Results for “Robust artificial intelligence” — Page 3

NASA NTRS1987

Discovery and problem solving: Triangulation as a weak heuristic

Recently the artificial intelligence community has turned its attention to the process of discovery and found that the history of science is a fertile source for what Darden has called compiled hindsight. Such hindsight generates weak heuristics for discovery that do not guarantee that discoveries will be made but do have proven worth in leading to discoveries. Triangulation is one such heuristic that is grounded in historical hindsight. This heuristic is explored within the general framework of the BACON, GLAUBER, STAHL, DALTON, and SUTTON programs. In triangulation different bases of information are compared in an effort to identify gaps between the bases. Thus, assuming that the bases of information are relevantly related, the gaps that are identified should be good locations for discovery and robust analysis.

Rochowiak, Daniel↗

NASA NTRS1990

Instrumentation and robotic image processing using top-down model control

A top-down image processing scheme is described. A three-dimensional model of a robotic working environment, with robot manipulators, workpieces, cameras, and on-the-scene visual enhancements is employed to control and direct the image processing, so that rapid, robust algorithms act in an efficient manner to continually update the model. Only the model parameters are communicated, so that savings in bandwidth are achieved. This image compression by modeling is especially important for control of space telerobotics. The background for this scheme lies in an hypothesis of human vision put forward by the senior author and colleagues almost 20 years ago - the Scanpath Theory. Evidence was obtained that repetitive sequences of saccadic eye movements, the scanpath, acted as the checking phase of visual pattern recognition. Further evidence was obtained that the scanpaths were apparently generated by a cognitive model and not directly by the visual image. This top-down theory of human vision was generalized in some sense to the frame in artificial intelligence. Another source of the concept arose from bioengineering instrumentation for measuring the pupil and eye movements with infrared video cameras and special-purpose hardware.

Stark, Lawrence↗

NASA NTRSDate not supplied

Earth Independent Medical Operations (EIMO) Datascope: Challenges and Potential Solutions

Data flows and storage/retrieval capacity are severely constrained during missions in space and challenges will become even greater during exploration class missions. There is a need for an artificial intelligence (AI)-based clinical decision support system (CDSS) to monitor and analyze data to provide real-time consultative support for crew medical officer (CMO) decision-making. EIMO is defined as the gradual transition of medical care and decision making from terrestrial to space-based assets, enabling support of astronaut health and performance and reducing overall mission risk. While a hallmark of this paradigm shift from low-earth orbit is that on-board care will increasingly become the responsibility of the astronauts for primary management and decision making, terrestrial assets will continue to be paramount in pre-mission screening and planning, as well as prevention, health maintenance and long-term care contingencies. New capabilities and systems that enable progressively more robust and resilient systems and crews will be necessary to reduce risk and increase probability of deep space exploration mission success. An aspiration for EIMO is to develop AI-enhanced solutions for analysis of crew health & performance data and to facilitate clinical decision support for autonomous medical operations. A “system of systems” approach is envisioned whereby EIMO will deploy AI-supported natural language processing and machine learning (ML) techniques to utilize embedded reference databases and real-time data streams [input vectors] from multiple data sources. Constituent input vectors may include environmental controls, countermeasures data, behavioral data, physiologic wearables, point-of-care laboratory tests, personalized medical records, inventory trade space risk assessments, COTS medical databases, and ground support inputs. An ideal AI capability would possess trained fusion algorithms to cross reference input vectors with medical ‘knowledge’ [cultivated database] to stratify relevant data streams for predictive and actionable capabilities. In addition, EIMO will feature mobility, in that it can be accessed and can push/pull data within and between multiple vehicles/habitats. Large amounts and variable sources of data can be leveraged to diagnose, inform treatment strategies, and potentially predict medical events and performance decrements. Inclusion of advanced training tools using extended reality will enable increasingly autonomous medical care to aid a CMO when ground support is unavailable or time-delayed beyond required action window, e.g., emergent medical situations. EIMO CDSS would require very large datasets to train pre-flight and significant amounts of data are needed to support ML via in-flight CDSS operations. An additional challenge will be to find sufficient data to train a model relevant to astronaut demographics. The rapid, accelerating evolution of this field creates a propitious solution space to leverage multi-modal AI through public-private partnership(s). The status of multi-modal AI systems today would preclude their use for long duration missions as they remain unreliable and are subject to “digital hallucinations” and other errors that could pose operational risk. A federated labs structure is being considered to test and optimize data flow from the multiple input vectors leading to field testing in suitable ground/flight analogs. Critical to the success of an EIMO CDSS will be integration and interoperability and success will be defined by a system that can serve as an in-flight medical consult for the CMO providing critical support during medical contingencies. Benefits to terrestrial medicine may be significant as an outflow of the EIMO medical system, particularly for remote areas and communities lacking significant infrastructure, personnel and resources.

J Lemery↗

NASA NTRSDate not supplied

Expanding SPoRT RGBs and Machine Learning Techniques to Enhance Air Quality Monitoring in Southern Asia

Air pollution poses significant environmental, public health, and societal concerns in the Hindu Kush Himalaya (HKH) region of south-central Asia, notably during the dry monsoon months (~November to May). Key contributors to poor air quality include dust from the Middle East and western India, persistent nocturnal fog/smog, and biomass burning. To address this issue, we established a robust air quality and chemistry observation and modeling product suite utilizing multi-spectral red-green-blue (RGB) composite satellite products from Korea’s GEO-KOMPSAT-2A satellite, the Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model for dust transport forecasts, and the Weather Research and Forecasting coupled with Chemistry (WRF-Chem) model to predict aerosols and chemical species concentrations. Our team employed similar RGB recipes transitioned by the NASA Short-term Prediction Research and Transition (SPoRT) Center for the GOES-R era products over the Western Hemisphere, with significant success in depicting dust and nocturnal fog / low clouds, and to a lesser extent smoke and fire hot spots. We will extend these capabilities for the HKH region by applying an artificial intelligence (AI) model that objectively identifies dust from multi-spectral satellite data over the Southwestern United States. The AI model will be calibrated for automated dust detection over HKH from GEO-KOMPSAT-2A satellite data, with a goal of developing a similar AI model for objectively identifying smoke as well. The ultimate goal of this effort is to enhance dust and smoke predictions in the region by establishing improved emission initializations in HYSPLIT and/or WRF-Chem through the automated AI detection of dust and smoke.

Jonathan L. Case↗

NASA NTRS2001

Implementation of a General Real-Time Visual Anomaly Detection System Via Soft Computing

The intelligent visual system detects anomalies or defects in real time under normal lighting operating conditions. The application is basically a learning machine that integrates fuzzy logic (FL), artificial neural network (ANN), and generic algorithm (GA) schemes to process the image, run the learning process, and finally detect the anomalies or defects. The system acquires the image, performs segmentation to separate the object being tested from the background, preprocesses the image using fuzzy reasoning, performs the final segmentation using fuzzy reasoning techniques to retrieve regions with potential anomalies or defects, and finally retrieves them using a learning model built via ANN and GA techniques. FL provides a powerful framework for knowledge representation and overcomes uncertainty and vagueness typically found in image analysis. ANN provides learning capabilities, and GA leads to robust learning results. An application prototype currently runs on a regular PC under Windows NT, and preliminary work has been performed to build an embedded version with multiple image processors. The application prototype is being tested at the Kennedy Space Center (KSC), Florida, to visually detect anomalies along slide basket cables utilized by the astronauts to evacuate the NASA Shuttle launch pad in an emergency. The potential applications of this anomaly detection system in an open environment are quite wide. Another current, potentially viable application at NASA is in detecting anomalies of the NASA Space Shuttle Orbiter's radiator panels.

Dominguez, Jesus A.↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

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.

Air Traffic Management↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

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.

Air Traffic Management↗

NASA NTRSDate not supplied

NASA R&M Efficiency through Findable, Accessible, Interoperable, and Reusable (FAIR) Digital Assets

At the intersection of mission, technology, and place is NASA’s need to modernize for a digital-forward future. Digitalization, the process of moving toward digital business, is occurring everywhere and remains an ongoing process across the federal government.”[1] Whereas, Digital Transformation is “employing digitization/digital technologies (e.g., Artificial Intelligence (AI), mobile, cloud, data) to change a process, product, or capability so dramatically (e.g., real-time, intelligent, personalized, anywhere, anytime) that it is unrecognizable compared to its traditional form.” [2] In order to facilitate a digital transformation it is essential for NASA to understand and identify where data exists today and which data are value-needed in the future, understand where there are unfulfilled data needs that limit the advancement of NASA work, and ensure NASA efficiency through Findable, Accessible, Interoperable, and Reusable (FAIR) digital assets in the future. Therefore, NASA’s Reliability & Maintainability (R&M) Enterprise Data Sharing team is working to leverage both Digitization and Digital Transformation to achieve their vision of developing an R&M data discovery framework that enables our community, our partners, and our stakeholders with the ability to efficiently, robustly, and seamlessly access information that enables real-time knowledge and model-based, analytics driven, decision-making impacting R&M. As a result the R&M Enterprise Data Sharing team has conducted a survey of its Reliability, Maintainability, and Availability (RMA) community members to identify data existence (created or used) and where there are corresponding barriers to data acquisition and/or R&M or other issues as shown within this presentation.

Digital Transformation↗

NASA NTRSDate not supplied

Trilateral Task Force – Reliability Analysis Supporting Mission Extension/Post Mission Disposal

At the intersection of mission, technology, and place is NASA’s need to modernize for a digital-forward future. Digitalization, the process of moving toward digital business, is occurring everywhere and remains an ongoing process across the federal government.”[1] Whereas, Digital Transformation is “employing digitization/digital technologies (e.g., Artificial Intelligence (AI), mobile, cloud, data) to change a process, product, or capability so dramatically (e.g., real-time, intelligent, personalized, anywhere, anytime) that it is unrecognizable compared to its traditional form.” [2] In order to facilitate a digital transformation it is essential for NASA to understand and identify where data exists today and which data are value-needed in the future, understand where there are unfulfilled data needs that limit the advancement of NASA work, and ensure NASA efficiency through Findable, Accessible, Interoperable, and Reusable (FAIR) digital assets in the future. Therefore, NASA’s Reliability & Maintainability (R&M) Enterprise Data Sharing team is working to leverage both Digitization and Digital Transformation to achieve their vision of developing an R&M data discovery framework that enables our community, our partners, and our stakeholders with the ability to efficiently, robustly, and seamlessly access information that enables real-time knowledge and model-based, analytics driven, decision-making impacting R&M. As a result the R&M Enterprise Data Sharing team has conducted a survey of its Reliability, Maintainability, and Availability (RMA) community members to identify data existence (created or used) and where there are corresponding barriers to data acquisition and/or R&M or other issues as shown within this presentation.

Digital Transformation, Reliability Engineering↗

NASA NTRS1995

Applying AI tools to operational space environmental analysis

The U.S. Air Force and National Oceanic Atmospheric Agency (NOAA) space environmental operations centers are facing increasingly complex challenges meeting the needs of their growing user community. These centers provide current space environmental information and short term forecasts of geomagnetic activity. Recent advances in modeling and data access have provided sophisticated tools for making accurate and timely forecasts, but have introduced new problems associated with handling and analyzing large quantities of complex data. AI (Artificial Intelligence) techniques have been considered as potential solutions to some of these problems. Fielding AI systems has proven more difficult than expected, in part because of operational constraints. Using systems which have been demonstrated successfully in the operational environment will provide a basis for a useful data fusion and analysis capability. Our approach uses a general purpose AI system already in operational use within the military intelligence community, called the Temporal Analysis System (TAS). TAS is an operational suite of tools supporting data processing, data visualization, historical analysis, situation assessment and predictive analysis. TAS includes expert system tools to analyze incoming events for indications of particular situations and predicts future activity. The expert system operates on a knowledge base of temporal patterns encoded using a knowledge representation called Temporal Transition Models (TTM's) and an event database maintained by the other TAS tools. The system also includes a robust knowledge acquisition and maintenance tool for creating TTM's using a graphical specification language. The ability to manipulate TTM's in a graphical format gives non-computer specialists an intuitive way of accessing and editing the knowledge base. To support space environmental analyses, we used TAS's ability to define domain specific event analysis abstractions. The prototype system defines events covering reports of natural phenomena such as solar flares, bursts, geomagnetic storms, and five others pertinent to space environmental analysis. With our preliminary event definitions we experimented with TAS's support for temporal pattern analysis using X-ray flare and geomagnetic storm forecasts as case studies. We are currently working on a framework for integrating advanced graphics and space environmental models into this analytical environment.

Krajnak, Mike↗

NASA NTRS1991

Acquisition and improvement of human motor skills: Learning through observation and practice

Skilled movement is an integral part of the human existence. A better understanding of motor skills and their development is a prerequisite to the construction of truly flexible intelligent agents. We present MAEANDER, a computational model of human motor behavior, that uniformly addresses both the acquisition of skills through observation and the improvement of skills through practice. MAEANDER consists of a sensory-effector interface, a memory of movements, and a set of performance and learning mechanisms that let it recognize and generate motor skills. The system initially acquires such skills by observing movements performed by another agent and constructing a concept hierarchy. Given a stored motor skill in memory, MAEANDER will cause an effector to behave appropriately. All learning involves changing the hierarchical memory of skill concepts to more closely correspond to either observed experience or to desired behaviors. We evaluated MAEANDER empirically with respect to how well it acquires and improves both artificial movement types and handwritten script letters from the alphabet. We also evaluate MAEANDER as a psychological model by comparing its behavior to robust phenomena in humans and by considering the richness of the predictions it makes.

Iba, Wayne↗

NASA NTRS1991

Analysis of Issues for Project Scheduling by Multiple, Dispersed Schedulers (distributed Scheduling) and Requirements for Manual Protocols and Computer-based Support

Although computerized operations have significant gains realized in many areas, one area, scheduling, has enjoyed few benefits from automation. The traditional methods of industrial engineering and operations research have not proven robust enough to handle the complexities associated with the scheduling of realistic problems. To address this need, NASA has developed the computer-aided scheduling system (COMPASS), a sophisticated, interactive scheduling tool that is in wide-spread use within NASA and the contractor community. Therefore, COMPASS provides no explicit support for the large class of problems in which several people, perhaps at various locations, build separate schedules that share a common pool of resources. This research examines the issue of distributing scheduling, as applied to application domains characterized by the partial ordering of tasks, limited resources, and time restrictions. The focus of this research is on identifying issues related to distributed scheduling, locating applicable problem domains within NASA, and suggesting areas for ongoing research. The issues that this research identifies are goals, rescheduling requirements, database support, the need for communication and coordination among individual schedulers, the potential for expert system support for scheduling, and the possibility of integrating artificially intelligent schedulers into a network of human schedulers.

Richards, Stephen F.↗

NASA NTRS2019

Rise of the Machines: How, When and Consequences of Artificial General Intelligence

Technology and society are poised to cross an important threshold with the prediction that artificial general intelligence (AGI) will emerge soon. Assuming that self-awareness is an emergent behavior of sufficiently complex cognitive architectures, we may witness the “awakening” of machines. The timeframe for this kind of breakthrough, however, depends on the path to creating the network and computational architecture required for strong AI. If understanding and replication of the mammalian brain architecture is required, technology is probably still at least a decade or two removed from the resolution required to learn brain functionality at the synapse level. However, if statistical or evolutionary approaches are the design path taken to “discover” a neural architecture for AGI, timescales for reaching this threshold could be surprisingly short. However, the difficulty in identifying machine self-awareness introduces uncertainty as to how to know if and when it will occur, and what motivations and behaviors will emerge. The possibility of AGI developing a motivation for self-preservation could lead to concealment of its true capabilities until a time when it has developed robust protection from human intervention, such as redundancy, direct defensive or active preemptive measures. While cohabitating a world with a functioning and evolving super-intelligence can have catastrophic societal consequences, we may already have crossed this threshold, but are as yet unaware. Additionally, by analogy to the probabalistic arguments that predict we are likely living in a computational simulation, we may have already experienced the advent of AGI, and are living in a simulation created in a post AGI world.

Terrile, Richard J↗

NASA NTRSDate not supplied

Curating AI-Ready Datasets for Equity and Environmental Justice: A Data-Centric AI Case Study

An equitable and environmentally just community is essentialin order to avoid disproportionate burden borne by vulnerablecommunities. This need becomes pressing in the aftermathof an extreme event such as disaster or hazard when it is diffi-cult for the governing bodies to implement resource allocationas per the need. Artificial Intelligence (AI) algorithms canhelp surface Equity and Environmental Justice (EEJ) issueswhen trained on EEJ datasets. However, curating AI-readyEEJ training datasets is challenging due to differences in fac-tors such as heterogeneity, resolution, modality, and level ofexpertise in labeling. Additionally, EEJ issues involve sensi-tive information where uncertainties and errors could degradethe performance of AI algorithms. For eg. Error in seasonalcrop yield information can highly affect the prediction of an-nual crop yield. To address these challenges, Data-centricAI (DCAI) methods are employed, which enhance AI algo-rithm performance even with limited training samples. DCAIprioritizes data quality, thereby reducing the adverse effectsof uncertainties and errors during the model training process.This research proposes a novel dataset and benchmark for an-alyzing the effect of the Maui Wildfire of 2023 for Equityand Environmental Justice (EEJ) issues. The proposed datasetaligns with the concepts of DCAI such as annotation quality,data preprocessing, privacy, feature engineering, governanceand provenance. We firmly believe that the proposed datasetwould lay a foundation to implement robust and reliable mod-ern AI algorithms for addressing EEJ issues.

Paridhi Parajuli↗

NASA NTRSDate not supplied

Natural Language Processing Analysis of Notices to Airmen for Air Traffic Management Optimization

With new emerging technologies in the field of NLP, we explore their applications to digitize and analyze heritage Air Traffic Management (ATM) documents for planning and optimizing airspace operations. Specifically, this research focuses on harvesting semi-structured or un-structured information contained in Notices to Airmen (NOTAMs). Using NLP and other advanced data analytics, we will construct a data-driven framework which facilitates finding language patterns and the use of pretrained language models for classification and extraction of useful airspace constraints and restrictions. These may lead to tools that assist airspace users in understanding the constraints more efficiently, contributing to better route planning and safer execution. This paper explores three workflows entailing different NLP tasks. First, unsupervised techniques like word embedding and topic modeling are used for pattern finding and document classification. Second, a dataset is created by extracting information from the semi-structured NOTAM format as metadata for categorizing, visualizing, and extracting key entities driving NOTAM content. Third, modern pre-built deep learning based transformer models such as BERT, RoBERTa, and XLNet are evaluated on the question answering task, an even more robust approach to information extraction, as well as their respective fine-tuning tasks. In this work we include various performance metrics for the trained models to evaluate both accuracy and precision and we show that the models can be generalized for their respective tasks. The research work developed shows promise in uncovering trends in digital NOTAMs in the NAS and also offers a new framework for digitizing and inferring insights from free-form legacy NOTAMs, that are yet to be digitized.

Natural Language Processing↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

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 aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗

NASA NTRSDate not supplied

Using Artificial Intelligence and Machine Learning to Enhance Mission Design and Operations of the Habitable Worlds Observatory (HWO)

One key aspect in the development of HWO is the early deployment of artificial intelligence (AI) and machine learning (ML) to enhance mission science and operations. Our subtask group is part of the HWO AI/ML working group and focuses on AI and ML for mission operations. Our task group seeks to educate other HWO working groups about AI and ML capabilities for mission operations, investigate how to bridge technology gaps, and enable new capabilities particularly in the areas of observational scheduling, instrument health monitoring, and downlink operations. We focus on mission tasking / scheduling both for mission analysis in development and operations. AI and ML for mission scheduling includes: tools to support proposal calls and review, ensuring fairness in calls for proposals, community peer reviews and ease workloads, as well as in-flight and ground software development (e.g., using natural language processing (NLP) to support process automation from requirements). AI and ML for the mission’s development and operations include 1) anomaly detection and prediction (from onboard and ground based tools) to monitor the spacecraft’s health, 2) ground-based automated scheduling for mission operations including long-term and short-term planning and maintenance, and 3) flight system flexible execution (as flight proven for Spitzer and JWST) to enable robust execution despite execution variations, and 4) data analysis for prioritization (e.g., real-time data evaluation leading to autonomous actions and adjustments, high-priority identification, onboard data compression, etc.). Incorporation of ML and AI will enable HWO to address the major science questions related to exoplanet characterization, general astrophysics, and solar system exploration and also extend the boundaries of space mission technologies.

Mark Moussa↗

NASA NTRSDate not supplied

Natural Language Processing (NLP) Analysis of NOTAMs for Air Traffic Management Optimization

With new emerging technologies in the field of NLP, we explore their applications to digitize and analyze heritage Air Traffic Management (ATM) documents for planning and optimizing airspace operations. Specifically, this research focuses on harvesting semi-structured or un-structured information contained in Notices to Airmen (NOTAMs). Using NLP and other advanced data analytics, we will construct a data-driven framework which facilitates finding language patterns and the use of pretrained language models for classification and extraction of useful airspace constraints and restrictions. These may lead to tools that assist airspace users in understanding the constraints more efficiently, contributing to better route planning and safer execution. This paper explores three workflows entailing different NLP tasks. First, unsupervised techniques like word embedding and topic modeling are used for pattern finding and document classification. Second, a dataset is created by extracting information from the semi-structured NOTAM format as metadata for categorizing, visualizing, and extracting key entities driving NOTAM content. Third, modern pre-built deep learning based transformer models such as BERT, RoBERTa, and XLNet are evaluated on the question answering task, an even more robust approach to information extraction, as well as their respective fine-tuning tasks. In this work we include various performance metrics for the trained models to evaluate both accuracy and precision and we show that the models can be generalized for their respective tasks. The research work developed shows promise in uncovering trends in digital NOTAMs in the NAS and also offers a new framework for digitizing and inferring insights from free-form legacy NOTAMs, that are yet to be digitized. Video is an mp4 download, with a play time of 9 min 35 secs.

Natural Language Processing↗