in collider physics.

Amram, Oz [Fermilab]↗
DOE OSTI2021

Quantifying the Influence of Charge Rate and Cathode-Particle Architectures on Degradation of Li-Ion Cells Through 3D Continuum-Level Damage Models

In this article, we develop a 3D, continuum-level damage model implemented on statistically generated LiNi 0.5 Mn 0.3 Co 0.2 O (NMC 532) secondary cathode particles. The primary motivation of the particle-level model is to inform cathode-particle design through detailed exploration of the influence of secondary and primary particle sizes on the damage predicted during operation, and determine charging profiles that reduce cathode fracture. The model considers NMC 532 secondary particles containing an agglomeration of anisotropic, randomly oriented grains. These brittle, Ni-based cathodes are prone to mechanical degradation, which reduces overall battery cycle life. The model predicts that secondary-particle fracture is primarily due to non-ideal grain interactions and high-rate charge demands. The model predicts that small secondary-particles with large grains develop significantly less damage than larger secondary particles with small grains. The model predicts most of the chemo-mechanical damage accumulates in the first few cycles. The chemo-mechanical model predicts monotonically increasing capacity fade with cycling and rate. Comparing to experimental results, the model is well suited for capturing initial capacity fade mechanisms, but additional physics is required to capture long-term capacity fade effects.

25 ENERGY STORAGE↗