Search NASA⌕ Search

SEARCH · Search NASA

Results for “training 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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

Predicting Arrival and Departure Runway Assignments with Machine Learning

Runway assignments at major airports are made by air traffic controllers subject to various constraints, and to achieve various objectives. In this research, we describe our efforts training machine learning (ML) models to predict both departure and arrival runway assignments using an entirely data-driven approach. This approach is compared to existing rule-based approaches developed in previous research using input from Subject Matter Experts. The models have features derived from various FAA data feeds, and leverage multiple machine learning algorithms. Results for models trained for nine major U.S. airports are described and compared to one another across various important dimensions. Particular attention was paid to developing a repeatable framework for training these models so the approach could be scaled to other airports, and to developing models that are useful in a real-time environment. In addition, the models were designed to be functional in a real-time environment to support NASA’s ATD-2 project, as part of an ML-powered shadow system to compare against the performance of the fielded system.

machine learning↗
NASA NTRS1997

Evaluation of Model-Based Training for Vertical Guidance Logic

This paper will summarize the results of a study which introduces a structured, model based approach to learning how the automated vertical guidance system works on a modern commercial air transport. The study proposes a framework to provide accurate and complete information in an attempt to eliminate confusion about 'what the system is doing'. This study will examine a structured methodology for organizing the ideas on which the system was designed, communicating this information through the training material, and displaying it in the airplane. Previous research on model-based, computer aided instructional technology has shown reductions in the amount of time to a specified level of competence. The lessons learned from the development of these technologies are well suited for use with the design methodology which was used to develop the vertical guidance logic for a large commercial air transport. The design methodology presents the model from which to derive the training material, and the content of information to be displayed to the operator. The study consists of a 2 X 2 factorial experiment which will compare a new method of training vertical guidance logic and a new type of display. The format of the material used to derive both the training and the display will be provided by the Operational Procedure Methodology. The training condition will compare current training material to the new structured format. The display condition will involve a change of the content of the information displayed into pieces that agree with the concepts with which the system was designed.

Feary, Michael↗
NASA NTRS2022

Microstructure Segmentation with Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset

This study examined the improvement of microscopy segmentation accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures, including VGG, Inception, and ResNet, were trained on over 100,000 labelled microscopy images from 54 classes. These pre-trained encoders were then embedded into multiple segmentation architectures including U-Net and DeepLabV3+ to evaluate segmentation performance on newly created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2 percent reduction in relative segmentation error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.

machine learning↗
NASA NTRS2022

Microstructure Segmentation With Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset

This study examined the improvement of microscopy segmentation intersection over union accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures were trained on over 100,000 labeled microscopy images from 54 material classes. These pre-trained encoders were then embedded into multiple segmentation architectures including UNet and DeepLabV3+ to evaluate segmentation performance on created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2% reduction in relative intersection over union error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.

machine learning↗
NASA NTRSDate not supplied

QuantifyML: How good is my machine learning model?

This paper presents an approach, QuantifyML, which employs model counting to assess the learnability and robustness of machine learning models. Typically the efficacy of machine learning models is determined by computing their accuracy statistically on test data sets. However, this may be misleading, if the test data is not representative of the problem that is being studied. Further, two different models may have the same accuracy on a given data set, measured statistically, but may be very different in their behavior on unseen data. Also, models with high accuracy could have poor adversarial robustness. In QuantifyML, our goal is to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into a C program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise counts w.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, expressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the robustness of trained models around given inputs. Our evaluation demonstrates these applications of QuantifyML on decision trees and neural networks trained to learn relational properties of graphs, for which we know the ground truth, and to perform image classification, for which we do not have the ground truth, but we can quantify local robustness.

Deep Neural Networks↗
NASA NTRSDate not supplied

QuantifyML: How Good is My Machine Learning Model?

We present QuantifyML, which applies model counting to assess the learn ability, safety, and robustness of machine learning models. Typically, the efficacy of machine learning models is determined by computing their accuracy statistically on test datasets. However, this may be misleading, if the test data is not representative of the problem that is being studied. With QuantifyML we aim to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into aC program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise countsw.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, ex-pressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the safety and robustness of trained models.

Deep Neural Networks↗
NASA NTRS2010

Systems Engineering Model and Training Application for Desktop Environment

Provide a graphical user interface based simulator for desktop training, operations and procedure development and system reference. This simulator allows for engineers to train and further understand the dynamics of their system from their local desktops. It allows the users to train and evaluate their system at a pace and skill level based on the user's competency and from a perspective based on the user's need. The simulator will not require any special resources to execute and should generally be available for use. The interface is based on a concept of presenting the model of the system in ways that best suits the user's application or training needs. The three levels of views are Component View, the System View (overall system), and the Console View (monitor). These views are portals into a single model, so changing the model from one view or from a model manager Graphical User Interface will be reflected on all other views.

May, Jeffrey T.↗
NASA NTRS2005

Improvements in Virtual Sensors: Using Spatial Information to Estimate Remote Sensing Spectra

Various instruments are used to create images of the Earth and other objects in the universe in a diverse set of wavelength bands with the aim of understanding natural phenomena. Sometimes these instruments are built in a phased approach, with additional measurement capabilities added in later phases. In other cases, technology may mature to the point that the instrument offers new measurement capabilities that were not planned in the original design of the instrument. In still other cases, high resolution spectral measurements may be too costly to perform on a large sample and therefore lower resolution spectral instruments are used to take the majority of measurements. Many applied science questions that are relevant to the earth science remote sensing community require analysis of enormous amounts of data that were generated by instruments with disparate measurement capabilities. In past work [1], we addressed this problem using Virtual Sensors: a method that uses models trained on spectrally rich (high spectral resolution) data to "fill in" unmeasured spectral channels in spectrally poor (low spectral resolution) data. We demonstrated this method by using models trained on the high spectral resolution Terra MODIS instrument to estimate what the equivalent of the MODIS 1.6 micron channel would be for the NOAA AVHRR2 instrument. The scientific motivation for the simulation of the 1.6 micron channel is to improve the ability of the AVHRR2 sensor to detect clouds over snow and ice. This work contains preliminary experiments demonstrating that the use of spatial information can improve our ability to estimate these spectra.

Oza, Nikunj C.↗
NASA NTRS1997

Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography

The use of computational-model trained artificial neural networks to acquire damage specific information from electronic holograms is discussed. A neural network is trained to transform two time-average holograms into a pattern related to the bending-induced-strain distribution of the vibrating component. The bending distribution is very sensitive to component damage unlike the characteristic fringe pattern or the displacement amplitude distribution. The neural network processor is fast for real-time visualization of damage. The two-hologram limit makes the processor more robust to speckle pattern decorrelation. Undamaged and cracked cantilever plates serve as effective objects for testing the combination of electronic holography and neural-net processing. The requirements are discussed for using finite-element-model trained neural networks for field inspections of engine components. The paper specifically discusses neural-network fringe pattern analysis in the presence of the laser speckle effect and the performances of two limiting cases of the neural-net architecture.

Decker, Arthur J.↗
NASA NTRS1998

Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography

The use of computational-model trained artificial neural networks to acquire damage specific information from electronic holograms is discussed. A neural network is trained to transform two time-average holograms into a pattern related to the bending-induced-strain distribution of the vibrating component. The bending distribution is very sensitive to component damage unlike the characteristic fringe pattern or the displacement amplitude distribution. The neural network processor is fast for real-time visualization of damage. The two-hologram limit makes the processor more robust to speckle pattern decorrelation. Undamaged and cracked cantilever plates serve as effective objects for testing the combination of electronic holography and neural-net processing. The requirements are discussed for using finite-element-model trained neural networks for field inspections of engine components. The paper specifically discusses neural-network fringe pattern analysis in the presence of the laser speckle effect and the performances of two limiting cases of the neural-net architecture.

Decker, Arthur J.↗
NASA NTRS2011

Houston, We Have a Problem Solving Model for Training

In late 2006, the Mission Operations Directorate (MOD) at NASA began looking at ways to make training more efficient for the flight controllers who support the International Space Station. The average certification times for flight controllers spanned from 18 months to three years and the MOD, responsible for technical training, was eager to develop creative solutions that would reduce the time to 12 months. Additionally, previously trained flight controllers sometimes participated in more than 50 very costly, eight-hour integrated simulations before becoming certified. New trainees needed to gain proficiency with far fewer lessons and training simulations than their predecessors. This poster presentation reviews the approach and the process that is currently in development to accomplish this goal.

Schmidt, Lacey↗
NASA NTRSDate not supplied

Quantum Hardware-Enabled Molecular Dynamics via Transfer Learning

The ability to perform ab initio molecular dynamics simulations using potential energy surfaces provided by quantum computers would open the door to virtually exact dynamics for a variety of chemical and biochemical systems, with impacts on catalysis and biophysics. Nonetheless, performing molecular dynamics on surfaces produced by quantum hardware has been hampered by the noisy energies typically produced by quantum computers and challenges associated with computing gradients and scaling to large systems interest. A recent set of advances in machine learning, known as transfer learning, provides a new path forward for molecular dynamics simulations on quantum hardware. Transfer learning offers a workaround, where one first trains models on larger, less accurate classical datasets and then refines them on smaller, more accurate quantum datasets. We explore this approach by training machine learning models to predict a molecule's potential energy based on its geometric structure using Behler-Parrinello neural networks. When successfully trained, the model enables energy gradient predictions necessary for dynamic simulations. To reduce the quantum resources needed, the model is initially trained with data derived from classical density functional theory and subsequently refined with a smaller dataset obtained from a variational quantum eigensolver optimization of the unitary coupled cluster ansatz. We show that this approach significantly reduces the size of the needed quantum training dataset while capturing the high accuracies needed within quantum chemistry simulations. The success of this two-step training method opens more opportunities to apply machine learning models on quantum data, a significant stride towards efficient quantum-classical hybrid computational models.

quantum computing↗
NASA NTRS1990

Designing a training tool for imaging mental models

The training process can be conceptualized as the student acquiring an evolutionary sequence of classification-problem solving mental models. For example a physician learns (1) classification systems for patient symptoms, diagnostic procedures, diseases, and therapeutic interventions and (2) interrelationships among these classifications (e.g., how to use diagnostic procedures to collect data about a patient's symptoms in order to identify the disease so that therapeutic measures can be taken. This project developed functional specifications for a computer-based tool, Mental Link, that allows the evaluative imaging of such mental models. The fundamental design approach underlying this representational medium is traversal of virtual cognition space. Typically intangible cognitive entities and links among them are visible as a three-dimensional web that represents a knowledge structure. The tool has a high degree of flexibility and customizability to allow extension to other types of uses, such a front-end to an intelligent tutoring system, knowledge base, hypermedia system, or semantic network.

Dede, Christopher J.↗
NASA NTRS2002

Neural Network and Regression Soft Model Extended for PAX-300 Aircraft Engine

In fiscal year 2001, the neural network and regression capabilities of NASA Glenn Research Center's COMETBOARDS design optimization testbed were extended to generate approximate models for the PAX-300 aircraft engine. The analytical model of the engine is defined through nine variables: the fan efficiency factor, the low pressure of the compressor, the high pressure of the compressor, the high pressure of the turbine, the low pressure of the turbine, the operating pressure, and three critical temperatures (T(sub 4), T(sub vane), and T(sub metal)). Numerical Propulsion System Simulation (NPSS) calculations of the specific fuel consumption (TSFC), as a function of the variables can become time consuming, and numerical instabilities can occur during these design calculations. "Soft" models can alleviate both deficiencies. These approximate models are generated from a set of high-fidelity input-output pairs obtained from the NPSS code and a design of the experiment strategy. A neural network and a regression model with 45 weight factors were trained for the input/output pairs. Then, the trained models were validated through a comparison with the original NPSS code. Comparisons of TSFC versus the operating pressure and of TSFC versus the three temperatures (T(sub 4), T(sub vane), and T(sub metal)) are depicted in the figures. The overall performance was satisfactory for both the regression and the neural network model. The regression model required fewer calculations than the neural network model, and it produced marginally superior results. Training the approximate methods is time consuming. Once trained, the approximate methods generated the solution with only a trivial computational effort, reducing the solution time from hours to less than a minute.

Patnaik, Surya N.↗
NASA NTRS2012

JELC-LITE: Unconventional Instructional Design for Special Operations Training

Current special operations staff training is based on the Joint Event Life Cycle (JELC). It addresses operational level tasks in multi-week, live military exercises which are planned over a 12 to 18 month timeframe. As the military experiences changing global mission sets, shorter training events using distributed technologies will increasingly be needed to augment traditional training. JELC-Lite is a new approach for providing relevant training between large scale exercises. This new streamlined, responsive training model uses distributed and virtualized training technologies to establish simulated scenarios. It keeps proficiency levels closer to optimal levels -- thereby reducing the performance degradation inherent in periodic training. It can be delivered to military as well as under-reached interagency groups to facilitate agile, repetitive training events. JELC-Lite is described by four phases paralleling the JELC, differing mostly in scope and scale. It has been successfully used with a Theater Special Operations Command and fits well within the current environment of reduced personnel and financial resources.

Friedman, Mark↗
NASA NTRSDate not supplied

Probabilistic Calibration of Expensive Models using Efficiently Trained Surrogates

Calibration of computational models in the presence of uncertainty is often cast as a Bayesian inference problem and solved via sampling methods, e.g., Markov chain Monte Carlo. When the computational model is expensive, this task becomes intractable due to the large number of samples required to accurately estimate the posterior distribution of the calibration parameters. A popular solution to this problem is to use machine learning to develop a faster-to-evaluate, lower-fidelity substitute for the original model to serve as a surrogate while solving the inference problem. Although considered an offline cost, generating training data to construct this surrogate model can still be an expensive task in practice. An active learning algorithm is presented that focuses training on improving surrogate accuracy specifically in and around the bulk of the posterior distribution, as this is where the model is exercised during calibration. Candidate samples are drawn from families of distributions related to an approximation of the posterior. The sample maximizing predictive variance is then selected for evaluation by the original computational model, yielding a label for the training point. Iterating this approach increases efficiency relative to space filling designs (e.g., Latin hypercube sampling) by avoiding low probability points. Practical considerations are discussed, including the benefits of using a sequential Monte Carlo sampling approach, convergence heuristics, and the importance of both exploration and exploitation given that the true posterior is unknown a priori.

uncertainty quantification↗
NASA NTRS1999

Neural-Net Processing of Characteristic Patterns From Electronic Holograms of Vibrating Blades

Finite-element-model-trained artificial neural networks can be used to process efficiently the characteristic patterns or mode shapes from electronic holograms of vibrating blades. The models used for routine design may not yet be sufficiently accurate for this application. This document discusses the creation of characteristic patterns; compares model generated and experimental characteristic patterns; and discusses the neural networks that transform the characteristic patterns into strain or damage information. The current potential to adapt electronic holography to spin rigs, wind tunnels and engines provides an incentive to have accurate finite element models lor training neural networks.

Decker, Arthur J.↗
NASA NTRS2022

The Influence of Land Use and Land Cover Change on Landslide Susceptibility in the Lower Mekong River Basin

The Lower Mekong River Basin in Southeast Asia experiences frequent rainfall-triggered landslides especially during the monsoon season. In this study, the influence of land use and land cover change and other causative factors on landslide susceptibility is evaluated in the Lower Mekong Basin. Frequency ratio analysis is performed to quantify the relationship between LULC change and susceptibility. Detailed landslide inventory maps are used for analysis with yearly LULC maps. The LULC change is used as a contributing variable in a logistic regression-based susceptibility model with other variables including distance to roads, slope, aspect, forest loss, and soil properties. The Receiver Operating Characteristic (ROC) curve and Area Under the Curve are estimated for the model trained by each landslide inventory. The models show good performance, with AUC values ranging from 0.697 to 0.958 and an average AUC equal to 0.820. Both the Frequency Ratio analysis and the Logistic Regression models indicate LULC change from agricultural land to forest has a positive correlation with landslide occurrence. The most significant factors in the models are found to be distance to roads, slope, and aspect. A better understanding of the effects of LULC on landslide susceptibility can be useful for local land and disaster management and for the implementation of LULC as a factor in future susceptibility models. Using datasets that are unique to the Lower Mekong region, this study provides additional insights into the relationship between causative factors and landslide activity to better inform regional and global landslide susceptibility modeling.

River Basin↗