Search NASA⌕ Search

SEARCH · Search NASA

Results for “task work”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Extracting Material Property Measurements from Scientific Literature with Limited Annotations

Extracting material property data from scientific text is pivotal for advancing data-driven research in chemistry and materials science; however, the extensive annotation effort required to produce training data for named entity recognition (NER) models for this task often makes it a barrier to extracting specialized data sets. Here, in this work, we present a comparative study of the conventional, supervised NER methodology to alternative few-shot learning architectures and large language model (LLM)-based approaches that mitigate the need to label large training data sets. We find that the best-performing LLM (GPT-4o) not only excels in directly extracting relevant material properties based on limited examples but also enhances supervised learning through data augmentation. We supplement our findings with error and data quality assessments to provide a nuanced understanding of factors that impact property measurement extraction.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Best Practices for Equitable Solar Workforce Development

The Midwest Renewable Energy Association (MREA) was selected to serve as a lead organization for the U.S. Department of Energy Solar Energy Technology Office’s Equitable Solar Communities of Practice initiative. This project, facilitated through a partnership with ENERGYWERX, aimed to develop strategies to support the expansion of equitable benefits in solar adoption across the U.S. Specifically, the MREA was chosen to lead the solar workforce development community of practice, focusing on scaling the U.S. solar workforce, to meet growing industry demands and ensure that these opportunities are accessible and beneficial to all communities. For the purpose of this initiative, we define the solar workforce in line with the National Solar Jobs Census, which defines a solar worker as someone who spends a majority of their time on solar-related work. This also includes workers who spend a plurality of their time on solar tasks. It’s important to note that manufacturing jobs were not included in this research, as the focus is primarily on solar installation, development, and related roles. To achieve the goals of the Equitable Solar Communities of Practice initiative, the MREA leveraged existing resources and engaged a diverse core team and group of stakeholders including industry professionals, educators, policymakers, and community leaders. The MREA began with a literature review and gap analysis to identify existing best practices and gaps in the solar workforce. This was followed by a community convening to gather insights from a wide range of stakeholders. The findings informed the best practices and pathways to scale the benefits of solar workforce development, focusing on training programs, workforce services, apprenticeship, and justice, inclusion, and sustainability. This report outlines the background, methodology, findings, and conclusions drawn from the landscape and gap analysis, providing valuable insights into workforce needs and training program capacities across the U.S. The outcomes of this research are presented in this report and contain recommendations for optimizing workforce development and training funding to support the equitable growth of the solar industry, ensuring that the transition to solar energy is inclusive and beneficial for all communities.

14 SOLAR ENERGY↗
DOE OSTI2025

FY25 Mid-Year Report: FABIA In-Field Laser Absorption Spectroscopy for UF6 Enrichment

From September 2024 through April 2025, the FABIA team has been working towards completing the IAEA requirements for technology transfer of the instrument. The primary tasks in place for this transfer are to complete a validation study using various enrichments of UF6, to finalize the data analysis routines in the FABIA software, and to complete FABIA electrical component compatibility. These topics are expanded in greater detail below. In addition to the tasks, the FABIA team hosted IAEA representatives to observe a live analysis demonstration of the FABIA instrument on February 3, 2025. As a result of this visit, some updates to the tasks were communicated.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Multi-fidelity equations of state and transport coefficient datasets for pulsed-power applications

Reliably simulating experiments relevant to the National Nuclear Security Administration (NNSA) requires a detailed description of material properties across a wide range of conditions. Such properties include the equations of state, charged-particle transport coefficients, and optical properties like the opacity. Together, these properties make up the material models used in radiation-magnetohydrodynamic simulations of nuclear fusion experiments. Many of these models do not incorporate uncertainties in the data used to produce them. It is unknown whether these uncertainties significantly impact the interpretation of simulation results and diagnostics. The purpose of this work is to quantify how such uncertainties impact simulations of pulsed-power experiments. We accomplished this task by first assessing discrepancies between approaches used to generate the data. This included bringing together members of the high-energy-density community spanning the three NNSA laboratories and multiple universities. Then, using these data, we developed a general framework that systematically incorporates physical uncertainties within the material models suitable for uncertainty quantification analyses. The framework utilizes machine learning, Bayesian inference, and incorporates multi-fidelity datasets. We demonstrated the framework by quantifying the impact that material model uncertainties have on simulations of pulsed-power experiments underway on Z at Sandia National Laboratories. As a result of this work, we discovered that modest uncertainties in material models (roughly 20%) correspond to significant uncertainties in the outputs from simulations. Our framework has enabled rapid construction of material models through an automated procedure and allows for the generation of material models of interest to the NNSA.

36 MATERIALS SCIENCE↗
DOE OSTI2025

ChatPORT: Fine-Tuned LLM for Easy Code {PORT}ing

Fine-tuning existing LLMs for specialized tasks has become a very attractive alternative due to its low cost and quick development cycle. With many pre-trained LLMs available, it is an increasingly complex task to choose the correct model as the starting point or base model. In this work we discuss ChatPORT - a specialized fine-tuned LLM geared towards providing correctly translated codes from one programming model to another. We evaluate a number of base models and compare and contrast their features and characteristics that make them a viable starting point. In this paper, we focus on the OpenMP offload porting capabilities of ChatPORT. We build our training data using kernels from the Heterogeneous Computing Benchmarks (HeCBench) [12] and the OpenMP Validation and Verification suite [5] to fine-tune the base models. We then test the model using unseen kernels extracted from the HeCBench benchmark suite. Our results show that: (1) not all open LLMs geared towards HPC are aware of programming models like OpenMP, (2) although all base models benefit from fine-tuning they learn differently and produce different correctness rates, (3) depending on the memory size and compute resource available, different base models can be used for fine-tuning without significantly affecting the quality of transpiled code they generate, (4) fine-tuning improved the correctness rate of the LLM by an average of 43.2%, and (5) feedback-based training data further increased the correctness rate by an average of 6% over the LLMs tested.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗
DOE OSTI2024

Machine learning-guided discovery of polymer membranes for CO 2 separation with genetic algorithm

Designing polymer membranes with high gas permeability and selectivity is a difficult multi-task constrained problem due to the trade-off between these two properties. In this work, we present a machine learning (ML) driven genetic algorithm to tackle the design problem of polymer membranes for CO 2 separation from N 2 and O 2 . Using literature data of permeability for three gases, we constructed multiple ML models with different fingerprinting featurization schemes to predict gas permeabilities. Then, we employed a genetic algorithm to design new polymers and evaluated their performance using our ML models. We were able to identify new polymer membranes that are promising for both CO 2 /N 2 and CO 2 /O 2 separations. Further, the top discovered polymers are predicted to have high glass transition temperatures. Similarly, the pyridine functionality was found in ≈20% of the predicted polymers. This framework can be used to design polymers for any application involving constrained optimization. Finally, we outlined the challenges and opportunities with using ML guided data-driven inverse design of polymers.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Chemical signature characterization with hyperspectral imagery: novel deep learning model architectures and physically-motivated data augmentation techniques

The high spectral resolution afforded by Hyperspectral Imaging (HSI) sensors is poised to bring unprecedented advancements to signature characterization applications. Thus far, much of the research in the machine learning field devoted to HSI applications has focused on a few specific tasks like land-use land-cover classification. In land classification tasks, spatial information is very important, and model architectures are often designed to leverage spatial contexts. However, it is unclear how well these spatially-tuned models will translate to tasks where spectral information is critical, like the detection and characterization of chemicals. In this work, we compare spectral models (inputs are 1D spectra) and spatial-spectral models (inputs are 3D cubes) in the context of predicting chemical concentration maps. We find that spatial-spectral models perform the best, though we find a wide range in performance across the different architectures tested. Additionally, we find that model performance is impacted by the availability of training data, particularly in scenarios where the training data doesn't fully capture the true variance of real-world conditions. We find that data augmentation can help mitigate sparse coverage of observed parameter space (e.g., seasonal or geographic variability in ground cover), and present augmentation strategies that are tailored to hyperspectral data.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2024

Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning

Despite the dramatic progress in Large Language Model (LLM) development, LLMs often provide seemingly plausible but not factual information, often referred as hallucinations. Retrieval-augmented LLMs provide a non-parametric approach to solve these issues by retrieving relevant information from external data sources and augment the training process. These models helps to trace evidence from an externally provided knowledge base allowing the model predictions to be better interpreted and verified. In this work, we critically evaluate these models in their ability to perform in scientific document reasoning tasks. To this end, we tuned multiple such model variants with science-focused instructions and evaluated them on a scientific document reasoning benchmark for the usefulness of the retrieved document passages. Our findings suggest that models justify predictions in science tasks with fabricated evidence and leveraging scientific corpus as pretraining data does not alleviate the risk of evidence fabrication.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2025

Learning the simplicity of scattering amplitudes

The simplification and reorganization of complex expressions lies at the core of scientific progress, particularly in theoretical high-energy physics. This work explores the application of machine learning to a particular facet of this challenge: the task of simplifying scattering amplitudes expressed in terms of spinor-helicity variables. We demonstrate that an encoder-decoder transformer architecture achieves impressive simplification capabilities for expressions composed of handfuls of terms. Lengthier expressions are implemented in an additional embedding network, trained using contrastive learning, which isolates subexpressions that are more likely to simplify. The resulting framework is capable of reducing expressions with hundreds of terms—a regular occurrence in quantum field theory calculations—to vastly simpler equivalent expressions. Starting from lengthy input expressions, our networks can generate the Parke-Taylor formula for five-point gluon scattering, as well as new compact expressions for five-point amplitudes involving scalars and gravitons.

Cheung, Clifford [California Institute of Technolo↗
DOE OSTI2024

Accuracy Enhancement of Nuclear Power Plant Simulators Utilizing High Accuracy Simulation Predictions

More recently, reactor core simulators for core designs associated with commercial nuclear power plants that utilize what is believed to be higher fidelity models have been developed. Features such as neutronics models that utilize transport equation solvers with fine spatial meshes and many energy-groups, thermal-hydraulic models that utilize sub-channel solvers with fine spatial mesh and capable of treating a wide range of fluid conditions, and fuel-coolant chemistry interaction models capable of treating CRUD deposition are to be found in these higher fidelity core simulators. These reactor core simulators require access to higher performance computers, characterized by many processors, cores and large memory. So associated with utilization of these simulators is access to high performance computers and ability to accommodate in one’s workflow longer execution times. By contrast, currently used core simulators by the nuclear industry can execute on engineering workstations and have execution times of seconds to minutes. The desirability for having short execution times is not only desired for support of time critical tasks but supports the mental process of decision making by engineers. The goal of the work reported upon here has the objective of retaining the fidelity of higher fidelity models while retaining the ability to utilize engineering workstations. Beyond the core simulator goal, additional goals of this work include incorporating the just described core simulator capability into a Nuclear Steam Supply System (NSSS) simulator, and to incorporate the resulting capability into an environment supportive of design and operational decision making associated with nuclear power stations. The model selected for the core neutronics model is the NESTLE code, for the core thermal-hydraulic model is the CTF code utilizing coarse mesh, and for the NSSS model is the RELAP5-3D code. WSC’s proprietary 3KEYMASTERTM platform is being used to provide software coupling, user interface, visualization, and reporting. The NESTLE core neutronics simulator was first integrated with the CTF core thermal-hydraulic simulator using CTF developed communication commands which are also used for CTF to communicate with RELAP5-3D under WSC’s proprietary 3KEYMASTERTM platform. To assure NESTLE prediction consistency with higher fidelity core neutronic simulators, buffer codes have been created to automatically generate from output files written by the VERA core simulator the NESTLE nodal neutronic parameter’ library, geometry, and pin-power reconstruction input files, thereby avoiding a number of challenges associated with utilizing lattice physics codes and providing consistency with VERA predictions. To treat absorber rod effects a multi-set library is utilized, where a set refers to a specific absorber rod fully inserted pattern. A coarse spatial mesh CTF model was developed with features added that support using CTF as envisioned in the engineering quality simulator. A hybrid meshing approach was implemented to allow for automated construction of models with mixed levels of refinement. Specifically, a core model could resolve some assemblies at a nodal level (4 subchannels per assembly) and others at a pin-resolution (one subchannel per coolant subchannel in the assembly). The intention is that this will allow for better resolution of limiting conditions such as DNBR and PCT, which are based on local rod and subchannel conditions. Further development was done of features that enhance the capabilities for the envisioned engineering quality simulator that has been developed, but now for RELAP-3D. The RELAP5-3D code development includes ability to model more than 999 components and the addition of the cross-channels turbulence mixing model and the void drift model that are implemented in CTF, aiming to achieve closer prediction agreement of the two codes for transient simulations, specifically, more accurate matches of the overall mass, momentum, and energy exchanges of both the liquid and gas phases between the neighboring core assemblies. Graphics were also developed for the Instructor Station for this project under WSC’s proprietary 3KEYMASTERTM platform to facilitate design and operational decision making.

42 ENGINEERING↗
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 OSTI2024

Development of High Temperature (>700°C) Molten Salt Pump Technology for Generation 3 Solar Power Tower Systems

Bearings are required for long-shafted pumps historically used in concentrating solar thermal power applications. For molten chloride salts, bearings for such service conditions are not commercially available, nor has a design been demonstrated to work. Therefore, a project was sponsored by the Department of Energy’s Solar Energy Technologies Office for the development and demonstration of a submerged bearing for use in chloride salt pumps. This project’s tasks covered the tribological testing of candidate materials and the design, fabrication, testing, and post-test analysis of full-scale salt-compatible bearings. This work expands upon previous work. The effects of potential particulate in the salt were investigated through tribological bench testing. Through 11 tests, the MgO particulate size and concentration in a molten chloride salt were varied, and the effects on friction, wear rate, and wear characteristics were recorded. Novel journal bearings for chloride salt service were designed and fabricated based on these results. The bearings were of a relevant scale (i.e., for a 1.5 in. pump shaft) to demonstrate the technology with respect to further scale-up. The bearings were made of Haynes 244 and Yttria Partially Stabilized Zirconia. A custom bearing test rig, salt tanks, and associated infrastructure (e.g., heaters, tanks, transfer lines, gas flow control) were designed, procured, and installed. A few issues were encountered in the system fabrication process, resulting in delay of the project schedule. The system was successfully fabricated and assembled. Heating, cover gas, and pump motor systems were integrated into the control logic. This progress of the bearing test system represents a significant step forward towards demonstrating this promising technology. Nevertheless, the project ended before testing of the full-scale bearings could be performed.

14 SOLAR ENERGY↗
DOE OSTI2026

Generative large language models for predictive maintenance planning

Maintenance planning and the generation of necessary components for tasks can prove time-consuming and complex. Automating the creation of recurring or similar tasks by leveraging previous planning packages and data, while uncovering insights to automate planning package generation, presents an opportunity to conserve valuable time and resources. This work aims to harness the textual and probabilistic capabilities of large language models (LLMs) to automate the generation of planning packages. Utilizing diverse data sources ranging from raw data to handwritten text, both singular and collaborative LLMs are trained and tested. Results demonstrate their capability to generate essential planning package components, effectively replicating the statistical patterns in the data. This demonstrates the use of these tools inside a digital asset for automated planning. This work outlines a methodology for constructing datasets, a training suite, and evaluation methods for LLM-based textual and conversational planning tools utilized in an asset digital twin. Results indicate that the fine-tuned models generate estimated planning information within the statistical ranges observed in real maintenance data. The models achieve high accuracy (>90%) in document question-answering and instruction generation tasks. Furthermore, the conversational retrieval-augmented generation (RAG) assistant system achieves 100% document retrieval accuracy, while conversational information capture exceeds 98% across the majority of work-package assistant modules.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Denoising diffusion probabilistic models for generative alloy design

Inverse material design is an extremely challenging optimization task made difficult by, in part, the highly nonlinear relationship linking performance with composition. Quantitative approaches have improved significantly owing to advances in high throughput experimentation and computational thermodynamics. However, existing physics-based tools are mostly forward models; input a chemistry and obtain a prediction. More recently the materials community has leveraged advances in the machine learning community to establish novel inverse design frameworks. Very recently denoising diffusion probabilistic models have been shown to be extremely powerful generators producing synthetic data of various modalities e.g. images, text, audio, tables, etc.. In this work a novel framework for alloy design and optimization is proposed leveraging these class of models. Five key generative tasks are demonstrated (1) unconditional generation (2) composition conditioned generation (3) property conditioned generation (4) multi-feedstock conditioned generation and (5) generative optimization. These methods were tested on three case studies: high entropy alloy design, superalloy binder jet additive manufacturing, and in-situ dual-feedstock wire-arc additive manufacturing. Results indicate that the established models are extremely flexible, expressive, and robust. The architecture’s flexibility and training procedure empower the model to learn complex intra-compositional and composition-property relationships. Furthermore, the probabilistic nature of these models makes them well suited for addressing solution non-uniqueness and tackling uncertainty quantification tasks. While the fidelity and quantity of the underlying training data is paramount, we envision that future alloy design frameworks will make extensive use of these kinds of machine learning models as “search” tools bolstering the utility of experimental and computational approaches.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Quantitative near-field water–air spray measurements at elevated pressures by neutron radiography imaging

Extensive experimental research on high-pressure spray has been conducted for decades to deepen our understanding and optimize its use in transportation, aviation, and propulsion applications; however, the near-field and in-nozzle flow characteristics are not fully understood. Dense near-field spray is among the most challenging diagnostic tasks since light is severely scattered and diffused by the liquid droplets and columns. In this work, the near-field spray and in-nozzle flow characteristics of an aeration nozzle at elevated pressures were characterized by neutron radiography imaging at the Oak Ridge National Laboratory High Flux Isotope Reactor. Neutron imaging benefits via strong penetration depths for some metals (i.e., aluminum, lead, and steel) and is sufficiently sensitive to detection of light elements, especially for hydrogen-based molecules, due to the large incoherent scattering cross section of neutrons. Both two-dimensional snapshots of the near-field spray and a three-dimensional tomographic scan of the nozzle geometry and in-nozzle water were obtained. This work provides new quantitative characterization of practical metal nozzle geometry for accurate boundary conditions, internal flow patterns inside the nozzle, and high-pressure spray flows. In conclusion, the findings may be used to improve performance and operating conditions of transportation vehicles and propulsion systems.

42 ENGINEERING↗
DOE OSTI2026

Generalist multimodal AI: A review of architectures, challenges and opportunities

Multimodal models are expected to be a critical component to future advances in artificial intelligence. Here, this field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e. one model across different data modalities and tasks. However, there is little research that systematically analyzes recent multimodal models (particularly the ones that work beyond text and vision) with respect to the underling architecture proposed. Therefore, this work provides a fresh perspective on generalist multimodal models (GMMs) via a novel architecture and training configuration specific taxonomy. This includes factors such as Unifiability, Modularity, and Adaptability that are pertinent and essential to the wide adoption and application of GMMs. The review further highlights key challenges and prospects for the field and guide the researchers into the new advancements.

Artificial intelligence (AI)↗
DOE OSTI2024

Progressive transfer learning for advancing machine learning-based reduced-order modeling

Abstract To maximize knowledge transfer and improve the data requirement for data-driven machine learning (ML) modeling, a progressive transfer learning for reduced-order modeling (p-ROM) framework is proposed. A key concept of p-ROM is to selectively transfer knowledge from previously trained ML models and effectively develop a new ML model(s) for unseen tasks by optimizing information gates in hidden layers. The p-ROM framework is designed to work with any type of data-driven ROMs. For demonstration purposes, we evaluate the p-ROM with specific Barlow Twins ROMs (p-BT-ROMs) to highlight how progress learning can apply to multiple topological and physical problems with an emphasis on a small training set regime. The proposed p-BT-ROM framework has been tested using multiple examples, including transport, flow, and solid mechanics, to illustrate the importance of progressive knowledge transfer and its impact on model accuracy with reduced training samples. In both similar and different topologies, p-BT-ROM achieves improved model accuracy with much less training data. For instance, p-BT-ROM with four-parent (i.e., pre-trained models) outperforms the no-parent counterpart trained on data nine times larger. The p-ROM framework is poised to significantly enhance the capabilities of ML-based ROM approaches for scientific and engineering applications by mitigating data scarcity through progressively transferring knowledge.

97 MATHEMATICS AND COMPUTING↗