SEARCH · Engineering Papers

Results for “Training Analysis”

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.

SourceResearch connectionFrom yearThrough year

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

At least 775 records · Page 43

All sources NASA NTRS DOE OSTI

NASA NTRS2023

Spatial and Temporal Analysis of Global Landslide Reporting Using a Decade of the Global Landslide Catalog

Rainfall-triggered landslides can result in devastating loss of life and property damage and are a growing concern from local to global scale. NASA’s Global Landslide Catalog (GLC) compiles a record of rainfall-triggered landslide events from media reports, academic articles, and existing databases at global scale. The database consists of all types of mass movement events that are triggered by rainfall and represents a minimum number of events occurring between 2007 – 2018. The research presented here evaluates global patterns in landslide reporting from events in the GLC. The evaluation includes an analysis of the spatial and temporal distribution of global landslide events and associated casualties and comparisons with other landslide inventories. This database has been used to estimate landslide hotspots, evaluate geographic patterns in landslides, and train and validate landslide models from local to global scales. The most notable landslide hotspots are in the Pacific Northwest of North America, High Mountain Asia, and the Philippines. Additionally, the relationship between country GDP and income status with landslide occurrence was determined to have a positive correlation between economic status and landslide reporting. The GLC also indicates a reporting bias towards English-speaking countries. The general goal of this research is to assess the decade of global landslide reports from the GLC and show how this database can be used for rainfall-triggered landslide research.

Global Landslide Catalog↗

NASA NTRSDate not supplied

Principal Component and Machine Learning Approach to Gap Fill Hyperspectral Ocean Color Satellite Retrievals

Retrievals of ocean color properties from space are important for monitoring the health of the ocean ecosystem but such retrievals can be limited spatially due to conditions such as clouds, aerosols, and sun glint. Gap filling of ocean color retrievals is typically performed by combining retrievals from multiple satellites or temporally averaging multiple days of retrievals. Despite these techniques large gaps still exist posing challenges for near real time monitoring of events like harmful algae blooms. To address these limitations, we developed a spatial gap filling approach applying machine learning approach to hyperspectral instruments to learn how to perform an atmospheric correction under challenging retrieval conditions. In this approach a principal component analysis is used to decompose the hyperspectral measurements into spectral components that describe the scattering and absorption of the atmosphere mixed with the surface spectral signatures. The coefficients of the principal components are used to train a neural network to predict ocean color properties derived from a standard MODIS ocean color algorithm. We apply the approach to two hyperspectral UV/VIS sensors, the Ozone Monitoring Instrument (OMI) and TROPOspheric Monitoring Instrument (TROPOMI) to show that it can be used to estimate ocean color properties such as chlorophyll, remote sensing reflectance, and fluorescence line height. This method could be used as a gap-filling technique for the future Ocean Color Instrument (OCI) onboard upcoming NASA's Plankton, Aerosol Cloud, ocean Ecosystem (PACE) satellite to provide additional information for monitoring the health of our global oceans. Additionally, it could be applied to the first NASA and Smithsonian geostationary Tropospheric Emissions: Monitoring of Pollution (TEMPO) spectrometer to better understand diurnal variability in inland and coastal ocean ecology.

Zachary Fasnacht↗

NASA NTRS2024

Effective structural impact detection and localization using convolutional neural network and Bayesian information fusion with limited sensors

Due to their unpredictable nature, many impact events (e.g., overheight vehicles striking on bridges) go unnoticed or get reported many hours later. However, they can induce structural failures or hidden damage that accelerates the structure’s long-term degradation. Therefore, prompt impact detection and localization strategies are essential for early warning of impact events and rapid maintenance of structures. Most existing impact detection strategies are developed for aircraft composite panels utilizing high-rate synchronized measurement from densely deployed sensors. Limited efforts have been made for infrastructure or human habitats which generally require large-scale but low-rate measurement. In particular, due to harsh environments (e.g., deep space habitats under meteoroids), structural impact localization must be robust to limited sensors (e.g., sensor damage during impacts) and multi-source errors (e.g., measurement errors). In this study, an effective impact detection and localization strategy is proposed using a limited number of vibration measurements, especially in harsh environments (e.g. in deep space). Convolutional neural networks are trained for each sensor node and are fused using Bayesian theory to improve the accuracy of impact localization. Special considerations are paid to evaluate the effect of both measurement error and modeling error in the analysis. The proposed strategy is illustrated using 1D structure, and further validated in 3D geodesic dome structure numerically. The results demonstrate that it can detect and localize impact events accurately and robustly on structures.

Yuguang Fu↗

NASA NTRSDate not supplied

Combining Data with Physical Knowledge for Uncertainty Quantification in Certification and Reliability Analysis

Unifying empirical data with predictive models can enable engineering cost-savings through certification by analysis and reliability-based design. Both concepts require rigorous uncertainty quantification (UQ) and robust understanding and treatment of relevant physics. Combining sampling-based UQ algorithms with high-fidelity simulations creates a computational bottleneck that is often alleviated through the use of machine learning (ML). ML can be used to create computationally efficient surrogates for simulations of complex or high-dimensional physical interactions (e.g., multi-phase interactions associated with melt pools in laser powder bed fusion or spatially-dependent material properties in functionally graded materials). However, negative side effects of ML may include a lack of interpretability and negative correlation between event rarity and simulation accuracy due to a lack of training data. As such, it is important to infuse ML algorithms with physics-based guardrails to provide confidence in their predictions. This talk will provide a brief review of recent NASA research at this intersection of physics-based simulation, ML, and UQ with a focus on certification and reliability analysis.

uncertainty quantification↗

NASA NTRS1989

Methods and decision making on a Mars rover for identification of fossils

A system for automated fusion and interpretation of image data from multiple sensors, including multispectral data from an imaging spectrometer is being developed. Classical artificial intelligence techniques and artificial neural networks are employed to make real time decision based on current input and known scientific goals. Emphasis is placed on identifying minerals which could indicate past life activity or an environment supportive of life. Multispectral data can be used for geological analysis because different minerals have characteristic spectral reflectance in the visible and near infrared range. Classification of each spectrum into a broad class, based on overall spectral shape and locations of absorption bands is possible in real time using artificial neural networks. The goal of the system is twofold: multisensor and multispectral data must be interpreted in real time so that potentially interesting sites can be flagged and investigated in more detail while the rover is near those sites; and the sensed data must be reduced to the most compact form possible without loss of crucial information. Autonomous decision making will allow a rover to achieve maximum scientific benefit from a mission. Both a classical rule based approach and a decision neural network for making real time choices are being considered. Neural nets may work well for adaptive decision making. A neural net can be trained to work in two steps. First, the actual input state is mapped to the closest of a number of memorized states. After weighing the importance of various input parameters, the net produces an output decision based on the matched memory state. Real time, autonomous image data analysis and decision making capabilities are required for achieving maximum scientific benefit from a rover mission. The system under development will enhance the chances of identifying fossils or environments capable of supporting life on Mars

Eberlein, Susan↗

NASA NTRS1997

Automation Bias and Countermeasures in Flight Crews

Results of recent research investigating the use of automated systems have indicated the presence of automation bias, a term describing errors made when decision makers rely on automated cues as a heuristic replacement for vigilant information seeking and processing. Automation commission errors, i.e., errors made when decision makers take inappropriate action because they over-attend to automated information or directives, and automation omission errors, i.e., errors made when decision makers do not take appropriate action because they are not informed of an imminent problem or situation by automated aids, can result from this tendency. In a series of studies, participants who perceived themselves as "accountable" for their strategies of interaction with automation were significantly more likely to verify its correct functioning, and committed significantly fewer automation-related errors than those who did not report this perception. In this study, we focus on two manipulations to encourage verification behaviors within cockpit crews. The first, an information/training manipulation, will focus on explicit information on automation bias, and training for verification of automated functioning. The second manipulation will consist of display prompts to verify automated functioning. Participants (glass-cockpit crews) will fly a series of approaches on the Mini-ACFS, a two-person pan-task flight simulator. Approach scenarios include several automation "events," that is, glitches, malfunctions, or inappropriate recommendations, that can be caught if cross-checked with other cockpit indicators. We anticipate that these manipulations will ameliorate automation bias. Final data analysis will be completed prior to the OSU symposium, and is expected to support the hypotheses that: a) reduced errors are associated with verification behaviors; b) crews will be more likely to verify under training/display conditions than when in the control condition; and c) effects will persist when subjects return for a follow-up exercise 6-9 weeks after their first session. Implications for training and automation design will be discussed.

Mosier, Kathleen, L.↗

NASA NTRS1977

Crop identification and area estimation over large geographic areas using LANDSAT MSS data

The author has identified the following significant results. LANDSAT MSS data was adequate to accurately identify wheat in Kansas; corn and soybean estimates in Indiana were less accurate. Computer-aided analysis techniques were effectively used to extract crop identification information from LANDSAT data. Systematic sampling of entire counties made possible by computer classification methods resulted in very precise area estimates at county, district, and state levels. Training statistics were successfully extended from one county to other counties having similar crops and soils if the training areas sampled the total variation of the area to be classified.

Bauer, M. E.↗

NASA NTRS1977

Remote sensing data processing - Two years ago, today, and two years from today

Certain technical problems arising in the recent past (1975) in the field of the processing of remote sensing data are reviewed including approaches to the analysis of Landsat MSS data and technical difficulties which must be overcome to achieve operational data processing. The current status of remote sensing data processing is then examined with emphasis on such current technical issues as training selection and labeling, sampling schemes and classification and mensuration. Hardware projections are made for the near future (1979) relative to the development of remote sensing data processing.

Holmes, Q. A.↗

NASA NTRS1980

Research in the application of spectral data to crop identification and assessment, volume 2

The development of spectrometry crop development stage models is discussed with emphasis on models for corn and soybeans. One photothermal and four thermal meteorological models are evaluated. Spectral data were investigated as a source of information for crop yield models. Intercepted solar radiation and soil productivity are identified as factors related to yield which can be estimated from spectral data. Several techniques for machine classification of remotely sensed data for crop inventory were evaluated. Early season estimation, training procedures, the relationship of scene characteristics to classification performance, and full frame classification methods were studied. The optimal level for combining area and yield estimates of corn and soybeans is assessed utilizing current technology: digital analysis of LANDSAT MSS data on sample segments to provide area estimates and regression models to provide yield estimates.

Daughtry, C. S. T.↗

NASA NTRS1979

Evaluation of SLAR and thematic mapper MSS data for forest cover mapping using computer-aided analysis techniques

The spatial characteristics of the data were evaluated. A program was developed to reduce the spatial distortions resulting from variable viewing distance, and geometrically adjusted data sets were generated. The potential need for some level of radiometric adjustment was evidenced by an along track band of high reflectance across different cover types in the Varian imagery. A multiple regression analysis was employed to explore the viewing angle effect on measured reflectance. Areas in the data set which appeared to have no across track stratification of cover type were identified. A program was developed which computed the average reflectance by column for each channel, over all of the scan lines in the designated areas. A regression analysis was then run using the first, second, and third degree polynomials, for each channel. An atmospheric effect as a component of the viewing angle source of variance is discussed. Cover type maps were completed and training and test field selection was initiated.

Hoffer, R. M.↗

NASA NTRS1989

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

Ali, Moonis↗

NASA NTRS2004

DASL-Data and Activities for Solar Learning

DASL-Data and Activities for Solar Learning Data and Activities for Solar Learning (DASL) provides a classroom learning environment based on a twenty-five year record of solar magnetograms from the National Solar Observatory (NSO) at Kitt Peak, AZ. The data, together with image processing software for Macs or PCs, can be used to learn basic facts about the Sun and astronomy at the middle school level. At the high school level, students can study properties of the Sun's magnetic cycle with classroom exercises emphasizing data and error analysis and can participate in a new scientific study, Research in Active Solar Longitudes (RASL), in collaboration with classrooms throughout the country and scientists at NSO and NASA. We present a half-day course to train teachers in the scientific content of the project and its classroom use. We will provide a compact disc with the data and software and will demonstrate software installation and use, classroom exercises, and participation in RASL with computer projection.

Jones, Harrison P.↗

NASA NTRS1994

Gear tooth topological modification

The topology of parallel axis gears, such as spur and helical gears is modified to produce quieter and more smoothly operating gear sets with more uniform load distribution. A finite element analysis of the gear in its operating mode is made to produce a plot of radial and tangential deflections of the pinion and gear tooth surfaces which will occur when the gears are loaded during operation. The resultant plot is then inverted to produce a plot, or set of coordinates, which will define the path of travel of the gear tooth grinding wheel, which path is a mirror image of the plot of the finite element analysis. The resulting gears, when subjected to operating loads, will thus be deflected tangentially and radially to their optimum operating, or theoretical true involute, positions so as to produce quieter, smoother, and more evenly loaded gear trains.

Kish, Jules G.↗

NASA NTRS2008

Automatic Rock Detection and Mapping from HiRISE Imagery

This system includes a C-code software program and a set of MATLAB software tools for statistical analysis and rock distribution mapping. The major functions include rock detection and rock detection validation. The rock detection code has been evolved into a production tool that can be used by engineers and geologists with minor training.

Huertas, Andres↗

NASA NTRS2009

Comparison of GOES Cloud Classification Algorithms Employing Explicit and Implicit Physics

Cloud-type classification based on multispectral satellite imagery data has been widely researched and demonstrated to be useful for distinguishing a variety of classes using a wide range of methods. The research described here is a comparison of the classifier output from two very different algorithms applied to Geostationary Operational Environmental Satellite (GOES) data over the course of one year. The first algorithm employs spectral channel thresholding and additional physically based tests. The second algorithm was developed through a supervised learning method with characteristic features of expertly labeled image samples used as training data for a 1-nearest-neighbor classification. The latter's ability to identify classes is also based in physics, but those relationships are embedded implicitly within the algorithm. A pixel-to-pixel comparison analysis was done for hourly daytime scenes within a region in the northeastern Pacific Ocean. Considerable agreement was found in this analysis, with many of the mismatches or disagreements providing insight to the strengths and limitations of each classifier. Depending upon user needs, a rule-based or other postprocessing system that combines the output from the two algorithms could provide the most reliable cloud-type classification.

EXPLICIT PHYSICS ALGORITHMS↗

NASA NTRS2018

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle S.↗

NASA NTRS2018

Supervised Learning Applied to Air Traffic Trajectory Classification

Bosson, Christabelle↗

NASA NTRSDate not supplied

Use of Design of Experiments and Rule-Based Inference in Determining Neural Network Architectures for Loss of Control Detection

In this work, we describe methods for selecting the neural network architectures and input spaces to implement belief state inference on generic commercial transport aircraft. First, we highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). We present a structured method that can be used in a number of aerospace applications, to optimize the structure and training parameters of the CVAE for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from a NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications. While theoretically, we could create a single CVAE with an input space the size of all measurable flight variables and environmental dynamics, it becomes intractable to use such a neural network in an in-situ intelligent multi-agent system. Using the recommendations from our case study, we introduce a technical approach for feasibly describing the belief space by (1) identifying significant statistical relationships among flight variables using rule induction, (2) using a set of rules that cover all features to define the input space of multiple CVAEs, and (3) forming a belief space based on the joint probability density of their collective latent spaces. This results in a series of relatively small matrix multiplications that can be performed in real time, as opposed to large matrix computations in a single CVAE. We demonstrate the application of this approach on the T-2 flight loss-of control experiments, using the architecture and hyperparameter recommendations from the case study. We compare the utilities of an individual CVAE trained on all flight variables and multiple CVAEs defined on subsets of flight variables for detecting qualitative changes in flight. We demonstrate that the use of multiple CVAEs with smaller input spaces permits the CVAE to capture more granular relationships in the latent space, permitting better state space characterization and loss-of-control detection.

Design of experiments↗