Search NASA⌕ Search

SEARCH · Search NASA

Results for “Neural Machine Learning”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRS2019

TPSAS-NF1676L-32345-DND

Interest in the use of Raman spectrometers has seen an increase in the fields of geology and planetary sciences due to the non-destructive insight Raman spectra may provide into the molecular makeup of a given sample. Advancements in Raman spectrometer hardware have allowed for compact instruments to have deployment capabilities directly on interplanetary missions, flexible usage conditions requiring no sample collection/preparation, and no need for daylight radiation shielding. As the amount of science which can be collected from a Raman spectrometer in a given amount of time increases, a bottleneck will be created in data analysis which leaves a need for a faster method of spectral data classification. Recent studies have shown that machine learning models are able to solve this problem by achieving high-accuracy classification. Liu et al4 found the convolutional neural network (CNN) held the highest classification accuracy (96% top 5) for single sample Raman data.

A Atkinson↗
NASA NTRS2024

Soil Salinity Level Assessment and Prediction Integrating UAV-borne Hyperspectral Imaging and Machine Learning Algorithms to Combat Desertification

In response to the ongoing global food crisis, the United Nations has identified “Zero Hunger” as one of its Sustainable Development Goals. A central contributor to the crisis is the process in which agricultural lands go through desertification. Research has shown a direct correlation between soil salinity and desertification - increased salinity levels indicate a higher risk for desertification. Furthermore, researchers have explored various techniques to map soil salinity, but these methods are oftentimes inefficient and don’t address future salinity predictions. To improve desertification monitoring, soil salinity can be observed via hyperspectral imaging on unmanned aerial vehicles (UAVs) to predict the risk of agricultural desertification using artificial intelligence (AI) and machine learning (ML) techniques. A significant gap exists in past research that applies ML and imaging techniques to soil salinity: convolutional neural networks (CNNs) and regression models are rarely leveraged together, despite the efficiency and accuracy of these models. To compensate for this gap, the proposed system leverages the use of these AI and ML models to improve soil assessment and prediction techniques. This approach involves three steps - data collection, image analysis, and future prediction. Using hyperspectral cameras on UAVs to collect the data from the region, a trained CNN model will output estimated soil salinity levels at a specific time. The estimations will then be analyzed by a regression model to assess the accuracy of future soil salinity predictions. The proposed system will identify regions at risk of desertification to help farmers mitigate agricultural loss, in turn helping alleviate the food crisis.

UAV systems↗
NASA NTRS2004

Fast Query-Optimized Kernel-Machine Classification

A recently developed algorithm performs kernel-machine classification via incremental approximate nearest support vectors. The algorithm implements support-vector machines (SVMs) at speeds 10 to 100 times those attainable by use of conventional SVM algorithms. The algorithm offers potential benefits for classification of images, recognition of speech, recognition of handwriting, and diverse other applications in which there are requirements to discern patterns in large sets of data. SVMs constitute a subset of kernel machines (KMs), which have become popular as models for machine learning and, more specifically, for automated classification of input data on the basis of labeled training data. While similar in many ways to k-nearest-neighbors (k-NN) models and artificial neural networks (ANNs), SVMs tend to be more accurate. Using representations that scale only linearly in the numbers of training examples, while exploring nonlinear (kernelized) feature spaces that are exponentially larger than the original input dimensionality, KMs elegantly and practically overcome the classic curse of dimensionality. However, the price that one must pay for the power of KMs is that query-time complexity scales linearly with the number of training examples, making KMs often orders of magnitude more computationally expensive than are ANNs, decision trees, and other popular machine learning alternatives. The present algorithm treats an SVM classifier as a special form of a k-NN. The algorithm is based partly on an empirical observation that one can often achieve the same classification as that of an exact KM by using only small fraction of the nearest support vectors (SVs) of a query. The exact KM output is a weighted sum over the kernel values between the query and the SVs. In this algorithm, the KM output is approximated with a k-NN classifier, the output of which is a weighted sum only over the kernel values involving k selected SVs. Before query time, there are gathered statistics about how misleading the output of the k-NN model can be, relative to the outputs of the exact KM for a representative set of examples, for each possible k from 1 to the total number of SVs. From these statistics, there are derived upper and lower thresholds for each step k. These thresholds identify output levels for which the particular variant of the k-NN model already leans so strongly positively or negatively that a reversal in sign is unlikely, given the weaker SV neighbors still remaining. At query time, the partial output of each query is incrementally updated, stopping as soon as it exceeds the predetermined statistical thresholds of the current step. For an easy query, stopping can occur as early as step k = 1. For more difficult queries, stopping might not occur until nearly all SVs are touched. A key empirical observation is that this approach can tolerate very approximate nearest-neighbor orderings. In experiments, SVs and queries were projected to a subspace comprising the top few principal- component dimensions and neighbor orderings were computed in that subspace. This approach ensured that the overhead of the nearest-neighbor computations was insignificant, relative to that of the exact KM computation.

Mazzoni, Dominic↗
NASA NTRSDate not supplied

Interpretable Tree-Based and Graph Neural Network Approaches for Novel Solid State Electrolyte Design

All-solid-state batteries with Li metal anode can address the safety issues surrounding traditional Li-ion batteries as well as the demand for higher energy densities. However, the development of solid electrolytes simultaneously possessing high ionic conductivity and good chemical and electrochemical stabilities has proven to be a challenge. I will present our informatics approach to explore the Li compound space for promising solid electrolytes using high-throughput multi-property screening and interpretable machine learning. This is accomplished through the generation of a large database of battery-related materials properties of Li compounds. We use tree-based ensemble learning methods and graph neural network approaches to accurately learn relationships between crystal structures and corresponding thermodynamic and kinetic properties, with interpretability being a major focus. Our models give us the ability to enable rapid discovery and design of novel solid-state battery chemistries.

Materials discovery↗
NASA NTRS1987

Learning in Artificial Neural Systems

This paper presents an overview and analysis of learning in Artificial Neural Systems (ANS's). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANS's is then described, and compared with classical Machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized, and where possible, the limitations inherent to specific classes of rules are outlined.

Matheus, Christopher J.↗
NASA NTRS1993

Population-based learning of load balancing policies for a distributed computer system

Effective load-balancing policies use dynamic resource information to schedule tasks in a distributed computer system. We present a novel method for automatically learning such policies. At each site in our system, we use a comparator neural network to predict the relative speedup of an incoming task using only the resource-utilization patterns obtained prior to the task's arrival. Outputs of these comparator networks are broadcast periodically over the distributed system, and the resource schedulers at each site use these values to determine the best site for executing an incoming task. The delays incurred in propagating workload information and tasks from one site to another, as well as the dynamic and unpredictable nature of workloads in multiprogrammed multiprocessors, may cause the workload pattern at the time of execution to differ from patterns prevailing at the times of load-index computation and decision making. Our load-balancing policy accommodates this uncertainty by using certain tunable parameters. We present a population-based machine-learning algorithm that adjusts these parameters in order to achieve high average speedups with respect to local execution. Our results show that our load-balancing policy, when combined with the comparator neural network for workload characterization, is effective in exploiting idle resources in a distributed computer system.

Mehra, Pankaj↗
NASA NTRS1994

A neural network controller for automated composite manufacturing

At McDonnell Douglas Aerospace (MDA), an artificial neural network based control system has been developed and implemented to control laser heating for the fiber placement composite manufacturing process. This neurocontroller learns an approximate inverse model of the process on-line to provide performance that improves with experience and exceeds that of conventional feedback control techniques. When untrained, the control system behaves as a proportional plus integral (PI) controller. However after learning from experience, the neural network feedforward control module provides control signals that greatly improve temperature tracking performance. Faster convergence to new temperature set points and reduced temperature deviation due to changing feed rate have been demonstrated on the machine. A Cerebellar Model Articulation Controller (CMAC) network is used for inverse modeling because of its rapid learning performance. This control system is implemented in an IBM compatible 386 PC with an A/D board interface to the machine.

Lichtenwalner, Peter F.↗
NASA NTRSDate not supplied

A Machine-Learning Approach to Assess Aircraft Engine System Performance

Artificial intelligence (AI)/machine learning, and big data are transforming the global business environment. They have become the most disruptive technologies for organizations to improve workplace efficiency and productivity. This work explored the application of machine learning-based predictive analytics that would enable aircraft engine designers to estimate engine system performance quickly during the conceptual design stage. Supervised machine-learning algorithm was employed to study patterns in an existing database of production and research turbofan engines, and built predictive analytics for use in predicting system performance of new turbofan designs. Specifically, the author developed deep-learning analytics to predict turbofan system weight, using turbofan design parameters as the input. The predictive analytics were trained and deployed in Keras, an open-source neural networks API (application program interface) written in Python, with TensorFlow (an open-source artificial AI library developed by Google) serving as the backend engine. The current engine-weight prediction results, together with those for the TSFC (thrust specific fuel consumption) and core-size predictions that were studied previously by the author, show that machine learning-based predictive analytics can be an effective, time-saving tool for aircraft engine design-space exploration during the conceptual design stage. It would enable expeditious identification of the best engine design amongst several candidates.

Michael T Tong↗
NASA NTRSDate not supplied

Modeling Ring-Opening Polymerization with Machine-Learned Committors

Many important industrial and biological processes depend on ring-opening polymerization (ROP), including large-scale production polymers, such as nylon 6, and a variety of biodegradable polymers and high-performance resins. Large-scale simulations (>200K atoms) of ROP were performed using a deep neural network-based method that captured the effect of the local chemical environment of the reactive sites using training data from quantum chemical methods. The utility of this method was demonstrated by modeling the cationic ROP of bis-benzoxazine, a promising resin for use in advanced high-temperature application composites (>200°C). Density functional theory calculations were used to map out the various ring opening and polymerization reaction paths that occur during the thermal processing of bis-benzoxazine. The probabilities of these reactions, as a function of local atomic configurations, were used to construct committor functions using a neural network approach. The learned committor functions were then used to determine when a particular reaction occurred within the REACTER framework for reactive molecular dynamics simulations. The experimentally observed exotherm that occurs during bis-benzoxazine ROP was captured in an effective manner in the simulations by imposing a local heating of the system that corresponds to the enthalpy of reaction for each reaction. The dependence of the final polymer morphology on the ROP reaction temperature was analyzed at the molecular scale. The results presented in this work indicate that machine-learned committor functions are a promising approach for incorporating high-fidelity reactivity criteria that capture the effect of local chemical environments into large-scale polymerization simulations.

machine learning, polymer simulations, molecular d↗
NASA NTRSDate not supplied

Quantum-Assisted Variational Segmentation for Image-to-Image Wildfire Detection Using Satellite Data

The quantum computing community has been searching for suitable applications to demonstrate the potential of near-term quantum devices. Quantum machine learning is a potential candidate, particularly using models that cannot be efficiently simulated with classical computers [1, 2]. This work focuses on a transition phase of quantum computers where the quantum machine learning model is still simulable classically but projected not to be simulable as the size of the model grows. Ultimately quantum computers may have advantages for high-dimensional real-world problems. Due to the limited number of qubits in current noisy intermediate-scale quantum (NISQ) devices, the direct application of quantum computers in high dimensional data is not feasible. To remedy this problem, an encoder-decoder architecture can be utilized. The encoder model would transform the high-dimensional data into a compact representation, to a level that small quantum computers can be used today (or in the near future), and the decoder would take the quantum processed outputs back to the high-dimensional space. Addressing the two challenges of quantum machine learning, this work investigates a hybrid supervised generative model with a quantum Ising Born machine embedded as the latent distribution. The model contains four main parts (Figure 1.a.): (1) a U-NET architecture responsible for learning segmentation flow, (2) a Prior network responsible for learning an encoded latent distribution of the input data, (3) a Born machine which represents the latent distribution, and (4) a Posterior network in charge of learning the joint encoded latent distribution of inputs and target data. The initial model, proposed by [3], is optimized by (1) maximizing the overlap of the prior and posterior latent distributions, and (2) minimizing the segmentation loss. The proposed model is designed to be investigated in a simulation environment applied to the real-world application of wildfire segmentation. Specifically, the model is designed to solve the patchy wildfire segmentations of Moderate Resolution Imaging Spectroradiometer (MODIS) by taking the MODIS observations and using Visible Infrared Imaging Radiometer Suite’s (VIIRS) consistent wildfire product as the target. The model solves patchy wildfire segmentations and provides insight into the epistemic errors sourced from model variation. The model utilizes the Born machine as a QUBO solver to represent the latent space as a Bernoulli distribution. The proposed configuration allows the variational segmentation model to leverage the true quantum probabilistic nature and derive a more expressive latent configuration, increasing the model performance in describing wildfire segmentations. The quantum probabilistic information of the Born machine is directly incorporated in the Kullback-Leibler divergence loss in the prior and posterior distributions, forcing the Bernoulli latent distribution to maximize the overlap of input and joint input-target distributions. The proposed model is then trained and compared with a baseline only consisting of direct Bernoulli latent distribution with no Born machine representing the latent space. The models are evaluated based on the segmentation metrics, such as precision, recall, intersect of union, with uncertainty boundaries accounting for the stochastic nature of the model. Our findings show that even in low latent-dimensional space (due to the limit in computational power of the classical quantum simulator), we are able to effectively capture the latent representation and hence the model performs better than the baseline. The findings are a projection for scaling the model into higher dimensional latent space with the Born machine surpassing the baseline performance. Figure 1. Sub-figure (a) demonstrates the architecture for the training phase. The model consists of a Prior and Posterior network that encode inputs and joint input-target data into compact representations, respectively. The Born machine represents the latent distribution, and the U-NET branch learns the segmentation patterns of the data. The stochasticity is introduced to the U-NET through its last layer to create meaningful but stochastic segmentations. Sub-figure (b) represents the inference phase where the model takes the stochastic behavior from the prior network and injects that into the U-NET. Each attempt of inference will generate different but similar segmentations from the same distribution of the wildfire event. REFERENCES [1] Coyle, B., Mills, D., Danos, V., & Kashefi, E. (2020). The Born supremacy: quantum advantage and training of an Ising Born machine. npj Quantum Information, 6(1), 1-11. [2] Liu, J. G., & Wang, L. (2018). Differentiable learning of quantum circuit born machines. Physical Review A, 98(6), 062324. [3] Kohl, S., Romera-Paredes, B., Meyer, C., De Fauw, J., Ledsam, J. R., Maier-Hein, K., ... & Ronneberger, O. (2018). A probabilistic u-net for segmentation of ambiguous images. Advances in neural information processing systems, 31.

quantum machine learning↗
NASA NTRS2023

Use of Machine Learning and Principal Component Analysis to Retrieve Nitrogen Dioxide (NO 2 ) With Hyperspectral Imagers and Reduce Noise in Spectral Fitting

Nitrogen dioxide (NO 2 ) is an important trace-gas pollutant and climate agent whose presence also leads to spectral interference in ocean color retrievals. NO 2 column densities have been retrieved with satellite UV–Vis spectrometers such as the Ozone Monitoring Instrument (OMI) and the Tropospheric Monitoring Instrument (TROPOMI) that typically have spectral resolutions of the order of 0.5 nm or better and spatial footprints as small as 3.6 km × 5.6 km. These NO 2 observations are used to estimate emissions, monitor pollution trends, and study effects on human health. Here, we investigate whether it is possible to retrieve NO 2 amounts with lower-spectral-resolution hyperspectral imagers such as the Ocean Color Instrument (OCI) that will fly on the Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) satellite set for launch in early 2024. OCI will have a spectral resolution of 5 nm and a spatial resolution of ∼ 1 km with global coverage in 1–2 d. At this spectral resolution, small-scale spectral structure from NO 2 absorption is still present. We use real spectra from the OMI to simulate OCI spectra that are in turn used to estimate NO 2 slant column densities (SCDs) with an artificial neural network (NN) trained on target OMI retrievals. While we obtain good results with no noise added to the OCI simulated spectra, we find that the expected instrumental noise substantially degrades the OCI NO 2 retrievals. Nevertheless, the NO 2 information from OCI may be of value for ocean color retrievals. OCI retrievals can also be temporally averaged over timescales of the order of months to reduce noise and provide higher-spatial-resolution maps that may be useful for downscaling lower-spatial-resolution data provided by instruments such as OMI and TROPOMI; this downscaling could potentially enable higher-resolution emissions estimates and be useful for other applications. In addition, we show that NNs that use coefficients of leading modes of a principal component analysis of radiance spectra as inputs appear to enable noise reduction in NO 2 retrievals. Once trained, NNs can also substantially speed up NO 2 spectral fitting algorithms as applied to OMI, TROPOMI, and similar instruments that are flying or will soon fly in geostationary orbit.

NO2↗
NASA NTRS2021

Aerosol and Cloud Detection Using Machine Learning Algorithms and Space-Based Lidar Data

Clouds and aerosols play a significant role in determining the overall atmospheric radiation budget, yet remain a key uncertainty in understanding and predicting the future climate system. In addition to their impact on the Earth’s climate system, aerosols from volcanic eruptions, wildfires, man-made pollution events, and dust storms are hazardous to aviation safety and human health. Space-based lidar systems provide critical information about the vertical distributions of clouds and aerosols that greatly improve our understanding of the climate system. However, daytime data from backscatter lidars, such as the Cloud-Aerosol Transport System (CATS) on the International Space Station (ISS), must be averaged during science processing at the expense of spatial resolution to obtain sufficient signal-to-noise ratio (SNR) for accurately detecting atmospheric features. For example, 50% of all atmospheric features reported in daytime operational CATS data products require averaging to 60 km for detection. Furthermore, the single-wavelength nature of the CATS primary operation mode makes accurately typing these features challenging in complex scenes. This paper presents machine learning (ML) techniques that, when applied to CATS data, enable detection of atmospheric features during daytime operations with a horizontal resolution of 5 km compared to the 60 km horizontal resolution often required for daytime CATS data. A Convolutional Neural Network (CNN) trained using CATS standard data products also demonstrated the potential for improved cloud-aerosol discrimination compared to the operational CATS algorithms for cloud edges and complex near-surface scenes during daytime.

lidar↗
NASA NTRS2021

Applying Machine Learning to Predict Alaskan Ionospheric Irregularities

In this work several machine-learning (ML) techniques for predicting ionospheric irregularities in the northern auroral zone were tested. The techniques include Ridge Regression, Long Short-Term Memory Neural Network (LSTM), Classification Neural Network (CNN), Autoencoder Classification Neural Network (ACNN), and LSTM Autoencoder Classification Neural Network (LACNN). These techniques were tested with the rate of total electron content (TEC) index (ROTI) data collected during 2008 and 2009 from a geodetic station in Fairbanks, Alaska (64.98°N, 147.50°W), which is in the auroral zone. Using ROTI data with the ML techniques, experiments were conducted to reach two goals: (1) examine what space weather measurements present good correlation with ROTI so that they may be helpful in ML-based prediction of ionospheric irregularities in the polar region; (2) predict ROTI hours and days ahead by training the neural network models with historical ROTI data alone. The Ridge Regression experiments indicate that a combination of measurements of local geomagnetic horizontal components, geomagnetic SYM-H index, 3-hour Kp and ap indices, and F10.7 solar flux index appears to be more correlated to the single-site ROTI measurements than other parameters. The neural network (NN) experiments show that although the LACNN model allows for predictions of non-irregularity and irregularity conditions defined by ROTI levels up to 3 hours in advance, with an overall accuracy ≥ 92%, a number of irregularity events can still be missed. Hence, further development is needed to reduce the number of missed events. In this paper, the models, data processing, model performance, prediction results, and potential applications are presented.

Pi, Xiaoqing↗
NASA NTRS2012

Estimation and Bias Correction of Aerosol Abundance using Data-driven Machine Learning and Remote Sensing

Air quality information is increasingly becoming a public health concern, since some of the aerosol particles pose harmful effects to peoples health. One widely available metric of aerosol abundance is the aerosol optical depth (AOD). The AOD is the integrated light extinction coefficient over a vertical atmospheric column of unit cross section, which represents the extent to which the aerosols in that vertical profile prevent the transmission of light by absorption or scattering. The comparison between the AOD measured from the ground-based Aerosol Robotic Network (AERONET) system and the satellite MODIS instruments at 550 nm shows that there is a bias between the two data products. We performed a comprehensive analysis exploring possible factors which may be contributing to the inter-instrumental bias between MODIS and AERONET. The analysis used several measured variables, including the MODIS AOD, as input in order to train a neural network in regression mode to predict the AERONET AOD values. This not only allowed us to obtain an estimate, but also allowed us to infer the optimal sets of variables that played an important role in the prediction. In addition, we applied machine learning to infer the global abundance of ground level PM2.5 from the AOD data and other ancillary satellite and meteorology products. This research is part of our goal to provide air quality information, which can also be useful for global epidemiology studies.

Malakar, Nabin K.↗
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 NTRS2017

Application of Machine Learning to Rotorcraft Health Monitoring

Machine learning is a powerful tool for data exploration and model building with large data sets. This project aimed to use machine learning techniques to explore the inherent structure of data from rotorcraft gear tests, relationships between features and damage states, and to build a system for predicting gear health for future rotorcraft transmission applications. Classical machine learning techniques are difficult, if not irresponsible to apply to time series data because many make the assumption of independence between samples. To overcome this, Hidden Markov Models were used to create a binary classifier for identifying scuffing transitions and Recurrent Neural Networks were used to leverage long distance relationships in predicting discrete damage states. When combined in a workflow, where the binary classifier acted as a filter for the fatigue monitor, the system was able to demonstrate accuracy in damage state prediction and scuffing identification. The time dependent nature of the data restricted data exploration to collecting and analyzing data from the model selection process. The limited amount of available data was unable to give useful information, and the division of training and testing sets tended to heavily influence the scores of the models across combinations of features and hyper-parameters. This work built a framework for tracking scuffing and fatigue on streaming data and demonstrates that machine learning has much to offer rotorcraft health monitoring by using Bayesian learning and deep learning methods to capture the time dependent nature of the data. Suggested future work is to implement the framework developed in this project using a larger variety of data sets to test the generalization capabilities of the models and allow for data exploration.

machine learning↗
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↗