SEARCH · Engineering Papers
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.
This review examines the roles of large language models (LLMs) and autonomous agents in chemistry, exploring advancements in molecule design, property prediction, and synthesis automation.
Scientific hypothesis generation represents a fundamental challenge in contemporary research due to exponentially expanding literature volumes and increasing disciplinary specialization. Large language models (LLMs) have emerged as transformative tools for automated scientific discovery, moving beyond traditional rule-based and literature-mining approaches. Four paradigmatic approaches define current LLM-driven hypothesis generation: direct prompting and fine-tuning methods, knowledge-enhanced frameworks integrating retrieval-augmented generation (RAG), multi-agent collaborative systems simulating research teams, and reasoning-focused approaches implementing cognitive architectures. Domain-specific applications demonstrate statistical equivalence to human expert performance in social psychology, experimental validation in biomedical research, and near-expert quality in astronomy. Evaluation methodologies encompass human expert assessment, LLM-as-judge frameworks, and comprehensive benchmarking systems. Technical challenges include hallucination management, knowledge integration limitations, and balancing novelty with feasibility. Future directions emphasize hybrid neural-symbolic architectures and sophisticated human-AI collaboration models for responsible scientific discovery acceleration.
Thermoelectric materials have the ability to convert waste heat into electricity, offering a valuable solution for energy harvesting. However, their widespread use is hindered by low conversion efficiency, the reliance on expensive rare earth elements, and the environmental and regulatory concerns associated with lead-based materials. A fast and cost-effective way to identify highly efficient thermoelectric materials is through data-driven methods. These approaches rely on robust and comprehensive datasets to train models. Although there are several databases on thermoelectric materials, there is still a need to collect and integrate experimental data from peer-reviewed research articles to capture diverse compositions and properties of materials. Here, in this work, we developed a comprehensive database of 7,123 thermoelectric compounds, containing key information such as chemical composition, structural detail, seebeck coefficient, electrical and thermal conductivity, power factor, and figure of merit (ZT). We used the GPTArticleExtractor workflow, powered by large language models (LLM), to extract and curate data automatically from the scientific literature published in Elsevier journals. This process enabled the creation of a structured database that addresses the challenges of manual data collection. The open access database could stimulate data-driven research and advance thermoelectric material analysis and discovery.
Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.
Distributed temperature sensing (DTS) using fiber optic sensors (FOS) offers a promising method for temperature measurements in advanced reactors, such as sodium fast reactors and molten salt cooled reactors. To support the calibration and validation of DTS measurements, Argonne National Laboratory developed the Validation, Optical Calibration, and Learning (VOCAL) software package. This report describes the integration of a local large language model (LLM) with a retrieval-augmented generation (RAG) system into the VOCAL interface to serve as an interactive user assistant. The LLM framework enhances the VOCAL platform’s accessibility to users by explaining interface components, clarifying inputs and outputs, and answering user queries dynamically in real-time. The accuracy of the LLM assistant performance was evaluated with 20 queries regarding the interface and its parameters using experimental data from the Thermal Hydraulic Experimental Test Article (THETA) facility. Results demonstrate that the LLM achieved a 95% accuracy rate, with a BERTScore of 0.8816 and SBERT value of 0.7417. Furthermore, validation of the RAG system within the LLM framework showed optimal accuracy with k-values between 1 and 2 using the k-refinement convergence test. The prompt perturbation analysis demonstrated good initial consistency for the RAG system, exhibiting the highest accuracy under punctuation variations and the greatest sensitivity under query reordering. Notably, the model’s errors were limited to data retrieval failures rather than factual hallucinations, reinforcing its baseline reliability. The integration of LLM provides a highly accurate, userfriendly enhancement to the VOCAL platform without disrupting its core computational capabilities for FOS calibration and validation.
The emergence of AI-driven Earth observation systems promises to broaden access to petabyte-scale geospatial data beyond domain specialists. However, translating this vision into operational scientific infrastructure requires addressing fundamental challenges in data virtualization, code transparency, and domain-specific reasoning. We present Hydrology Copilot, a cloud-native AI framework for natural-language-driven analysis of Earth observation data. To demonstrate operational capabilities at scale, we implement the system using NASA's North American Land Data Assimilation System version 3 (NLDAS-3), which provides surface meteorological forcing and land-surface model output across North and Central America at 1-km resolution, from which drought diagnostics are derived. The system integrates five core contributions: (1) scalable data virtualization using Kerchunk-based cloud optimized access, achieving a 1.5 to 4.6 times improvement in I/O latency across benchmark queries spanning regional single-day extractions (4.6 times speedup) to continental monthly aggregations (1.5 times speedup); (2) transparent code generation through Microsoft Azure AI Foundry agents that expose executable Python workflows for scientific verification; (3) persistent conversational memory enabling multi-turn analytical discourse across sessions; (4) intelligent query validation that enforces dataset boundaries and resolves ambiguous requests before execution; and (5) a multi-agent architecture coordinating query parsing, code generation, and visualization. We evaluate the system through drought-monitoring workflows, demonstrating reliable code generation, accurate results validated against reference computations and the operational U.S. Drought Monitor, and efficient operation across increasingly complex tasks. By bridging natural-language interfaces with rigorous hydrological analysis, Hydrology Copilot advances beyond proof-of-concept demonstrations to provide a deployable framework for operational Earth science applications.
The application of the category-partition method to the test design phase of hardware, software, or system test development is discussed. The method provides a formal framework for reducing the total number of possible test cases to a minimum logical subset for effective testing. An automatic tool and a formal language were developed to implement the method and produce the specification of test cases.
Precipitation may form in humid containers undergoing rapid depressurization. This precipitation may be liquid, i.e. fog, if the dewpoint is crossed above the freezing point of water, or direct snow crystallization if the dewpoint is crossed below the freezing point. Accurate modeling of this effect is potentially important for rapidly ascending vented containers in aircraft, spacecraft, and launch vehicles, as well as rapidly depressurizing vacuum chambers. A transient thermodynamics model of precipitation formation during the rapid depressurization of a container was developed in python. The model is written for a generic container and includes an optional water pool and water vapor source. Details of the model and results from several example cases spanning the full capabilities of the model, including a validation case, will be presented. Although the model is not novel, in contrast to prior works, this one was treated as a case study of the assistance of AI Large Language Models (LLMs) to create physical models. Impressions, performance, time, and cost of using AI for this task will be discussed.
Human thermal analysis and model development inform NASA’s space suit development, vehicle/habitat design, and survivability studies. Historically, human thermal models such as the 41-node metabolic man (METMAN) and the Wissler model have been standalone software tools developed with FORTRAN, a programming language known for its high performance in computationally intensive applications. Though efficient, these standalone programs pose challenges to coupled human-system analysis with detailed life support and thermal control subsystem models in other commercial software. This paper describes the conversion of the METMAN human thermal model from a standalone FORTRAN program to a model in Thermal Desktop (Ansys), a commonly used CAD-based simulation software for engineering that specializes in heat transfer, thermal radiation, and fluid flow analysis. This format was chosen to best facilitate model sharing and compatibility, enabling the direct integration of METMAN human thermal analysis with subsystem models across NASA programs and commercial partners.
NEML2 vectorizes constitutive-model evaluation for large-scale multiphysics simulation, using PyTorch as its tensor backend so that a batch of material-point updates runs on CPU or GPU through a single implementation. In the two prior reports in this series it was a C++-native library, deployed through TorchScript tracing and just-in-time (JIT) compilation; it has since been rewritten from the ground up into a Python-native library deployed through Ahead-of-Time Inductor (AOTInductor), a modern PyTorch graph-compilation backend. The rewrite is driven by a persistent tension, not a language preference: NEML2 composes constitutive models at runtime from a registry of small, independently-authored pieces, and that flexibility is difficult to reconcile with the compile-time knowledge an efficient GPU kernel needs. This report documents the rewrite and the investment that accompanied it: the AOTInductor export pipeline that turns a Python-authored model into a portable, Python-free compiled artifact loadable from pure C++; the eager and compiled runtimes and the new implicit solver layer built on them; a head-to-head benchmark of legacy JIT against AOTInductor; the physics-model catalog and its worked examples; the developer tooling; and the corresponding overhaul of MOOSE’s NEML2 integration that lets MOOSE consume it. A central objective is to examine whether modern PyTorch graph-compilation backends are effective for MOOSE GPU integration. The benchmark answers directly: AOTInductor outperforms legacy JIT on every GPU scenario measured, by 1.0–4.5×. Modern graph-compilation backends are effective for MOOSE GPU integration, and AOTInductor specifically – not compilation in the abstract – is why.
Whether it be monitoring the thermal subsystem of Space Station Freedom, or controlling the navigation of the autonomous rover on Mars, NASA missions in the 90's cannot enjoy an increased level of autonomy without the efficient use of expert systems. Merely increasing the computational speed of uniprocessors may not be able to guarantee that real time demands are met for large expert systems. Speed-up via parallel processing must be pursued alongside the optimization of sequential implementations. Prototypes of parallel expert systems have been built at universities and industrial labs in the U.S. and Japan. The state-of-the-art research in progress related to parallel execution of expert systems was surveyed. The survey is divided into three major sections: (1) multiprocessors for parallel expert systems; (2) parallel languages for symbolic computations; and (3) measurements of parallelism of expert system. Results to date indicate that the parallelism achieved for these systems is small. In order to obtain greater speed-ups, data parallelism and application parallelism must be exploited.
As motor control algorithms become increasingly complex, traditional microcontroller-based implementations are reaching computational limits that prevent the controller from operating at the required speed. This paper presents a novel workflow leveraging High-Level Synthesis (HLS) to migrate motor control algorithms from a microcontroller implementation to a Field-Programmable Gate Array (FPGA) implementation. The proposed approach utilizes the free Vitis HLS software to automatically convert Embedded Coder-generated C code from a Simulink model into Hardware Description Language (HDL) code suitable for FPGA deployment.
As motor control algorithms become increasingly complex, traditional microcontroller-based implementations are reaching computational limits that prevent the controller from operating at the required speed. This paper presents a novel workflow leveraging High-Level Synthesis (HLS) to migrate motor control algorithms from a microcontroller implementation to a Field-Programmable Gate Array (FPGA) implementation. The proposed approach utilizes the free Vitis HLS software to automatically convert Embedded Coder-generated C code from a Simulink model into Hardware Description Language (HDL) code suitable for FPGA deployment.
Team functioning is integral to success in future long term space exploration missions. Proactively detecting declines in team functioning can mitigate conflict and ensure mission success. This project developed a speech-based artificial intelligence (AI) system that unobtrusively predicts degradation in team functioning, including performance and cohesion, in the Human Exploration Research Analog (HERA) Campaigns 4 and 5. The AI system conducted automated analysis of the prosodic (tone of voice) and linguistic (language content) components of speech, modeling interpersonal dynamics at both the turn-taking and day-wide levels. We investigated team functioning via observing structured interactions (i.e., multi-mission space exploration vehicle-extra vehicular activity [MMSEV-EVA], team interaction battery [TIB]) and unstructured interactions before the MMSEV-EVA task. We developed machine learning models to predict team functioning (objective task accuracy, self reported team efficacy and self reported team cohesion) by analyzing OpenSmile acoustic features, linguistic descriptors extracted via the linguistic inquiry and word count (LIWC) dictionary, and semantic embeddings. In the TIB, static models using logistic regression and random forests were not able to predict task accuracy, but predicted team efficacy and cohesion during both the decision making and relational tasks to a moderate level (60-70%). Majority voting on the individual turns to predict day long team efficacy further increased accuracies (70-80%). Finally, long short-term memory (LSTM) models showed the best performance across all variables (80-91%), including task performance. In the MMSEV-EVA, static models achieved an accuracy of 60% with majority voting, which increased to 80% through the incorporation of mission day as a variable, accounting for the learning effect. A key finding across both tasks was the "team-dependent" nature of these interactions; models achieved much higher accuracy when trained on prior days of the same team's data rather than attempting to generalize across entirely different teams, with even 1-2 days of prior data per team achieving 5-15% improvement over team-independent models. In addition, the incorporation of pre-task data from the same team also improves model performance, e.g., incorporating data from the decision-making task of the TIB, which preceded the relational task, improved the prediction of team efficacy and cohesion during the latter. We compared model performance when trained on machine-generated data compared to data that had been further corrected by human annotators. Overall, models trained on human-corrected data exhibited a modest improvement in performance, particularly when acoustic features were used. We found no significant correlation between word error rate (WER) and model accuracy (r(55) = -0.08, p = 0.51), but model’s accuracy was significantly higher for medium/high quality transcription (0.74 (SD = 0.48)) compared to the low-quality group (0.64 (SD = 0.36)) (t(63)=2.82, p = 0.006). Based on these, several design recommendation emerge, that could inform Standards at NASA. Models predicting team functioning should incorporate at least one to two days of historical interaction data, include brief pre-task discussions, and explicitly model temporal learning effects, especially for longer operational tasks. Minimum quality standards for automated speech-processing pipelines are needed, given the performance gains observed with manually corrected acoustic data. Finally, systems should leverage both acoustic features and language embeddings in complementary ways, with modality choices and fusion strategies tailored to mission context, task demands, and data quality requirements.
Abstract Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.
This work presents a Tom’s Obvious Minimal Language (TOML)-based representation of input for the US Nuclear Regulatory Commission’s TRAC/RELAP Advanced Computational Engine (TRACE) thermal hydraulics code. Implemented using the Workbench Analysis Sequence Processor (WASP), the approach maps traditional TRACE input structures to a hierarchical format composed of named parameters, typed values, and native data collections. The resulting representation preserves TRACE’s existing modeling capabilities while providing a modern, structured interface for model development and management. WASP further extends TOML through a file import directive that supports modular model composition and reusable input organization. In addition, WASP provides extended array data entry convenience with various data repeat and interpolation capabilities. Examples of the new TOML syntax are provided for major TRACE input categories, including hydraulic components, heat structures, control systems, and trip logic. The TOML representation establishes a foundation for improved validation, tooling, automation, and model maintainability while remaining compatible with existing TRACE workflows. To facilitate migration to the TOML-based input format, the TRACE executable now supports conversion of native TRACE input into an intermediate JSON representation. A Python utility subsequently transforms the JSON data into an equivalent TOML model. Lastly, the TRACE executable now supports execution using TOML-formatted input.
Digital engineering (DE) and integrated computational materials engineering (ICME) are widely recognized as critical enablers of faster, more affordable, and more reliable aerospace systems. However, many organizations have struggled to realize the promised return on investment (ROI) from digital initiatives. A primary reason is the absence of a shared, decision-focused framework that distinguishes simple digitization of existing workflows from true digital transformation that fundamentally changes how engineering decisions are made. This paper introduces an ICME capability maturity framework that fills this gap. The framework defines six cumulative ICME capability maturity levels (CMLs), explicitly tied to decision authority, engineering integration, optimization, and uncertainty management across material, process, structure, and performance scales. It is designed to complement established readiness metrics such as technology readiness levels (TRLs), manufacturing readiness levels (MRLs), and integration readiness levels (IRLs), by addressing a missing dimension: the conditions required for model-informed decision authority across scales. A unifying figure and capability table illustrate the six-level ICME Capability Maturity Framework, showing how organizations progress from digitization—with limited or negative ROI—to true digital transformation, where ICME-enabled workflows deliver measurable improvements in decision quality, cycle time, risk reduction, and reuse. The framework is intended for both technical practitioners and executive leadership, providing a common language to assess current state, guide roadmaps, align software ecosystem investments, and set realistic expectations for digital transformation outcomes. A regulatory-relevant statement clarifying the relationship between ICME capability and existing certification frameworks is provided.