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.
The GES DIS is one of 12 NASA Earth science data centers. The GES DISC vision is to enable researchers and educators maximize knowledge of the Earth by engaging in understanding their goals, and by leading the advancement of remote sensing information services in response to satisfying their goals. This presentation will describe the GES DISC approach, successes, challenges, and best practices.
Since the mid 1980s, much of the marine science research effort in the United Kingdom has been focused into large scale collaborative projects involving public sector laboratories and university departments, termed Community Research Projects. Two of these, the Biogeochemical Ocean Flux Study (BOFS) and the North Sea Project incorporated large scale data collection to underpin multidisciplinary modeling efforts. The challenge of providing project data sets to support the science was met by a small team within the British Oceanographic Data Centre (BODC) operating as a topical data center. The role of the data center was to both work up the data from the ship's sensors and to combine these data with sample measurements into online databases. The working up of the data was achieved by a unique symbiosis between data center staff and project scientists. The project management, programming and data processing skills of the data center were combined with the oceanographic experience of the project communities to develop a system which has produced quality controlled, calibrated data sets from 49 research cruises in 3.5 years of operation. The data center resources required to achieve this were modest and far outweighed by the time liberated in the scientific community by the removal of the data processing burden. Two online project databases have been assembled containing a very high proportion of the data collected. As these are under the control of BODC their long term availability as part of the UK national data archive is assured. The success of the topical data center model for UK Community Research Project data management has been founded upon the strong working relationships forged between the data center and project scientists. These can only be established by frequent personal contact and hence the relatively small size of the UK has been a critical factor. However, projects covering a larger, even international scale could be successfully supported by a network of topical data centers managing online databases which are interconnected by object oriented distributed data management systems over wide area networks.
NASA over the years has developed many types of technologies and conducted various types of science resulting in numerous variations of operations, data and applications. For example, operations range from deep space projects managed by JPL, Saturn and Shuttle operations managed from JSC and KSC, ISS science operations managed from MSFC and numerous low earth orbit satellites managed from GSFC that are varied and intrinsically different but require many of the same types of services to fulfill their missions. Also, large data sets (databases) of Shuttle flight data, solar system projects and earth observing data exist which because of their varied and sometimes outdated technologies are not and have not been fully examined for additional information and knowledge. Many of the applications/systems supporting operational services e.g. voice, video, telemetry and commanding, are outdated and obsolete. The vast amounts of data are located in various formats, at various locations and range over many years. The ability to conduct unified space operations, access disparate data sets and to develop systems and services that can provide operational services does not currently exist in any useful form. In addition, adding new services to existing operations is generally expensive and with the current budget constraints not feasible on any broad level of implementation. To understand these services a discussion of each one follows. The Spaceflight User-based Services are those services required to conduct space flight operations. Grid Services are those Grid services that will be used to overcome, through middleware software, some or all the problems that currently exists. In addition, Network Services will be discussed briefly. Network Services are crucial to any type of remedy and are evolving adequately to support any technology currently in development.
The University of Maryland's Remote Sensing Systems Laboratory submitted to NASA/Goddard an interim progress report on the work being conducted within its Pilot Land Data System IPLDS project. The Remote Sensing Systems Laboratory addressed the following tasks: (1) identify data types and data sources needed to describe the selected test sites in collaboration with Goddard's Hydrological Sciences Branch; (2) define the procedures necessary to access/acquire this data; (3) conduct meetings with the PLDS Systems Engineering Group to identify functional specification priorities for PLDS development; (4) assemble documentation on historical remotely sensed imagery and transfer of such information to the PLDS Data Management Group; (5) collect data identified by Goodard's Hydrological Sciences Branch for data set inventory in PLD; (6) develop a Workstation-PLDS system interface over high speed lines, (7) develop and test through a Phase 1 demonstration of a micro workstation to access PLDS; and (8) establish interdepartmental agreement of development of computer link for electronic access of water resources data from USGS.
The most recent data strategy documents at both the federal and NASA levels stipulate that systems should strive for the data they manage to be Findable, Accessible, Interoperable, and Reusable (FAIR). The NASA Life Sciences Portal (NLSP) has already begun leading efforts in this area for HRP, initiating efforts to comply with the FAIR principles. The broad interpretation of the FAIR principles has led to a plethora of tools that use a splay of metrics specifically but variably developed to judge how compliant data and systems are with the principles. A recent review [3] identified and studied 1,180 metrics across 20 publicly available tools for checking FAIR compliance of data and systems. Because of their very recent development, many organizations and data systems managers and developers have not yet had adequate time or resources to understand these FAIR compliance tools and metrics, their variations in design, accuracy or ease of application to their specific data sets and systems. Thus, it would be best for larger organizations like NASA to approach formulating a strategy for governance of FAIR compliance that can be flexibly applied and is adaptable to an evolving awareness knowledge of FAIR compliance methods and tools. In September 2024, the NASA Science Mission Directorate(SMD) organized a workshop on NASA science data repositories, including the topics of implementing FAIR and governing FAIR compliance across SMD. The initial part of these FAIR discussions focused on developing consensus around required science metadata fields. This is challenging given the diverse nature of NASA’s scientific data portfolio, the variety of metadata models and vocabularies used, and variable level of resources available to curate these data. Later discussion focused on three possible approaches to governing FAIR compliance: distributed, in which various programs, projects or systems define their own methods for assessing FAIR compliance, reporting results up appropriate management lines; centralized, in which higher-level organization(s) specify compliance tools or methods for the various data systems; and multi-level, in which a group comprised of individuals with expertise from multiple levels with organizations is formed to provide guidance and/or specifications for governing FAIR compliance. We report on the recommendations this session yielded, and how these might be shaped specifically to help implement and govern the compliance with FAIR of Human Research Program data and systems.
The Department of Energy's (DOE) Geothermal Data Repository (GDR) is celebrating its tenth anniversary! Over the last decade it has grown from the simple idea of storing public data in a centralized location to a valuable tool at the center of the US geothermal scientific community and an integral part of the DOE Geothermal Technologies Office (DOE GTO) project management strategy. Researchers funded by the DOE GTO have contributed over 1,300 data submissions to the GDR. These data have been used to further advancements in geothermal science, economic analysis, exploration, research, development, and operational efficiency. The adoption of open data methodologies and a data management strategy that prioritizes universal open access and standardized, interoperable data have further increased the value of GDR data, making them available across a distributed network of data sharing partners and improving their utility to other industries and related fields, including material science and space exploration. Incorporating feedback from users has been critical to the GDR's success, allowing it to grow over the years to meet the evolving needs of the geothermal community. This paper will explore some of many changes that occurred throughout the GDRs tenure and the lessons learned along the way, as well as highlight some of the new features and recent improvements that been implemented to support innovation, reduce duplication of effort, and advance the geothermal industry as a whole.
NASA's GSFC Earth Sciences (GES) Data and Information and Data Services Center (DISC) manages the archive, distribution and data access for atmospheric composition data from AURA'S OMI, MLS, and hopefully one day, HIRDLS instruments, as well as heritage datasets from TOMS, UARS, MODIS, and AIRS. This data is currently archived in the GES Distributed Active Archive Center (DAAC). The GES DISC has begun the development of a community driven data management system that's sole purpose is to manage and provide value added services to NASA's Atmospheric Composition (AC) Data. This system, called the Atmospheric Composition Data and Information Services Center (ACDISC) will provide access all AC datasets from the above mentioned instruments, as well as AC datasets residing at remote archive sites (e.g, LaRC DAAC) The goals of the ACDISC are to: 1) Provide a data center for Atmospheric Scientists, guided by Atmospheric Scientists; 2) Be absolutely responsive to the data and data service needs of the Atmospheric Composition (AC) community; 3) Provide services (i.e., expertise) that will facilitate the effortless access to and usage of AC data; 4) Collaborate with AC scientists to facilitate the use of data from multiple sensors for long term atmospheric research. The ACDISC is an AC specific, user driven, multi-sensor, on-line, easy access archive and distribution system employing data analysis and visualization, data mining, and other user requested techniques that facilitate science data usage. The purpose of this presentation is to provide the evolution path that the GES DISC in order to better serve AC data, and also to receive continued community feedback and further foster collaboration with AC data users and providers.
A key recommendation from NASA’s 2022 Airborne and Field Data Workshop called for the development of a virtual Resource Center for all stakeholders across the data lifecycle of airborne and field Earth observations. The agency’s Earth Science Data and Information System (ESDIS) Project and Airborne Data Management Group (ADMG) have worked in concert to establish the newly launched NASA Airborne and Field Data Resource Center (AFDRC) to provide a single entry point for a wide assortment of information on and the effective, responsible stewardship of non-satellite observational data. The AFDRC compiles access to many existing resources, but does so in a newly organized way that integrates availability to increase efficiency and holistic understanding while simplifying users’ experience. Initially launched in fall of 2023, the AFDRC is a NASA Earthdata domain website that clarifies several previously disparate resources and provides newly updated information, including: Learning Resources: Educational resources to broaden understanding of the role airborne and field observations play in advancing understanding of our planet and NASA’s role in collecting and archiving these data. Support for data users to Find and Access Data: Advanced contextual browse/search capabilities that efficiently link researchers to data products suitable for their science objectives - this includes linking to NASA’s Catalog of Archived Suborbital Earth Science Investigations (CASEI). Working with Data: Tools specific to individual types of suborbital Earth Science data and their (inter-)disciplinary communities to provide access as well as guidance for their application. Stewardship Responsibilities: Resources for data producers with to lessen requirement burdens at the time of data transfer, and information for data stewards with consistent, authoritative guidance on best practices and agency- and/or community- specific archival procedures. This presentation will give an overview of the motivation for NASA’s AFDRC, approach for the design and content, iterative community-driven improvements, promote the use of the AFDRC, and solicit additional feedback from airborne and field data user communities.
A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge and support human space missions. Through artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in space biosciences and engineered astronaut health systems, to enable Earth-independence and mission operations autonomy. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated mission biomonitoring, and 8) a Precision Space Health system. AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the space biology field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics to phenotypic data using an ensemble model to infer causality of rodent liver health disruption, 2) usage of explainable ML to interrogate muscular underpinnings of muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interactions, and 5) a suite of benchmarked open science datasets enabling programmers to identify best algorithms to answer space biology questions.
A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.
A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.
Data analytics is the process of examining large amounts of data of a variety of types to uncover hidden patterns, unknown correlations and other useful information. Data analytics is a broad term that includes data analysis, as well as an understanding of the cognitive processes an analyst uses to understand problems and explore data in meaningful ways. Analytics also include data extraction, transformation, and reduction, utilizing specific tools, techniques, and methods. Turning to data science, definitions of data science sound very similar to those of data analytics (which leads to a lot of the confusion between the two). But the skills needed for both, co-analyzing large amounts of heterogeneous data, understanding and utilizing relevant tools and techniques, and subject matter expertise, although similar, serve different purposes. Data Analytics takes on a practitioners approach to applying expertise and skills to solve issues and gain subject knowledge. Data Science, is more theoretical (research in itself) in nature, providing strategic actionable insights and new innovative methodologies. Earth Science Data Analytics (ESDA) is the process of examining, preparing, reducing, and analyzing large amounts of spatial (multi-dimensional), temporal, or spectral data using a variety of data types to uncover patterns, correlations and other information, to better understand our Earth. The large variety of datasets (temporal spatial differences, data types, formats, etc.) invite the need for data analytics skills that understand the science domain, and data preparation, reduction, and analysis techniques, from a practitioners point of view. The application of these skills to ESDA is the focus of this presentation. The Earth Science Information Partners (ESIP) Federation Earth Science Data Analytics (ESDA) Cluster was created in recognition of the practical need to facilitate the co-analysis of large amounts of data and information for Earth science. Thus, from a to advance science point of view: On the continuum of ever evolving data management systems, we need to understand and develop ways that allow for the variety of data relationships to be examined, and information to be manipulated, such that knowledge can be enhanced, to facilitate science. Recognizing the importance and potential impacts of the unlimited ways to co-analyze heterogeneous datasets, now and especially in the future, one of the objectives of the ESDA cluster is to facilitate the preparation of individuals to understand and apply needed skills to Earth science data analytics. Pinpointing and communicating the needed skills and expertise is new, and not easy. Information technology is just beginning to provide the tools for advancing the analysis of heterogeneous datasets in a big way, thus, providing opportunity to discover unobvious scientific relationships, previously invisible to the science eye. And it is not easy It takes individuals, or teams of individuals, with just the right combination of skills to understand the data and develop the methods to glean knowledge out of data and information. In addition, whereas definitions of data science and big data are (more or less) available (summarized in Reference 5), Earth science data analytics is virtually ignored in the literature, (barring a few excellent sources).
Since 2019, NASA’s Airborne Data Management Group (ADMG) within the Interagency Implementation and Advanced Concepts Team (IMPACT) has worked to promote and ensure the discoverability and accessibility of the agency’s non-satellite Earth science observations. A primary component of this effort is the development of NASA’s Catalog of Archived Suborbital Earth Science Investigations (CASEI) and the vetting of key contextual details required to sustain this unique inventory of airborne and field metadata. CASEI provides information on the science objectives motivating data collection, key events/time periods in the observational record aligned with the science objectives, complementary simultaneous observations, programmatic details, and much more. The diverse set of data formats and disciplines served by CASEI have required the implementation of a common data model to organize suborbital observation metadata and efficiently connect appropriate campaigns, platforms, and instruments. The CASEI inventory provides a single entry point for users to search and browse NASA’s airborne and field data archives, regardless of which repository is responsible for their stewardship. This presentation will provide a summary of the motivations for and the development of the CASEI system. Particular attention will be granted to how CASEI facilitates discovery and reuse of these lesser-known NASA data, supporting the Open Science vision and enhancing the return on investments made to collect these unique and varied observations. An up-to-date summary of CASEI inventory content and initial metrics will be provided. Current and future avenues ADMG is pursuing to enhance both CASEI and specific components of suborbital data stewardship at various stages of the data life cycle will also be discussed.
The National Aeronautic and Space Administration (NASA) Commercial Smallsat Data Acquisition (CSDA) Program was established to identify, evaluate, and acquire data from commercial satellite companies that support and complement NASA’s Earth sciences missions and research goals. Since becoming a sustained program in 2020, CSDA has been developing a data system to provide scalable, efficient, continuous, and repeatable data management processes for all commercial data acquired by NASA. This includes providing access to commercial data to approved science investigators through NASA developed and vendor operated interfaces. As the commercial data user community and volume of data acquired by CSDA has grown, the team managing these data has adapted technologies and services to better address the data and information search, discovery, and access needs of the science user community. This presentation will provide an overview of CSDA Program data system activities including data availability, development of CSDA user interfaces, challenges in managing large-volume diverse datasets, and long-term data preservation activities to retain data for scientific reproducibility.
Ni–Ti–based shape memory alloys (SMAs) have found widespread use in the last 70 years, but improving their functional stability remains a key quest for more robust and advanced applications. Named for their ability to retain their processed shape as a result of a reversible martensitic transformation, SMAs are highly sensitive to compositional variations. Alloying with ternary and quaternary elements to fine-tune the lattice parameters and the thermal hysteresis of an SMA, therefore, becomes a challenge in materials exploration. Combinatorial materials science allows streamlining of the synthesis process and data management from multiple characterization techniques. In this study, a composition spread of Ni–Ti–Cu–V thin-film library was synthesized by magnetron co-sputtering on a thermally oxidized Si wafer. Composition-dependent phase transformation temperature and microstructure were investigated and determined using high-throughput wavelength dispersive spectroscopy, synchrotron X-ray diffraction, and temperature-dependent resistance measurements. Of the 177 compositions in the materials library, 32 were observed to have shape memory effect, of which five had zero or near-zero thermal hysteresis. These compositions provide flexibility in the operating temperature regimes that they can be used in. A phase map for the quaternary system and correlations of functional properties are discussed with respect to the local microstructure and composition of the thin-film library.
NASA's Scientific Data Purchase (SDP) project is currently a $70 million operation managed by the Earth Science Applications Directorate at Stennis Space Center. The SDP project was developed in 1997 to purchase scientific data from commercial sources for distribution to NASA Earth science researchers. Our current data holdings include 8TB of remote sensing imagery consisting of 18 products from 4 companies. Our anticipated data volume is 60 TB by 2004, and we will be receiving new data products from several additional companies. Our current system capacity is 24 TB, expandable to 89 TB. Operations include tasking of new data collections, archive ordering, shipment verification, data validation, distribution, metrics, finances, customer feedback, and technical support. The program has been included in the Stennis Space Center Commercial Remote Sensing ISO 9001 registration since its inception. Our operational system includes automatic quality control checks on data received (with MatLab analysis); internally developed, custom Web-based interfaces that tie into commercial-off-the-shelf software; and an integrated relational database that links and tracks all data through operations. We've distributed nearly 1500 datasets, and almost 18,000 data files have been downloaded from our public web site; on a 10-point scale, our customer satisfaction index is 8.32 at a 23% response level. More information about the SDP is available on our Web site.
The Department of Energy's (DOE) Geothermal Data Repository (GDR) is celebrating its tenth anniversary! Over the last decade it has grown from the simple idea of storing public data in a centralized location to a valuable tool at the center of the US geothermal scientific community and an integral part of the DOE Geothermal Technologies Office (DOE GTO) project management strategy. Researchers funded by the DOE GTO have contributed over 1,300 data submissions to the GDR. These data have been used to further advancements in geothermal science, economic analysis, exploration, research, development, and operational efficiency. The adoption of open data methodologies and a data management strategy that prioritizes universal open access and standardized, interoperable data have further increased the value of GDR data, making them available across a distributed network of data sharing partners and improving their utility to other industries and related fields, including material science and space exploration. Incorporating feedback from users has been critical to the GDRs success, allowing it to grow over the years to meet the evolving needs of the geothermal community. This paper will explore some of many changes that occurred throughout the GDRs tenure and the lessons learned along the way, as well as highlight some of the new features and recent improvements that been implemented to support innovation, reduce duplication of effort, and advance the geothermal industry as a whole.
The National Aeronautics and Space Administration (NASA) Air Mobility Pathfinders (AMP) project is developing and evaluating concepts of operations (ConOps) for safe, secure, and scalable Urban Air Mobility (UAM) operations. The AMP project’s Operational Concepts, Architecture, and Requirements Integration (OCARI) Team is using a Model Based System Engineering (MBSE) approach for integration, interoperability, and traceability of Advanced Air Mobility (AAM) ecosystems centered around urban air taxi services. The team’s goal is to define structures and behaviors needed for system feasibility, readiness, and interoperability, establish a UAM knowledge base, and trace and validate assumptions and requirements relevant to AAM. NASA Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers together across organizational boundaries. It does so through the management of an information database defined by mathematical, data science, and system engineering principles. Machine Learning (ML) algorithms play a key role in this concept by extracting meaningful knowledge from relational and graph databases, document repositories, and system artifacts, which the human user leverages to greatly improve the efficiency and effectiveness of their research. Recent advancements in the field of Large Language Models (LLMs), specifically models trained for tool use, such as Command-R , now allow for the reliable implementation of single-step and multi-step tool-centric systems. These techniques provide the LLM with a set of tools, in our case Python functions, that can be called on to answer a much wider range of questions compared to LLMs implemented using a traditional single-source or Retrieval Augmented Generation (RAG) approach. Through this method, the LLM can pull information from multiple data sources, such as relational or graph databases, document repositories, application programming interfaces (APIs), and SysML artifacts depending on the user’s question. The LLM can also output the information in a variety of different formats, using output generation tools, such as CSV, UML, or SysML artifacts. Additionally, tools can be assigned roles and can work together to provide answers to queries in an “agent” like approach, similar to that implemented by Microsoft’s AutoGen framework where different agents can converse with each other to accomplish tasks. Previously, our team developed a chatbot system with “agent like” functionality in the form of different “modes” the user could select from a user interface (UI), this architecture can be seen on the left in figure 1. Three different modes were implemented, the first mode allowed the LLM to utilize the structures and algorithms within a graph database to trace UAM requirements. The second mode gave the LLM access to a vector search capable of providing relevant information from thousands of document pages related to UAM ConOps and requirements. The third mode served as a general assistant where users could enter open-ended questions and custom prompts to utilize the LLM for different use-cases. This system improved the process surrounding generating and analyzing information related to UAM requirements, however, the implementation provided a clunky user experience. Users were required to know what mode to select within the UI in advance before entering their question to the selected tool. Moreover, the different tools were isolated from each other, they lacked bidirectional links that would allow for tools to collaborate to generate better responses. Our team is working on a new architecture, seen on the right in the below figure, with the goal to address many of the UX shortcomings of our original system while improving the accuracy and depth of responses from the LLM. This new system will automatically select the appropriate tool to use based off the user’s question. Each tool will be capable of calling on any of the other tools available to the LLM, resulting in a collaborative pipeline where tools can pass data between other tools until enough data is received to generate an answer to the user’s question. Using a locally deployed, open-source, LLM, the NASA OCARI team, in collaboration with Collins Aerospace, will implement a prototype application that will bridge knowledge across multiple sources to assist System Engineers (SEs) with requirements discovery and tracing, research question and use case identification, and assumption validation. Such a system will also allow SEs to more easily, and intuitively, explore the AAM ecosystem, ultimately improving the efficiency and effectiveness of the SE's research and decision-making processes surrounding ConOps development and validation. In this session, our team will provide a video demonstration of our new prototype architecture in action. We will also present an overview of our prototype system architecture and talk about its advantages over traditional LLM deployments along with how those advantages can provide additional value to the field of System Engineering.