SEARCH · Search NASA
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.
Framework for interacting with prompt-based LLMs (Large Language Models such as, but not limited to, ChatGPT) in order to develop domain specific taxonomies. The software itself is a series of prompts designed to extract hierarchical taxonomy categories from an LLM, as well as guidelines for how to fine-tune LLMs in order to provide better domain-specific taxonomic categories.
Language models are transforming materials-aware naturallanguage processing by enabling the extraction of dynamic, context-rich information from unstructured text, thus, moving beyond the limitations of traditional information-extraction methods. Moreover, small language models are on the rise because some of them can perform better than large language models (LLMs) when given domain-specific questionanswer tasks, especially about an application area that relies on a highly specialized vernacular, such as materials science. We therefore present a new class of MechBERT language models for understanding mechanical stress and strain in materials. These employ Bidirectional Encoder Representations for transformer (BERT) architectures. We showcase four MechBERT models, all of which were pretrained on a corpus of documents that are textually rich in chemicals and their stress–strain properties and were fine-tuned on question-answering tasks. We evaluated the level of performance of our models on domain-specific as well as general English-language question-answer tasks and also explored the influence of the size and type of BERT architectures on model performance. We find that our MechBERT models outperform BERT-based models of the same size and maintain relevancy better than much larger BERT-based models when tasked with domain-specific question-answering tasks within the stress–strain engineering sector. These small language models also enable much faster processing and require a much smaller fraction of data to pretrain them, affording them greater operational efficiency and energy sustainability than LLMs.
The mission planners for NASA's Europa Clipper deep-space mission use automated scheduling software to generate activity plans and command sequences for multiple instruments and subsystems before sending the sequences for execution on board. Both science and engineering planners must translate their intents into expressions of mission constraints, goals, and preferences that the scheduling engine understands. This paper describes the ongoing development of a dedicated domain-specific java-embedded language that can efficiently and accurately capture such concerns for the Europa Clipper mission, along with a user-interface companion for the language.
Program synthesis is the process of automatically deriving executable code from (non-executable) high-level specifications. It is more flexible and powerful than conventional code generation techniques that simply translate algorithmic specifications into lower-level code or only create code skeletons from structural specifications (such as UML class diagrams). Key to building a successful synthesis system is specializing to an appropriate application domain. The AUTOBAYES and AUTOFILTER systems, under development at NASA Ames, operate in the two domains of data analysis and state estimation, respectively. The central concept of both systems is the schema, a representation of reusable computational knowledge. This can take various forms, including high-level algorithm templates, code optimizations, datatype refinements, or architectural information. A schema also contains applicability conditions that are used to determine when it can be applied safely. These conditions can refer to the initial specification, to intermediate results, or to elements of the partially-instantiated code. Schema-based synthesis uses AI technology to recursively apply schemas to gradually refine a specification into executable code. This process proceeds in two main phases. A front-end gradually transforms the problem specification into a program represented in an abstract intermediate code. A backend then compiles this further down into a concrete target programming language of choice. A core engine applies schemas on the initial problem specification, then uses the output of those schemas as the input for other schemas, until the full implementation is generated. Since there might be different schemas that implement different solutions to the same problem this process can generate an entire solution tree. AUTOBAYES and AUTOFILTER have reached the level of maturity where they enable users to solve interesting application problems, e.g., the analysis of Hubble Space Telescope images. They are large (in total around 100kLoC Prolog), knowledge intensive systems that employ complex symbolic reasoning to generate a wide range of non-trivial programs for complex application do- mains. Their schemas can have complex interactions, which make it hard to change them in isolation or even understand what an existing schema actually does. Adding more capabilities by increasing the number of schemas will only worsen this situation, ultimately leading to the entropy death of the synthesis system. The root came of this problem is that the domain knowledge is scattered throughout the entire system and only represented implicitly in the schema implementations. In our current work, we are addressing this problem by making explicit the knowledge from Merent parts of the synthesis system. Here; we discuss how Gruber's definition of an ontology as an explicit specification of a conceptualization matches our efforts in identifying and explicating the domain-specific concepts. We outline the dual role ontologies play in schema-based synthesis and argue that they address different audiences and serve different purposes. Their first role is descriptive: they serve as explicit documentation, and help to understand the internal structure of the system. Their second role is prescriptive: they provide the formal basis against which the other parts of the system (e.g., schemas) can be checked. Their final role is referential: ontologies also provide semantically meaningful "hooks" which allow schemas and tools to access the internal state of the program derivation process (e.g., fragments of the generated code) in domain-specific rather than language-specific terms, and thus to modify it in a controlled fashion. For discussion purposes we use AUTOLINEAR, a small synthesis system we are currently experimenting with, which can generate code for solving a system of linear equations, Az = b.
As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the Aviation Safety Reporting System (ASRS). Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about weather and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.
As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the ASRS. Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about human factors, aircraft, and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.
Revolutionary new aviation services are currently in development, including small package delivery and short-range urban passenger transportation. These new services need a language to represent and deconflict trajectories, and a common language will simplify coordination between the new airspace domains as well as traditional airspace. A Trajectory Specification Language (TSL) was previously proposed for traditional air traffic, and it can also serve as a common language for the new aviation domains and services. The TSL specifies a reference trajectory in 4D space along with spatial tolerances that determine a bounding volume at any given time in flight. The tolerances are defined in terms of the route-oriented cross-track, along-track, and vertical axes, and they are allowed to vary with distance along the route. This bounding model can guarantee safe separation between flights as long as they are in conformance with their assigned trajectories. The advantages of this model over the previously proposed Operational Intent Volumes (OIVs) in terms of airspace usage efficiency are explained.
When modeling and analyzing the power grid and other large scale systems, researchers often express scenarios as optimization problems and feed them into advanced software solvers. In order to allow multiple solvers to communicate with each other and share data from different domains, the National Renewable Energy Laboratory (NREL) and associated Department of Energy (DOE) labs have developed a software framework called the Hierarchical Engine for Large-scale Infrastructure Co-Simulation (HELICS). HELICS allows cosimulation via a collection of client libraries for different languages that can be called from the appropriate optimization software. However, these client libraries do not provide a higher level of abstraction beyond reading and writing data off of the shared HELICS bus. In this paper, we describe a new software library called the SEAS Communication Engine that exposes a higher-level API for running cosimulation problems. The SEAS Engine provides a class-based abstraction on top of the Python HELICS client, in order to allow users to implement their domain-specific cosimulations without needing to interact with core HELICS primitives. This will make adoption of HELICS and cosimulation in general easier, by exposing a simpler API. In the second part of the paper, we validate our library on a collection of different simulation examples, including the canonical IEEE 13 Bus Feeder. Lastly, we demonstrate using the SEAS Engine to directly call domain-specific code written in the Julia programming language. Our hope is that this will serve as a template for easily calling software in different programming languages via the SEAS Engine, thereby avoiding code duplication and complexity.
We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer–solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent conditions, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems.
Querying a safety case to show how the various stakeholders' concerns about system safety are addressed has been put forth as one of the benefits of argument-based assurance (in a recent study by the Health Foundation, UK, which reviewed the use of safety cases in safety-critical industries). However, neither the literature nor current practice offer much guidance on querying mechanisms appropriate for, or available within, a safety case paradigm. This paper presents a preliminary approach that uses a formal basis for querying safety cases, specifically Goal Structuring Notation (GSN) argument structures. Our approach semantically enriches GSN arguments with domain-specific metadata that the query language leverages, along with its inherent structure, to produce views. We have implemented the approach in our toolset AdvoCATE, and illustrate it by application to a fragment of the safety argument for an Unmanned Aircraft System (UAS) being developed at NASA Ames. We also discuss the potential practical utility of our query mechanism within the context of the existing framework for UAS safety assurance.
This paper demonstrates a novel combination of program synthesis and verification to lift stencil computations from low-level Fortran code to a high-level summary expressed using a predicate language. The technique is sound and mostly automated, and leverages counter-example guided inductive synthesis (CEGIS) to find provably correct translations. Lifting existing code to a high-performance description language has a number of benefits, including maintainability and performance portability. For example, our experiments show that the lifted summaries can enable domain specific compilers to do a better job of parallelization as compared to an off-the-shelf compiler working on the original code, and can even support fully automatic migration to hardware accelerators such as GPUs. We have implemented verified lifting in a system called STNG and have evaluated it using microbenchmarks, mini-apps, and real-world applications. Here, we demonstrate the benefits of verified lifting by first automatically summarizing Fortran source code into a high-level predicate language, and subsequently translating the lifted summaries into Halide, with the translated code achieving median performance speedups of 4.1X and up to 24X for non-trivial stencils as compared to the original implementation.
We present a method for autogenerating a large domain-specific question-answering (QA) dataset from a thermoelectric materials database. We show that a small language model, BERT, once fine-tuned on this automatically generated dataset of 99,757 QA pairs about thermoelectric materials, affords better performance in the field of thermoelectric materials compared to a BERT model fine-tuned on the generic English-language QA data set, SQuAD-v2. We further show that mixing the two data sets (ours and SQuAD-v2), which have significantly different syntactic and semantic scopes, allows the BERT model to achieve even better performance. The best-performing BERT model fine-tuned on the mixed data set outperforms the models fine-tuned on the other two data sets by scoring an exact match of 67.93% and an F1 score of 72.29% when evaluated on our test data set. This has important implications as it demonstrates the ability to realize high-performing small language models, with modest computational resources, empowered by domain-specific materials data sets which can be generated according to our method.
In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.
In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.
Automated text summarization (ATS) is crucial for collecting specialized, domain-specific information. Zero-shot learning (ZSL) allows large language models (LLMs) to respond to prompts on information not included in their training, playing a vital role in this process. This study evaluates LLMs' effectiveness in generating accurate summaries under ZSL conditions and explores using retrieval augmented generation (RAG) and prompt engineering to enhance factual accuracy and understanding. We combined LLMs with summarization modeling, prompt engineering, and RAG, evaluating the summaries using the METEOR metric and keyword frequencies through word clouds. Results indicate that LLMs are generally well-suited for ATS tasks, demonstrating an ability to handle specialized information under ZSL conditions with RAG. However, web scraping limitations hinder a single generalized retrieval mechanism. While LLMs show promise for ATS under ZSL conditions with RAG, challenges like goal misgeneralization and web scraping limitations need addressing. Future research should focus on solutions to these issues.
A document presents a concept for run-time implementation of other concepts embodied in the Chapel programming language. (Now undergoing development, Chapel is intended to become a standard language for parallel computing that would surpass older such languages in both computational performance in the efficiency with which pre-existing code can be reused and new code written.) The aforementioned other concepts are those of distributions, domains, allocations, and access, as defined in a separate document called "A Semantic Framework for Domains and Distributions in Chapel" and linked to a language specification defined in another separate document called "Chapel Specification 0.3." The concept presented in the instant report is recognition that a data domain that was invented for Chapel offers a novel approach to distributing and processing data in a massively parallel environment. The concept is offered as a starting point for development of working descriptions of functions and data structures that would be necessary to implement interfaces to a compiler for transforming the aforementioned other concepts from their representations in Chapel source code to their run-time implementations.
Domain-overarching system models are crucial to investigate sector coupling concepts. Specifically, the coupling of building and electrical energy systems becomes crucial to integrate renewable energy sources such as photovoltaic power systems (PV). For such interdisciplinary simulation models, Modelica is a suitable language. However, most open-source Modelica libraries are either domain-specific or lack simple-to-parameterize PV models. We close this gap by developing a PV model for the IBPSA Modelica library. The model comprises two I-V-characteristic models and three mounting-dependent approaches to calculate the cell temperature. The I-V-characteristic models follow a single- and two-diodes approach. This study uses measurement data from a rooftop PV system in Berlin, Germany, for validation. The focus lies on comparing the implemented single- and two-diodes approach. Results prove that both models accurately calculate the modules’ DC power output and cell temperature. The two-diodes approach slightly outperforms the single-diode one at the expense of a higher parameterization effort.
The objective of automatic programming is to improve the overall environment for describing the program. This improved environment is realized by a reduction in the amount of detail that the programmer needs to know and is exposed to. Furthermore, this improved environment is achieved by a specification language that is more natural to the user's problem domain and to the user's way of thinking and looking at the problem. The goal of this research is to apply the concepts of automatic programming (AP) to modeling discrete event simulation system. Specific emphasis is on the design and development of simulation tools to assist the modeler define or construct a model of the system and to then automatically write the corresponding simulation code in the target simulation language, GPSS/PC. A related goal is to evaluate the feasibility of various languages for constructing automatic programming simulation tools.