Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the Aviation Safety Reporting System (ASRS). Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about weather and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗
NASA NTRS2023

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the ASRS. Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about human factors, aircraft, and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗
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 NTRS1981

Computational theory of line drawing interpretation

The recovery of the three dimensional structure of visible surfaces depicted in an image by emphasizing the role of geometric cues present in line drawings, was studied. Three key components are line classification, line interpretation, and surface interpolation. A model for three dimensional line interpretation and surface orientation was refined and a theory for the recovery of surface shape from surface marking geometry was developed. A new approach to the classification of edges was developed and implemented signatures were deduced for each of several edge types, expressed in terms of correlational properties of the image intensities in the vicinity of the edge. A computer program was developed that evaluates image edges as compared with these prototype signatures.

Witkin, A. P.↗
NASA NTRS1985

Discrete Random Media Techniques for Microwave Modeling of Vegetated Terrain

Microwave remote sensing of vegetated terrain has been studied. Vegetation is modeled so that backscattered radar signals can be used to infer parameters which characterize the vegetation and underlying ground. The vegetation is modeled by discrete lossy dielectric scatterers with prescribed characteristics. The goal of the modeling effort is to remotely sense vegetation type (classification), growth stage, and plant/ground moisture. This information can then be used as input into agricultural, forestry and global circulation models. The microwave frequency spectrum, particularly L and C bands, are especially appropriate for this purpose since the wavelength is comparable to plant leaf and stem size. The resulting resonant interaction leads to backscattered data highly depend on plant shape and orientation. In addition, the transparent nature of the atmosphere in this frequency regime allows for algorithm development which requires no atmospheric correction.

Lang, R. H.↗
NASA NTRS2020

Study of Antarctic Blowing Snow Storms Using MODIS and CALIOP Observations With a Machine Learning Model

As a common phenomenon over Antarctica, blowing snow (BLSN), especially the large BLSN storms, play an important role in the Antarctic surface mass balance, radiation budget, and planetary boundary layer processes. This study presents the work on BLSN storm identification and analysis with observations from the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard the Aqua satellite. Spectral analysis shows that BLSN identification is feasible with MODIS daytime data. A random forest machine learning model is developed and observations from the Cloud‐Aerosol Lidar with Orthogonal Polarization are used for training. Model performance results show that machine‐learning based classification can achieve over 90% overall accuracy when classifying MODIS pixels into cloud, clear, and BLSN categories. The machine learning model is applied to MODIS observations during the month of October 2009 for BLSN storm analysis. Results show that the size of BLSN storms has a large spectrum and can reach hundreds of thousands km2. The MODIS based BLSN storm frequency map extends the Cloud‐Aerosol Lidar and Infrared Pathfinder Satellite Observations coverage limit from 82°S to the South Pole. A BLSN storm belt, which extends from the South Pole region to the coastal area between 130°E and 160°E along the Transantarctic Mountains, provides a potential pathway of snow transport. These results are important in improving the understanding of BLSN impact on Antarctic surface mass balance and boundary layer processes.

Antarctic↗
NASA NTRS1989

Modeling, simulation, and analysis of optical remote sensing systems

Remote Sensing of the Earth's resources from space-based sensors has evolved in the past 20 years from a scientific experiment to a commonly used technological tool. The scientific applications and engineering aspects of remote sensing systems have been studied extensively. However, most of these studies have been aimed at understanding individual aspects of the remote sensing process while relatively few have studied their interrelations. A motivation for studying these interrelationships has arisen with the advent of highly sophisticated configurable sensors as part of the Earth Observing System (EOS) proposed by NASA for the 1990's. Two approaches to investigating remote sensing systems are developed. In one approach, detailed models of the scene, the sensor, and the processing aspects of the system are implemented in a discrete simulation. This approach is useful in creating simulated images with desired characteristics for use in sensor or processing algorithm development. A less complete, but computationally simpler method based on a parametric model of the system is also developed. In this analytical model the various informational classes are parameterized by their spectral mean vector and covariance matrix. These class statistics are modified by models for the atmosphere, the sensor, and processing algorithms and an estimate made of the resulting classification accuracy among the informational classes. Application of these models is made to the study of the proposed High Resolution Imaging Spectrometer (HRIS). The interrelationships among observational conditions, sensor effects, and processing choices are investigated with several interesting results.

Kerekes, John Paul↗
NASA NTRS2015

Online Dectection and Modeling of Safety Boundaries for Aerospace Application Using Bayesian Statistics

The behavior of complex aerospace systems is governed by numerous parameters. For safety analysis it is important to understand how the system behaves with respect to these parameter values. In particular, understanding the boundaries between safe and unsafe regions is of major importance. In this paper, we describe a hierarchical Bayesian statistical modeling approach for the online detection and characterization of such boundaries. Our method for classification with active learning uses a particle filter-based model and a boundary-aware metric for best performance. From a library of candidate shapes incorporated with domain expert knowledge, the location and parameters of the boundaries are estimated using advanced Bayesian modeling techniques. The results of our boundary analysis are then provided in a form understandable by the domain expert. We illustrate our approach using a simulation model of a NASA neuro-adaptive flight control system, as well as a system for the detection of separation violations in the terminal airspace.

Statistics↗
NASA NTRS2021

Classifying Forest Type in the National Forest Inventory Context with Airborne Hyperspectral and Lidar Data

Forest structure and composition regulate a range of ecosystem services, including biodiversity, water and nutrient cycling, and wood volume for resource extraction. Forest type is an important metric measured in the US Forest Service Forest Inventory and Analysis (FIA) program, the national forest inventory of the USA. Forest type information can be used to quantify carbon and other forest resources within specific domains to support ecological analysis and forest management decisions, such as managing for disease and pests. In this study, we developed a methodology that uses a combination of airborne hyperspectral and lidar data to map FIA-defined forest type between sparsely sampled FIA plot data collected in interior Alaska. To determine the best classification algorithm and remote sensing data for this task, five classification algorithms were tested with six different combinations of raw hyperspectral data, hyperspectral vegetation indices, and lidar-derived canopy and topography metrics. Models were trained using forest type information from 632 FIA subplots collected in interior Alaska. Of the thirty model and input combinations tested, the random forest classification algorithm with hyperspectral vegetation indices and lidar-derived topography and canopy height metrics had the highest accuracy (78% overall accuracy). This study supports random forest as a powerful classifier for natural resource data. It also demonstrates the benefits from combining both structural (lidar) and spectral (imagery) data for forest type classification.

random forest↗
NASA NTRS1983

The application of forest classification from Landsat data as a basis for natural hydrocarbon emission estimation and photochemical oxidant model simulations in southeastern Virginia

The possible contribution by natural hydrocarbon emissions to the total ozone budget recorded in the Tidewater region of southeastern Virginia during the height of the summer period was examined. Natural sources investigated were limited to the primary HC emitters and most prevalent natural vegetation, the forests. Three types and their areal coverage were determined for Region VI of the Virginia State Air Pollution Control Board using remotely sensed data from Landsat, a NASA experimental earth resources satellite. Emission factors appropriate to the specific types (coniferous 0.24 x 10 to the 13th, mixed 0.63 x 10 to the 13th, deciduous 1.92 x 10 to the 13th, microgram/h), derived from contemporary procedures, were applied to produce an overall regional emission rate of 2.79 x 10 to the 13th microgram/h for natural non-methane hydrocarbons (NMHC). This rate was used with estimates of the anthropogenic NO(x) and NMHC loading, as input into a photochemical box model. Additional HC loading on the order of that estimated to be produced by the natural forest communities was required in order to reach certain measured summer peak ozone levels as the computer simulation was unable to account for the measured episodic levels on the basis of the anthropogenic inventory alone.

Salop, J.↗
NASA NTRS1984

Multi crop area estimation in Idaho using EDITOR

The use of LANDSAT multispectral scanner digital data for multi-crop acreage estimation in the central Snake River Plain of Idaho was examined. Two acquisitions of LANDSAT data covering ground sample units selected from a U.S. Department of Agriculture sampling frame in a four country study site were used to train a maximum likelihood classifier which, subsequently, classified all picture elements in the study site. Acreage estimates for six major crops, by county and for the four counties combined, were generated from the classification using the Battesse-Fuller model for estimation by regression in small areas. Results from the regression analysis were compared to those obtained by direct expansion of the ground data. Using the LANDSAT data significantly decreased the errors associated with the estimates for the three largest acreage crops. The late date of the second LANDSAT acquisition may have contributed to the poor results for three summer crops.

Sheffner, E. J.↗
NASA NTRS1988

Digital and optical shape representation and pattern recognition; Proceedings of the Meeting, Orlando, FL, Apr. 4-6, 1988

The present conference discusses topics in pattern-recognition correlator architectures, digital stereo systems, geometric image transformations and their applications, topics in pattern recognition, filter algorithms, object detection and classification, shape representation techniques, and model-based object recognition methods. Attention is given to edge-enhancement preprocessing using liquid crystal TVs, massively-parallel optical data base management, three-dimensional sensing with polar exponential sensor arrays, the optical processing of imaging spectrometer data, hybrid associative memories and metric data models, the representation of shape primitives in neural networks, and the Monte Carlo estimation of moment invariants for pattern recognition.

Juday, Richard D.↗
NASA NTRS2002

Optimization of Designs for Nanotube-based Scanning Probes

Optimization of designs for nanotube-based scanning probes, which may be used for high-resolution characterization of nanostructured materials, is examined. Continuum models to analyze the nanotube deformations are proposed to help guide selection of the optimum probe. The limitations on the use of these models that must be accounted for before applying to any design problem are presented. These limitations stem from the underlying assumptions and the expected range of nanotube loading, end conditions, and geometry. Once the limitations are accounted for, the key model parameters along with the appropriate classification of nanotube structures may serve as a basis for the design optimization of nanotube-based probe tips.

Harik, V. M.↗
NASA NTRS2014

In-Situ and Remote-Sensing Data Fusion Using Machine Learning Techniques to Infer Urban and Fire Related Pollution Plumes

Airmass type characterization is key in understanding the relative contribution of various emission sources to atmospheric composition and air quality and can be useful in bottom-up model validation and emission inventories. However, classification of pollution plumes from space is often not trivial. Sub-orbital campaigns, such as SEAC4RS (Studies of Emissions, Atmospheric Composition, Clouds and Climate Coupling by Regional Surveys) give us a unique opportunity to study atmospheric composition in detail, by using a vast suite of in-situ instruments for the detection of trace gases and aerosols. These measurements allow identification of spatial and temporal atmospheric composition changes due to various pollution plumes resulting from urban, biogenic and smoke emissions. Nevertheless, to transfer the knowledge gathered from such campaigns into a global spatial and temporal context, there is a need to develop workflow that can be applicable to measurements from space. In this work we rely on sub-orbital in-situ and total column remote sensing measurements of various pollution plumes taken aboard the NASA DC-8 during 2013 SEAC4RS campaign, linking them through a neural-network (NN) algorithm to allow inference of pollution plume types by input of columnar aerosol and trace-gas measurements. In particular, we use the 4STAR (Spectrometer for Sky-Scanning, Sun-Tracking Atmospheric Research) airborne measurements of wavelength dependent aerosol optical depth (AOD), particle size proxies, O3, NO2 and water vapor to classify different pollution plumes. Our method relies on assigning a-priori ground-truth labeling to the various plumes, which include urban pollution, different fire types (i.e. forest and agriculture) and fire stage (i.e. fresh and aged) using cluster analysis of aerosol and trace-gases in-situ and auxiliary (e.g. trajectory) data and the training of a NN scheme to fit the best prediction parameters using 4STAR measurements as input. We explore our misclassification rates as related to our ground-truth labels, and with multi-layered pollution plume cases. The next step in our analysis is to optimize parameter selection for a scheme that can be applied to space-borne aerosol and trace-gas observation platforms such as OMI, and future geostationary satellites such as TEMPO and GEO-CAPE.

Neural-network↗
NASA NTRS2015

Data-Driven Surface Traversability Analysis for Mars 2020 Landing Site Selection

The objective of this paper is three-fold: 1) to describe the engineering challenges in the surface mobility of the Mars 2020 Rover mission that are considered in the landing site selection processs, 2) to introduce new automated traversability analysis capabilities, and 3) to present the preliminary analysis results for top candidate landing sites. The analysis capabilities presented in this paper include automated terrain classification, automated rock detection, digital elevation model (DEM) generation, and multi-ROI (region of interest) route planning. These analysis capabilities enable to fully utilize the vast volume of high-resolution orbiter imagery, quantitatively evaluate surface mobility requirements for each candidate site, and reject subjectivity in the comparison between sites in terms of engineering considerations. The analysis results supported the discussion in the Second Landing Site Workshop held in August 2015, which resulted in selecting eight candidate sites that will be considered in the third workshop.

Ono, Masahiro↗