NASA-GPT: Retrieval-Augmented Generation on NASA Technical Reports
Explore the source record for details and available documents.
SLS↗
SEARCH · Engineering Papers
Results for “GPT”
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.
Comparison of ozone determinations by ultraviolet photometry and gas-phase titration
A comparison of ozone determinations based on ultraviolet absorption photometry and gas-phase titration (GPT) shows good agreement between the two methods. Together with other results, these findings indicate that three candidate reference methods for ozone, UV photometry, IR photometry, and GPT are in substantial agreement. However, the GPT method is not recommended for routine use by air pollution agencies for calibration of ozone monitors because of susceptibility to experimental error.
Demore, W. B.↗
Effect of 14 days of bed rest on urine metabolite excretion and plasma enzyme levels
After 1 week of ambulatory base-line measurement, a group of 8 men 19-26 years of age remained continuously recumbent for 14 days. Studies were continued for 1 week following the prolonged recumbency. Urine excretion rates for a number of constituents were determined 2 days before bed rest, on day 14 of bed rest, and day 6 after bed rest. Blood plasma samples were also obtained at these times, and analyzed for several enzymes. On day 14 of bed rest significant increases were observed in urine excretion of total osmotically-active substances, magnesium, calcium, phosphate, creatinine, hydroxyproline, and 17-OH corticosteroids. A decrease occurred in urinary glucose excretion. Plasma levels of alkaline phosphatase and LDH-3 were depressed, while plasma GPT was elevated. Many of these changes persisted on day 6 after bed rest, and are interpreted as concomitants of the disuse atrophy of the musculoskeletal system that characterizes prolonged bed rest and weightlessness.
Pace, N.↗
Evaluation of Atmospheric Loading and Improved Troposphere Modelling
Forward modeling of non-tidal atmospheric loading displacements at geodetic tracking stations have not routinely been included in Doppler Orbitography and Radiopositionning Integrated by Satellite (DORIS) or Satellite Laser Ranging (SLR) station analyses for either POD applications or reference frame determination. The displacements which are computed from 6-hourly models such as the ECMWF and can amount to 3-10 mm in the east, north and up components depending on the tracking station locations. We evaluate the application of atmospheric loading in a number ways using the NASA GSFC GEODYN software: First we assess the impact on SLR & DORIS-determined orbits such as Jason-2, where we evaluate the impact on the tracking data RMS of fit and how the total orbits are changed with the application of this correction. Preliminary results show an RMS radial change of 0.5 mm for Jason-2 over 54 cycles and a total change in the Z-centering of the orbit of 3 mm peak-to-peak over one year. We also evaluate the effects on other DORIS-satellites such as Cryosat-2, Envisat and the SPOT satellites. In the second step, we produce two SINEX time series based on data from available DORIS satellites and assess the differences in WRMS, scale and Helmert translation parameters. Troposphere refraction is obviously an important correction for radiometric data types such as DORIS. We evaluate recent improvements in DORIS processing at GSFC including the application of the Vienna Mapping Function (VMF1) grids with a-priori hydrostatic (VZHDs) and wet (VZWDs) zenith delays. We reduce the gridded VZHD at the stations height using pressure and temperature derived from GPT (strategy 1) and Saastamoinen. We discuss the validation of the VMF1 implementation and its application to the Jason-2 POD processing, compared to corrections using the Niell mapping function and the GMF. Using one year of data, we also assess the impact of the new troposphere corrections on the DORIS-only solutions, most importantly on the scale of the weekly solutions.
Zelensky, Nikita P.↗
Improved DORIS Reference Frame Solution from NASA GSFC
At GSFC, since 2008, we have been routinely processing data to DORIS and SLR satellites from 1993. A SINEX time series, based on processing of DORIS data from 1993 to 2008 (designated wd10) was included in the IDS combination for ITRF2008 (Le Bail et al., 2010; Valette et al., 2010). We have updated this series with the addition of new satellites Cryosat2 and Jason-2, and the new series (designated wd12) is routinely submitted to the IDS combination center for inclusion in the DORIS operational combination. In preparation for an eventual reprocessing of all the DORIS data for eventual inclusion in a new ITRF we are now updating our processing standards. As a first step, we update to the ITRF2008 reference frame as expressed through DPOD2008. In addition, we apply the GMF and GPT models for the troposphere, and we update the modeling for the change in pitch of SPOT-5 solar arrays after January 2008. Finally, we consider updated standards for static and time-variable gravity modeling. With this base series, we compute cumulative solution, expressed in ITRF2008, and examine the week-by-week station solution parameters, in particular scale, WRMS and Helmert transformation parameters. Finally we consider a joint solution with SLR, where the DORIS system is tied to SLR in two ways, first through the orbit computations using satellites tracked by both SLR and DORIS (e.g. TOPEX, Envisat, Jason-2, Cryosat2), and second through explicit ties at collocated sites. As one of the means of testing of these DORIS-only and SLR+DORIS solutions, we examine the vertical rates at sites in the vicinity of tide gauges.
Lemoine, Frank↗
2022 Spring Internship Exit Presentation
As efforts of the National Aeronautics and Space Administration (NASA) and the Federal Aviation Administration (FAA) continue to digitize the air traffic management (ATM) domain, there is countless times of need for downstream natural language processing (NLP) tasks such as named entity recognition, text summarization, classification, and more. Although there are a plethora of open-sourced pre-trained transformer models in the NLP field such as BERT, RoBERTa, XLNet, and GPT-3, these models are trained on general corpora and perform poorly on domain-specific terminology and phraseology seen in ATM documents such as Notice to Airmen (NOTAMs) and Letters of Agreement (LoA). Our proposed research objective will be to first gather a large corpus of air traffic management related documents, orders, notices, books, technical papers, conference papers, articles, and other miscellaneous sources of text data from the FAA, NASA, and accredited conference and publication societies. After gathering this data, many steps will have to be taken to collate and preprocess the data into a format understandable by our test transformer models. Thirdly, we will set up training pipelines to train the RoBERTa model on its unsupervised training task masked language modelling (MLM) using resources provided by the NASA Advanced Supercomputing (NAS) facilities. Finally, these fine-tuned transformer models will be evaluated on their performance on down-stream NLP tasks as mentioned above, to show whether they will be effective when working with ATM related data or not. Once complete, this model could be made open-sourced on the HuggingFace website, where the rest of the ATM community can access and utilize this tool.
NLP↗
Harnessing Large Language Models for Scientific Endeavors
The rapid proliferation of Large Language Models (LLMs) such as GPT, Bard, and Llama has revolutionized various sectors, including the scientific community. These models, with their potential to automate and augment tasks, are increasingly being recognized as both a valuable asset and a potential challenge in the realm of scientific research and data management. However, the current LLMs, primarily trained on general corpora, exhibit a limited understanding of scientific concepts and terminologies due to the lack of scientific corpus in their training data. Recognizing this gap, several groups are now advocating for the development of LLMs specifically tailored for scientific applications. A notable initiative in this direction is the Large Language Model effort initiated by NASA's CSDO. This endeavor aims to align LLM efforts across NASA’s Science Mission Directorate, develop a science-specific corpus and validation test set for model training, and create an encoder-only model for various downstream tasks. Moreover, the initiative also plans to develop a decoder-only model to explore the potential benefits and risks associated with a generative LLM for science. Lastly, the project aims to create a science evaluation suite, encompassing various categories of downstream scientific tasks, to serve as a benchmark for assessing the value of any LLM for future use. This presentation will provide an overview and current status of this ongoing initiative, highlighting its potential to reshape the use of LLMs in the scientific domain.
Rahul Ramachandran↗
Requirement Discovery Using Embedded Knowledge Graph With ChatGPT
The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.
systems engineering↗
Requirement Discovery Using Embedded Knowledge Graph with ChatGPT
The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) concept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze requirements within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.
systems engineering↗
Requirement Discovery Using Embedded Knowledge Graph With ChatGPT - Poster
The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.
systems engineering↗
Emulating Nature: The Future of Sustainable Design with BIDARA
BIDARA (Bio-inspired Design and Research Assistant) is a GPT-4o chatbot that was instructed to help scientists and engineers understand, learn from, and emulate the strategies used by living things to create sustainable designs and technologies. BIDARA can guide users through the Biomimicry Institute’s Design Process, a step-by-step method to propose biomimetic solutions to challenges. This process includes defining the problem, biologizing the challenge, discovering natural models, abstracting design strategies, and emulating nature's lessons.
Brandon Ruffridge↗