Search NASASearch

SEARCH · Search NASA

Results for “Retrieval augmented generation”

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 55 records · Page 3

AstraAI v1

AstraAI is an open-source, structure-aware AI coding agent designed for large scientific and DOE-HPC codebases such as AMReX-based applications. Unlike general-purpose coding assistants, AstraAI combines retrieval-augmented generation (RAG) with compiler-level Abstract Syntax Tree (AST) analysis to perform precise, scope-constrained code modifications. It identifies exact function spans, enforces locality of edits, and maintains cross-file invariants, enabling deterministic and build-safe transformations in complex C++/GPU environments. AstraAI is intended for developers working on large, evolving HPC frameworks where correctness, reproducibility, and structural integrity are critical. Typical use cases include modifying physics kernels, updating GPU device lambdas, and performing multi-file refactors without breaking compilation or runtime semantics. Compared to conventional LLM-based coding agents - even those with repository access - AstraAI provides structural guarantees rather than free-form text patches. It minimizes unintended diffs, prevents scope drift, preserves formatting and build stability, and reduces structural hallucinations. By integrating compiler tooling directly into the generation loop, AstraAI transforms AI-assisted coding from probabilistic text editing into deterministic, structure-preserving program transformation suitable for mission-critical scientific software.

Natarajan, Mahesh [Lawrence Berkeley National Labo

eLog analysis for accelerators: status and future outlook

This work demonstrates electronic logbook (eLog) systems leveraging modern AI-driven information retrieval capabilities at the accelerator facilities of Fermilab, Jefferson Lab, Lawrence Berkeley National Laboratory (LBNL), SLAC National Accelerator Laboratory. We evaluate contemporary tools and methodologies for information retrieval with Retrieval Augmented Generation (RAGs), focusing on operational insights and integration with existing accelerator control systems. The study addresses challenges and proposes solutions for state-of-the-art eLog analysis through practical implementations, demonstrating applications and limitations. We present a framework for enhancing accelerator facility operations through improved information accessibility and knowledge management, which could potentially lead to more efficient operations.

Accelerator Physics

eLog Analysis for Accelerators: Status and Future Outlook

This work demonstrates electronic logbook (eLog) systems leveraging modern AI-driven information retrieval capabilities at the accelerator facilities of Fermilab, Jefferson Lab, Lawrence Berkeley National Laboratory (LBNL), SLAC National Accelerator Laboratory. We evaluate contemporary tools and methodologies for information retrieval with Retrieval Augmented Generation (RAGs), focusing on operational insights and integration with existing accelerator control systems. The study addresses challenges and proposes solutions for state-of-the-art eLog analysis through practical implementations, demonstrating applications and limitations. We present a framework for enhancing accelerator facility operations through improved information accessibility and knowledge management, which could potentially lead to more efficient operations.

Hellert, Thorsten [LBNL, ALS]

ESAC v1: Enhanced AI-Powered Chatbot for EQ-SANS Experiment Automation Improvements and Updates

ESAC (EQ-SANS Assisting Chatbot) is an advanced AI-powered application designed to streamline the workflow of neutron scattering experiments at the Spallation Neutron Source (SNS). This report documents the significant advancements in ESAC v1, which include the integration of a combined In-Context Learning (ICL) + Retrieval-Augmented Generation (RAG) capability, a robust integrated development environment, and standalone executable distribution. These enhancements address the limitations of the original version, making ESAC v1 a transformative tool for researchers. The report also discusses the technical challenges encountered during development and their resolution, highlighting the impact of these improvements on the neutron scattering research community.

36 MATERIALS SCIENCE

Augmenting LLM-Based Agents for Improved Performance in Pentesting and Commissioning Operational Technology in Critical Infrastructure

Artificial intelligence (AI), and more specifically large language models (LLMs) have the potential for use in penetration testing (“pentesting”) against devices, networks, and computer systems in information technology (IT). We explore the possibility of extending pentesting from IT systems to operational technology (OT) systems, which are more obscure than IT systems in their protocols and design. A challenge therefore exists when applying pretrained LLMs to OT systems as corpora are likely to underrepresent OT systems in comparison to other more prevalent systems. We evaluate augmentations of LLMs with various methods, especially retrieval augmented generation (RAG), to improve performance of the LLMs in the OT domain. In addition to pentesting, some of the testing of these OT devices may include commissioning to ensure that the newly installed devices work correctly. Our framework may also be applied in such cases.

97 MATHEMATICS AND COMPUTING

eLog analysis for accelerators: status and future outlook

This work demonstrates electronic logbook (eLog) systems leveraging modern AI-driven information retrieval capabilities at the accelerator facilities of Fermilab, Jefferson Lab, Lawrence Berkeley National Laboratory (LBNL), SLAC National Accelerator Laboratory. We evaluate contemporary tools and methodologies for information retrieval with Retrieval Augmented Generation (RAGs), focusing on operational insights and integration with existing accelerator control systems. The study addresses challenges and proposes solutions for state-of-the-art eLog analysis through practical implementations, demonstrating applications and limitations. We present a framework for enhancing accelerator facility operations through improved information accessibility and knowledge management, which could potentially lead to more efficient operations.

Sulc, A. [LBL, Berkeley]

Lessons Learned from AskGDR: Usage and Impact Analysis of the Geothermal Data Repository's AI Research Assistant: Preprint

In October of 2024, the Department of Energy's (DOE) Geothermal Data Repository (GDR) team officially launched AskGDR, an AI research assistant resulting from the integration of a Large Language Model (LLM) with the metadata and supporting documents associated with GDR datasets. AskGDR allows GDR users to ask deeper questions about the origin of datasets, the methods used to collect them, and the findings they help support. Using Retrieval Augmented Generation (RAG), AskGDR can be used to summarize findings spread across dozens of papers and technical reports or to extract relevant information describing a single data field. However, generative AI is experimental. The National Renewable Energy Laboratory (NREL) has been collecting metrics on AskGDR and documenting lessons learned during its deployment. This paper will outline the efficacy and impact of AskGDR through analysis of its use, operating costs, number and types of questions asked, and the quality of answers provided.

15 GEOTHERMAL ENERGY

Multi-agent AI collaboration for digital twin development and assessment

Developing a digital twin (DT) model involves different steps that encompass formulating requirements, model development, implementation, and assessment with respect to real applications. Human expertise is required to coordinate and implement different steps in the DT development and assessment process. However, certain parts of this process can be automated using artificial intelligence (AI) agents for efficient workflow development. In this work, we test and analyze a multiagent AI collaboration with humans in the loop to automate different elements of the DT development and assessment process. To implement the workflow for multiagent AI DT development and assessment, we use Autogen, a multiagent framework developed by Microsoft. Autogen offers a modular and flexible framework for configuring and designing task-specific multiagent workflows. In this framework, large language models (LLMs) form the core intelligence of the AI agents where the quality and performance of the automated element is governed by the inherent capabilities and knowledge base of the LLM. We use retrieval augmented generation to supplement the LLM with relevant domain-specific information for DT requirement formulation. We illustrate this multiagent workflow using a case study on a thermal energy storage system, focusing on how AI agents can collaborate with humans to expedite and optimize different elements of DT development and assessment process.

22 - GENERAL STUDIES OF NUCLEAR REACTORS

Use of AI for Interpreting Technical Specifications for Power Uprates in Nuclear Power Plants

Powerpoint presentation. Background information provided on power plant uprates. Discussion of the current and proposed approaches to power plant uprates. Explanation of what data is used to draft a LAR. Methods such as retrieval augmented generation (RAG) and fine-tuning are discussed. Use case analysis is performed. Different failure types are examined. Conclusions are drawn from the analysis. Future work is proposed.

97 - MATHEMATICS AND COMPUTING

Digitizing and Enhancing Accessibility of the Fusion Safety Archives

This project focuses on the digitization and public accessibility to the Fusion Safety Archives at the Idaho National Laboratory. The first phase involves a thorough review of each document in the physical archives to determine its online availability. For documents that are available online, PDF copies and unique identifiers are collected for database integration. Documents not available online are delivered to Red Inc. for digitization. Additionally, defunct storage devices such as diskettes are sent to INL’s archival department for data retrieval where possible. The second phase of the project involves the creation of a comprehensive database to house the digital copies of the archives. The database will facilitate easy access and management of the digitized documents. Following the database creation, we plan to train a Retrieval-Augmented Generation (RAG) based AI on publicly available documents. The trained AI will be integrated into a front-facing application, allowing the public to easily access information from the Fusion Safety Archives. This project aims to preserve valuable historical data, improve accessibility, and promote transparency in fusion safety research.

70 - PLASMA PHYSICS AND FUSION TECHNOLOGY

Enhancing building resilience in cold climates: Integrating heat pump technologies with renewable energy

As electrification advances and Cold Climate Heat Pump technology progresses, ensuring grid stability becomes increasingly critical for effective heating in cold climates. However, natural disasters, especially during winter, pose significant threats to grid stability, impacting the reliability of air-source heat pumps. Despite these challenges, the integration of renewable energy sources and storage solutions in heating systems has not been extensively studied within the context of resilience. Here, this paper delves into the literature on renewable-powered heat pumps to assess their potential in enhancing building resilience in U.S. cold climate zones, which are particularly susceptible to extreme weather and grid disruptions. By leveraging renewable sources—solar, geothermal, and water—in conjunction with heat pump technology and supported by thermal or battery storage, this approach aims to provide a dependable solution for maintaining indoor heating during grid failures. Our analysis begins with a review of various renewable energy sources suitable for heat pumps, followed by an exploration of their application in cold climate regions across the U.S., and discussions on potential integration strategies with heat pump systems. This study highlights the advantages and suitability of solar irradiance and geothermal resources, emphasizing the importance of tailored, site-specific assessments to maximize energy efficiency and resilience. Additionally, it outlines the economic and environmental considerations necessary for implementing such systems and identifies potential challenges and areas for future research to facilitate the broader integration of renewable energy in heating solutions for enhanced resilience.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI

Large language models for transportation research: Methodologies, state of the art, and future opportunities

The rapid rise of large language models (LLMs) is transforming transportation research, with significant advancements emerging between 2023 and 2025, a period marked by the inception and swift growth of adopting and adapting LLMs for various transportation applications. Despite these significant advancements, however, a systematic review and synthesis of the existing literature remains lacking. This paper aims to fill this gap by providing a comprehensive review of the methodologies and applications of LLMs in transportation. We explore key applications, including autonomous driving, travel behavior prediction, and general transportation-related queries, alongside LLM methodologies such as zero- or few-shot learning, prompt engineering, and fine-tuning. From the review, critical research gaps are identified. From the methodological perspective, many of the research limitations can be addressed by integrating LLMs with existing tools and refining LLM architectures. From the application perspective, research opportunities for LLMs to address various transportation challenges are also explored. By synthesizing these findings, this review not only presents the state-of-the-art LLM adoption and adaptation in transportation, but also proposes future research directions as well as insights and recommendations for policymakers and practitioners, paving the way for greater LLM-driven research innovations in transportation in the future.

42 ENGINEERING

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

Agentic Retrieval-Augmented Code Synthesis with Iterative RefinementIn supercomputing, efficient and optimized code generation is essential to leverage high-performance systems effectively. We have developed Agentic Retrieval-Augmented Code Synthesis (ARCS), an advanced framework for accurate, robust, and efficient code generation, completion, and translation. ARCS integrates Retrieval-Augmented Generation (RAG) with Chain-of-Thought (CoT) reasoning to systematically break down and iteratively refine complex programming tasks. An agent-based RAG mechanism retrieves relevant code snippets, while real-time execution feedback drives the synthesis of candidate solutions. This process is formalized as a state-action search tree optimization, balancing code correctness with editing efficiency. Evaluations on the Geeks4Geeks and HumanEval benchmarks demonstrate that ARCS significantly outperforms traditional prompting methods in translation and generation quality. By enabling scalable and precise code synthesis, ARCS offers transformative potential for automating and optimizing code development in supercomputing applications, enhancing computational resource utilization

Bhattarai, Manish [Los Alamos National Labs]

Opportunities for retrieval and tool augmented large language models in scientific facilities

Upgrades to advanced scientific user facilities such as next-generation x-ray light sources, nanoscience centers, and neutron facilities are revolutionizing our understanding of materials across the spectrum of the physical sciences, from life sciences to microelectronics. However, these facility and instrument upgrades come with a significant increase in complexity. Driven by more exacting scientific needs, instruments and experiments become more intricate each year. This increased operational complexity makes it ever more challenging for domain scientists to design experiments that effectively leverage the capabilities of and operate on these advanced instruments. Large language models (LLMs) can perform complex information retrieval, assist in knowledge-intensive tasks across applications, and provide guidance on tool usage. Using x-ray light sources, leadership computing, and nanoscience centers as representative examples, we describe preliminary experiments with a Context-Aware Language Model for Science (CALMS) to assist scientists with instrument operations and complex experimentation. With the ability to retrieve relevant information from facility documentation, CALMS can answer simple questions on scientific capabilities and other operational procedures. With the ability to interface with software tools and experimental hardware, CALMS can conversationally operate scientific instruments. By making information more accessible and acting on user needs, LLMs could expand and diversify scientific facilities’ users and accelerate scientific output.

97 MATHEMATICS AND COMPUTING

Results from an Aeromagnetic Survey to Detect Steel-Cased Wells at a Marcellus Shale Well Site in Washington County, Pennsylvania

Pennsylvania has a 150-year history of oil and gas production—the longest of any state—and this enduring activity has resulted in the drilling of more than 300,000 recorded wells. However, unknown wells likely exist because innumerable wells were drilled during Pennsylvania’s intense early oil and gas history when incomplete records were kept of well locations. There is concern that early wells are likely to be ineffectively sealed because there were no laws that required plugging when the wells were abandoned. Today, many undocumented and unplugged wells are thought to be in areas of emerging shale gas and shale oil development where open wellbores can provide a pathway for undesired upward migration of fluids and gas from hydraulically fractured reservoirs. Due to this concern, Pennsylvania regulators have asked operators to locate orphaned and abandoned wells within a 1,000-ft buffer of proposed new wells. The objective of this report is to demonstrate that high-resolution aeromagnetic surveys, historic air photos, and Light Detection and Ranging (LiDAR) imagery can be rapid and effective methods to reconnoiter large, forested areas of moderate terrain for the presence of abandoned wells. These well-finding methods were evaluated at a proposed Marcellus Shale gas drilling site in Washington County, Pennsylvania, where the methods collectively located 18 confirmed wells: 15 wells were identified from aeromagnetic surveys, two wells were identified from inspection of historical air photos, and one well was identified by evaluation of state-wide LiDAR imagery. Only six wells were previously known, and their locations, as recorded in Pennsylvania’s statewide oil and gas wells database (PA/IRIS/WIS), were often too inaccurate for the wells to be found in the dense underbrush. Twelve wells identified in this study were abandoned, unmarked, and undocumented. Aeromagnetic surveys locate wells by detecting the unique magnetic signature of vertical, steel well casing, which is depicted on magnetic maps as a “bull’s eye” type anomaly that is centered directly over the well. However, when wells were drilled and found to be sub-economic, their casing was sometimes pulled and salvaged for reuse. Such wellbores provide no magnetic response and go undetected if all casing was removed. Oftentimes attempts to retrieve well casing were not 100% successful. For example, historical records for one well in the study area indicate that the well was completed in 1902 as a dry hole and that, to the extent possible, the casing was pulled for reuse. However, a section of 10-in. diameter steel casing was not recovered and remains at an unknown depth in the wellbore. This well was easily detected by the aeromagnetic survey although only deep casing remained in the well. To mitigate for the likelihood that wellbores exist where most or all casing has been removed, this study augmented aeromagnetic data with historic air photos and digital terrain models generated from LiDAR datasets—both databases are publicly available at no cost for areas within Pennsylvania. These complementary methods located three wells where the aeromagnetic anomaly, although present, was subtle and overlooked. Together, these methods determined accurate locations for six known wells within the study area and located 12 previously unknown wells. Although it is not certain that these methods successfully located all wells in the study area, the application of these methods does represent a significant improvement over relying on existing databases for well locations. For the Appendix to the report, see: https://www.netl.doe.gov/energy-analysis/details?id=b46c417a-7c9e-4d25-b810-e6248b0217f4</p>

04 OIL SHALES AND TAR SANDS

GIScience in the era of Artificial Intelligence: a research agenda towards Autonomous GIS

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we further elaborate on the concept of autonomous GIS and present a conceptual framework that defines its five autonomous goals, five levels of autonomy, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision-cores, autonomous modelling, and examining the societal and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIScience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance geospatial solutions to pressing global challenges. Meanwhile, we emphasize that as we design and deploy increasingly intelligent geospatial systems, we carry a responsibility to ensure they are developed in socially responsible ways, serve the public good, and support the continued value of human geographic insight in an AI-augmented future.

Autonomous GI

An ML-based terrestrial data fusion and augmentation framework to enable advanced understanding of the terrestrial carbon and water interactions

Soil moisture is essential to the terrestrial carbon and water cycles and land–atmosphere interactions. There are various types of soil moisture data, and each type has the distinct spatiotemporal strengths and limitations, depending on the diverse applications and retrieval methodologies of different data types (Li et al., in review; The PNNL-82151 FY23 Report). However, the limitations of different soil moisture data in terms of accuracy and spatiotemporal coverage hinder our ability to further understand the soil moisture dynamics across scales. To have a gap free soil moisture data product with a fine spatiotemporal coverage and vertical profiles, we train extreme gradient boosting (XGBoost) models by using (1) in-situ soil moisture measurements from the International Soil Moisture Network (ISMN), (2) soil moisture from the ECMWF reanalysis (ERA) at the 9 km and sub-daily spatiotemporal resolution, (3) the Daymet meteorological fields, and (4) data products that characterize surface conditions, including soil texture, organic content, topography, vegetation type, and rooting depth. We use the trained XGBoost models that have consistent performance across seven soil layers, i.e., 0–5 cm, 5–10 cm, 10–20 cm, 20–40 cm, 40–60 cm, 60–100 cm, and 100–200 cm, and the gridded model predictors to generate a soil moisture data at the 1 km and daily spatiotemporal resolution for the Continental United States (CONUS) from 2001–2020. This dataset can be broadly used for Earth system model benchmark, monitoring extreme weathers, making informed decisions regarding agriculture, water resource management, climate change mitigation, and ecosystem preservation.

58 GEOSCIENCES