Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “DRF”

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.

42 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

A Data & Reasoning Fabric to Enable Advanced Air Mobility

A Data & Reasoning Fabric (DRF) is envisioned to enable the full potential of advanced air mobility by providing all data and reasoning where they are needed. The DRF marketplace is based on an open foundational ecosystem of data and reasoning exchange between the many systems that must seamlessly interplay to manage the envisioned highly complex and dense airspace operations. DRF activities will identify, test and - as needed - research and develop critical core technologies, and collaboratively test these technologies, open standards and architectures, and the integrated framework with end-users so as to deliver reference designs and development environments that catalyze broad private and public sector buy-in and self-sustaining development of it and associated standards.

Urban Air Mobility↗
NASA NTRSDate not supplied

Classification of Notices to Airmen using Natural Language Processing

This paper establishes the feasibility of using Natural Language Processing (NLP) to classify NOTAMs or Notices to Airmen – a pilot messaging framework to gather real-time situational awareness. Present day air mobility operations heavily rely on NOTAMs. However, pilots often have difficulty interpreting NOTAMs due to the sheer volume of inapplicable messages and unclear abbreviations. Using NLP, the presented study analyzes the accuracy of classifying NOTAMs and, thereby, the efficiency of generating actionable interpretations in real time. To this effect, efficacies of four NLP neural network architectures were analyzed, including three Recurrent Neural Networks (RNNs) with GloVe, Word2Vec, and FastText word embeddings, and one trained Bi-Directional Encoder Representations from Transformers (BERT) model. The four neural networks were trained and evaluated on three open-source datasets of varying text lengths, vocabularies, and grammars, taken from e-commerce product descriptions, social media tweets, and unstructured descriptions for data and analytics services on open data marketplaces such as NASA’s Data and Reasoning Fabric (DRF) platform. This provided cross-analysis of each neural network architecture’s performance per text type. The best performing architecture, BERT, was then fine-tuned on a collection of open-source NOTAM data. Post-training, a real-time NOTAM classification service was implemented to draw inference on new NOTAMs using the trained model, which demonstrated close to 99% accuracy in classification. This modular classification service is envisioned to be integrated with a data and analytics delivery platform, such as the DRF, thus availing real-time contextualization of NOTAMs to air mobility clients, humans, and machines for enhanced decision making.

Aiden C. Szeto↗
NASA NTRSDate not supplied

Classification of Notices to Airmen using Natural Language Processing

This paper establishes the feasibility of using Natural Language Processing (NLP) to classify NOTAMs or Notices to Airmen – a pilot messaging framework to gather real-time situational awareness. Present day air mobility operations heavily rely on NOTAMs. However, pilots often have difficulty interpreting NOTAMs due to the sheer volume of inapplicable messages and unclear abbreviations. Using NLP, the presented study analyzes the accuracy of classifying NOTAMs and, thereby, the efficiency of generating actionable interpretations in real time. To this effect, efficacies of four NLP neural network architectures were analyzed, including three Recurrent Neural Networks (RNNs) with GloVe, Word2Vec, and FastText word embeddings, and one trained Bi-Directional Encoder Representations from Transformers (BERT) model. The four neural networks were trained and evaluated on three open-source datasets of varying text lengths, vocabularies, and grammars, taken from e-commerce product descriptions, social media tweets, and unstructured descriptions for data and analytics services on open data marketplaces such as NASA’s Data and Reasoning Fabric (DRF) platform. This provided cross-analysis of each neural network architecture’s performance per text type. The best performing architecture, BERT, was then fine-tuned on a collection of open-source NOTAM data. Post-training, a real-time NOTAM classification service was implemented to draw inference on new NOTAMs using the trained model, which demonstrated close to 99% accuracy in classification. This modular classification service is envisioned to be integrated with a data and analytics delivery platform, such as the DRF, thus availing real-time contextualization of NOTAMs to air mobility clients, humans, and machines for enhanced decision making.

Aiden Szeto↗
NASA NTRS2012

A Miniaturized Laser Heterodyne Radiometer for a Global Ground-Based Column Carbon Monitoring Network

We present progress in the development of a passive, miniaturized Laser Heterodyne Radiometer (mini-LHR) that will measure key greenhouse gases (C02, CH4, CO) in the atmospheric column as well as their respective altitude profiles, and O2 for a measure of atmospheric pressure. Laser heterodyne radiometry is a spectroscopic method that borrows from radio receiver technology. In this technique, a weak incoming signal containing information of interest is mixed with a stronger signal (local oscillator) at a nearby frequency. In this case, the weak signal is sunlight that has undergone absorption by a trace gas of interest and the local oscillator is a distributive feedback (DFB) laser that is tuned to a wavelength near the absorption feature of the trace gas. Mixing the sunlight with the laser light, in a fast photoreceiver, results in a beat signal in the RF. The amplitude of the beat signal tracks the concentration of the trace gas in the atmospheric column. The mini-LHR operates in tandem with AERONET, a global network of more than 450 aerosol sensing instruments. This partnership simplifies the instrument design and provides an established global network into which the mini-LHR can rapidly expand. This network offers coverage in key arctic regions (not covered by OCO-2) where accelerated warming due to the release of CO2 and CH4 from thawing tundra and permafrost is a concern as well as an uninterrupted data record that will both bridge gaps in data sets and offer validation for key flight missions such as OCO-2, OCO-3, and ASCENDS. Currently, the only ground global network that routinely measures multiple greenhouse gases in the atmospheric column is TCCON (Total Column Carbon Observing Network) with 18 operational sites worldwide and two in the US. Cost and size of TCCON installations will limit the potential for expansion, We offer a low-cost $30Klunit) solution to supplement these measurements with the added benefit of an established aerosol optical depth measurement. Aerosols induce a radiative effect that is an important modulator of regional carbon cycles. Changes in the diffuse radiative flux fraction (DRF) due to aerosol loading have the potential to alter the terrestrial carbon exchange.

Wilson, Emily L.↗