SEARCH · Engineering Papers

Results for “learning algorithms”

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 865 records · Page 48

All sources NASA NTRS DOE OSTI

NASA NTRS1992

Efficient dynamic optimization of logic programs

A summary is given of the dynamic optimization approach to speed up learning for logic programs. The problem is to restructure a recursive program into an equivalent program whose expected performance is optimal for an unknown but fixed population of problem instances. We define the term 'optimal' relative to the source of input instances and sketch an algorithm that can come within a logarithmic factor of optimal with high probability. Finally, we show that finding high-utility unfolding operations (such as EBG) can be reduced to clause reordering.

Laird, Phil↗

NASA NTRS2006

Implementing Scientific Simulation Codes Highly Tailored for Vector Architectures Using Custom Configurable Computing Machines

The motivation for this work comes from an observation that amidst the push for Massively Parallel (MP) solutions to high-end computing problems such as numerical physical simulations, large amounts of legacy code exist that are highly optimized for vector supercomputers. Because re-hosting legacy code often requires a complete re-write of the original code, which can be a very long and expensive effort, this work examines the potential to exploit reconfigurable computing machines in place of a vector supercomputer to implement an essentially unmodified legacy source code. Custom and reconfigurable computing resources could be used to emulate an original application's target platform to the extent required to achieve high performance. To arrive at an architecture that delivers the desired performance subject to limited resources involves solving a multi-variable optimization problem with constraints. Prior research in the area of reconfigurable computing has demonstrated that designing an optimum hardware implementation of a given application under hardware resource constraints is an NP-complete problem. The premise of the approach is that the general issue of applying reconfigurable computing resources to the implementation of an application, maximizing the performance of the computation subject to physical resource constraints, can be made a tractable problem by assuming a computational paradigm, such as vector processing. This research contributes a formulation of the problem and a methodology to design a reconfigurable vector processing implementation of a given application that satisfies a performance metric. A generic, parametric, architectural framework for vector processing implemented in reconfigurable logic is developed as a target for a scheduling/mapping algorithm that maps an input computation to a given instance of the architecture. This algorithm is integrated with an optimization framework to arrive at a specification of the architecture parameters that attempts to minimize execution time, while staying within resource constraints. The flexibility of using a custom reconfigurable implementation is exploited in a unique manner to leverage the lessons learned in vector supercomputer development. The vector processing framework is tailored to the application, with variable parameters that are fixed in traditional vector processing. Benchmark data that demonstrates the functionality and utility of the approach is presented. The benchmark data includes an identified bottleneck in a real case study example vector code, the NASA Langley Terminal Area Simulation System (TASS) application.

Rutishauser, David↗

NASA NTRS2007

Sensor On-orbit Calibration and Characterization Using Spacecraft Maneuvers

Spacecraft flight operations often require activities that involve different kinds of maneuvers for orbital adjustments (pitch, yaw, and roll). Different maneuvers, when properly planned and scheduled, can also be applied to support and/or to perform on-board sensor calibration and characterization. This paper uses MODIS (Moderate Resolution Imaging Spectroradiometer) as an example to illustrate applications of spacecraft maneuvers for Earth-observing sensors on-orbit calibration and characterization. MODIS is one of the key instruments for NASA's Earth Observing System (EOS) currently operated on-board the EOS Terra and Aqua spacecraft launched in December 1999 and May 2002, respectively. Since their launch, both Terra and Aqua spacecraft have made a number of maneuvers, specially the yaw and roll maneuvers, to support the MODIS on-orbit calibration and characterization. For both Terra and Aqua MODIS, near-monthly spacecraft roll maneuvers are executed for lunar observations. These maneuvers are carefully scheduled so that the lunar phase angles are nearly identical for each sensor's lunar observations. The lunar observations are used to track MODIS reflective solar bands (RSB) calibration stability and to inter-compare Terra and Aqua MODIS RSB calibration consistency. To date, two sets of yaw maneuvers (each consists of two series of 8 consecutive yaws) by the Terra spacecraft and one set by the Aqua spacecraft have been performed to validate MODIS solar diffuser (SD) bi-directional reflectance factor (BRF) and to derive SD screen transmission. Terra spacecraft pitch maneuvers, first made on March 26, 2003 and the second on April 14, 2003 (with the Moon in the spacecraft nadir view), have been applied to characterize MODIS thermal emissive bands (TEB) response versus scan angle (RVS). This is particularly important since the pre-launch TEB RSV measurements made by the sensor vendor were not successful. Terra MODIS TEB RVS obtained from pitch maneuvers have been used in the current LIB calibration algorithm. Lunq observations from pitch maneuvers also provided information to cross-calibrate MODIS with other sensors (MISR and ASTER) on the same platform. We will provide a summary of MODIS maneuver activities and their applications for MODIS calibration and characterization. The results and lessons learned discussed in this paper from MODIS maneuver activities will provide useful insights into future spacecraft and sensor operation.

Xiong, X.↗

NASA NTRS2022

A New Machine Learning Based Analysis for Improving Satellite Retrieved Atmospheric Composition Data: OMI SO2 as an Example

Despite recent progress, satellite retrievals of anthropogenic SO2 still suffer from relatively low signal-tonoise ratios. In this study, we demonstrate a new machine learning data analysis method to improve the quality of satellite SO2 products. In the absence of large ground-truth datasets for SO2, we start from SO2 slant column densities (SCDs) retrieved from the Ozone Monitoring Instrument (OMI) using a data-driven, physically based algorithm and calculate the ratio between the SCD and the root mean square (rms) of the fitting residuals for each pixel. To build the training data, we select presumably clean pixels with small SCD / rms ratios (SRRs) and set their target SCDs to zero. For polluted pixels with relatively large SRRs, we set the target to the original retrieved SCDs. We then train neural networks (NNs) to reproduce the target SCDs using predictors including SRRs for individual pixels, solar zenith, viewing zenith and phase angles, scene reflectivity, and O3 column amounts, as well as the monthly mean SRRs. For data analysis, we employ two NNs: (1) one trained daily to produce analyzed SO2 SCDs for polluted pixels each day and (2) the other trained once every month to produce analyzed SCDs for less polluted pixels for the entire month. Test results for 2005 show that our method can significantly reduce noise and artifacts over background regions. Over polluted areas, the monthly mean NN-analyzed and original SCDs generally agree to within ±15 %, indicating that our method can retain SO2 signals in the original retrievals except for large volcanic eruptions. This is further confirmed by running both the NN-analyzed and original SCDs through a topdown emission algorithm to estimate the annual SO2 emissions for ∼ 500 anthropogenic sources, with the two datasets yielding similar results. We also explore two alternative approaches to the NN-based analysis method. In one, we employ a simple linear interpolation model to analyze the original SCD retrievals. In the other, we develop a PCA–NN algorithm that uses OMI measured radiances, transformed and dimension-reduced with a principal component analysis (PCA) technique, as inputs to NNs for SO2 SCD retrievals. While the linear model and the PCA–NN algorithm can reduce retrieval noise, they both underestimate SO2 over polluted areas. Overall, the results presented here demonstrate that our new data analysis method can significantly improve the quality of existing OMI SO2 retrievals. The method can potentially be adapted for other sensors and/or species and enhance the value of satellite data in air quality research and applications.

Can Li↗

NASA NTRS1992

A multilayer perceptron solution to the match phase problem in rule-based artificial intelligence systems

In rule-based AI planning, expert, and learning systems, it is often the case that the left-hand-sides of the rules must be repeatedly compared to the contents of some 'working memory'. The traditional approach to solve such a 'match phase problem' for production systems is to use the Rete Match Algorithm. Here, a new technique using a multilayer perceptron, a particular artificial neural network model, is presented to solve the match phase problem for rule-based AI systems. A syntax for premise formulas (i.e., the left-hand-sides of the rules) is defined, and working memory is specified. From this, it is shown how to construct a multilayer perceptron that finds all of the rules which can be executed for the current situation in working memory. The complexity of the constructed multilayer perceptron is derived in terms of the maximum number of nodes and the required number of layers. A method for reducing the number of layers to at most three is also presented.

Sartori, Michael A.↗

NASA NTRS2008

Towards Intelligent Control for Next Generation Aircraft

NASA Aeronautics Subsonic Fixed Wing Project is focused on mitigating the environmental and operation impacts expected as aviation operations triple by 2025. The approach is to extend technological capabilities and explore novel civil transport configurations that reduce noise, emissions, fuel consumption and field length. Two Next Generation (NextGen) aircraft have been identified to meet the Subsonic Fixed Wing Project goals - these are the Hybrid Wing-Body (HWB) and Cruise Efficient Short Take-Off and Landing (CESTOL) aircraft. The technologies and concepts developed for these aircraft complicate the vehicle s design and operation. In this paper, flight control challenges for NextGen aircraft are described. The objective of this paper is to examine the potential of state-of-the-art control architectures and algorithms to meet the challenges and needed performance metrics for NextGen flight control. A broad range of conventional and intelligent control approaches are considered, including dynamic inversion control, integrated flight-propulsion control, control allocation, adaptive dynamic inversion control, data-based predictive control and reinforcement learning control.

Acosta, Diana Michelle↗

NASA NTRSDate not supplied

Statistical Classification of Biosignature Information: Combining Elemental, Molecular, Reflectance, and Raman Data to Increase Life Detection Confidence

Planetary exploration missions seeking past or present signs of life carry not just a single instrument, but a suite. There is a need to study how these multiple data types can be combined to create “composite” biosignatures [1]. Algorithmic methods using existing data on living and non-living systems, though limited by the n = 1 of Earth, can nonetheless be informative. We assembled a database of 1277 measurements spanning 16 representative systems either indicative or non-indicative of life. Five classification (machine learning) methods were used on each individual data type, then on the entire set. This abstract summarizes the results; the data is described in more detail in [2], and methods in [3].

Biosignatures↗

NASA NTRS2013

NASA Computational Case Study SAR Data Processing: Ground-Range Projection

Radar technology is used extensively by NASA for remote sensing of the Earth and other Planetary bodies. In this case study, we learn about different computational concepts for processing radar data. In particular, we learn how to correct a slanted radar image by projecting it on the surface that was sensed by a radar instrument.

Synthetic Aperture Radar (SAR)↗

NASA NTRS2020

Terra MODIS: 20 years of on-orbit calibration and performance

Since its launch in December 1999, Terra Moderate Resolution Imaging Spectroradiometer (MODIS) has successfully operated for more than 20 years, with its observations generating a broad range of science data products that have greatly enabled the remote sensing community and users worldwide in their studies of many key geophysical parameters of the Earth’s systems. MODIS collects data in 36 spectral bands, covering wavelengths from 0.41 to 14.4 μm, which are calibrated by a set of onboard calibrators (OBCs). Also contributing to the sensor’s mission-long on-orbit calibration and characterization are near-monthly scheduled lunar observations and multiple time series of the sensor’s responses over select ground targets at a variety of scan angles. To a large extent, the quality of MODIS data products relies strongly on the dedicated efforts to operate and calibrate the instrument, to derive and update calibration parameters, and to develop and implement new calibration strategies and algorithms in response to on-orbit changes of the sensor’s characteristics and its OBC functions. We provide an overview of the Terra MODIS on-orbit operation and calibration activities over the last 20 years, including changes made to extend and preserve the instrument and OBC functions and their operation strategies. It also illustrates the sensor’s on-orbit performance with results derived from its OBC, lunar observations, and select ground targets and discusses major changes in sensor characteristics and corrections applied to the L1B algorithms as well as calibration lookup table updates. To date, the Terra MODIS instrument and its OBCs continue to operate and function normally. Except for those identified prelaunch, most spectral bands and detectors continue to meet their specified calibration requirements. Also discussed in our paper are lessons learned from Terra MODIS operation and calibration, as well as future efforts to further extend and maintain the quality of its long-term data records.

Terra↗

NASA NTRSDate not supplied

Space Flown Rodent Liver RNA Sequencing Data for Machine Learning in Space Biology Research

High-throughput nucleic acid sequencing (DNA-seq, RNA-seq) has become widespread in biomedical research due to the growing availability and affordability of these assays. Data analysis has been accelerated in recent years by the adoption of artificial intelligence (AI) and machine learning (ML) techniques by biomedical researchers. In space biology research, RNAseq datasets from space-flown experimental samples are critical for characterizing the gene expression aberrations associated with exposure to spaceflight stressors. However, space biological experiments tend to be very low sample size, so identifying proper AI/ML algorithms for sequencing data analysis is an ongoing challenge since these algorithms typically require large sample size. The NASA Science Mission Directorate (SMD) has started the “Benchmark Initiative for AI/ML”, focused on creating datasets meant for three main applications: 1) scientific benchmarking, which finds the best algorithm for a specific problem; 2) application benchmarking, which measures algorithm performance against a set of parameters; and 3) system benchmarking, which evaluates performance of hardware and software architecture. These scientific benchmarks consist of an AI-ready dataset and a reference implementation on a specific scientific question. In this work, we focused on generating standardized datasets to allow the scientific community to benchmark AI/ML algorithms in the domain of space biology. We present here a standardized, AI-ready, publicly available benchmark dataset for space biology RNA-seq data as a collaboration between the NASA AI4LS (Artificial Intelligence for Life Sciences) working group. and NASA’s SMD. This dataset consists of space-flown and ground control mouse liver found in the NASA GeneLab omics database. However, to amplify the small sample number (n=112 samples) for ML purposes, we employ Gaussian noise and a generative adversarial network to extend this dataset to 6,000 synthetic samples, matching the original gene expression characteristics.

James Casaletto↗

NASA NTRS2022

Verification and Validation of Hybridspectral Radiometry Obtained from an Unmanned Surface Vessel (USV) in the Open and Coastal Oceans

The hardware and software capabilities of the compact-profiling hybrid instrumentation for radiometry and ecology (C-PHIRE) instruments on an unmanned surface vessel (USV) are evaluated. Both the radiometers and USV are commercial-off-the-shelf (COTS) products, with the latter being only minimally modified to deploy the C-PHIRE instruments. The hybridspectral C-PHIRE instruments consist of an array of 18 multispectral microradiometers with 10 nm wavebands spanning 320–875 nm plus a hyperspectral compact grating spectrometer (CGS) with 2048 pixels spanning 190–1000 nm. The C-PHIRE data were acquired and processed using two architecturally linked software packages, thereby allowing lessons learned in one to be applied to the other. Using standard data products and unbiased statistics, the C-PHIRE data were validated with those from the well-established compact-optical profiling system (C-OPS) and verified with the marine optical buoy (MOBY). Agreement between algorithm variables used to estimate colored dissolved organic matter (CDOM) absorption and chlorophyll a concentration were also validated. Developing and operating novel technologies, such as the C-PHIRE series of instruments, deployed on a USV increase the frequency and coverage of optical observations, which are required to fully support the present and next-generation validation exercises in radiometric remote sensing of aquatic ecosystems.

Hybridspectral↗

NASA NTRS1994

Automated rule-base creation via CLIPS-Induce

Many CLIPS rule-bases contain one or more rule groups that perform classification. In this paper we describe CLIPS-Induce, an automated system for the creation of a CLIPS classification rule-base from a set of test cases. CLIPS-Induce consists of two components, a decision tree induction component and a CLIPS production extraction component. ID3, a popular decision tree induction algorithm, is used to induce a decision tree from the test cases. CLIPS production extraction is accomplished through a top-down traversal of the decision tree. Nodes of the tree are used to construct query rules, and branches of the tree are used to construct classification rules. The learned CLIPS productions may easily be incorporated into a large CLIPS system that perform tasks such as accessing a database or displaying information.

Murphy, Patrick M.↗

NASA NTRS2012

Development of an OSSE Framework for a Global Atmospheric Data Assimilation System

Observing system simulation experiments (OSSEs) are powerful tools for estimating the usefulness of various configurations of envisioned observing systems and data assimilation techniques. Their utility stems from their being conducted in an entirely simulated context, utilizing simulated observations having simulated errors and drawn from a simulation of the earth's environment. Observations are generated by applying physically based algorithms to the simulated state, such as performed during data assimilation or using other appropriate algorithms. Adding realistic instrument plus representativeness errors, including their biases and correlations, can be critical for obtaining realistic assessments of the impact of a proposed observing system or analysis technique. If estimates of the expected accuracy of proposed observations are realistic, then the OSSE can be also used to learn how best to utilize the new information, accelerating its transition to operations once the real data are available. As with any inferences from simulations, however, it is first imperative that some baseline OSSEs are performed and well validated against corresponding results obtained with a real observing system. This talk provides an overview of, and highlights critical issues related to, the development of an OSSE framework for the tropospheric weather prediction component of the NASA GEOS-5 global atmospheric data assimilation system. The framework includes all existing observations having significant impact on short-term forecast skill. Its validity has been carefully assessed using a range of metrics that can be evaluated in both the OSSE and real contexts, including adjoint-based estimates of observation impact. A preliminary application to the Aeolus Doppler wind lidar mission, scheduled for launch by the European Space Agency in 2014, has also been investigated.

Gelaro, Ronald↗

NASA NTRS2015

Flight Testing of Guidance, Navigation and Control Systems on the Mighty Eagle Robotic Lander Testbed

During 2011 a series of progressively more challenging flight tests of the Mighty Eagle autonomous terrestrial lander testbed were conducted primarily to validate the GNC system for a proposed lunar lander. With the successful completion of this GNC validation objective the opportunity existed to utilize the Mighty Eagle as a flying testbed for a variety of technologies. In 2012 an Autonomous Rendezvous and Capture (AR&C) algorithm was implemented in flight software and demonstrated in a series of flight tests. In 2012 a hazard avoidance system was developed and flight tested on the Mighty Eagle. Additionally, GNC algorithms from Moon Express and a MEMs IMU were tested in 2012. All of the testing described herein was above and beyond the original charter for the Mighty Eagle. In addition to being an excellent testbed for a wide variety of systems the Mighty Eagle also provided a great learning opportunity for many engineers and technicians to work a flight program.

Hannan, Mike↗

NASA NTRS2024

Noise Reduction for Solar-Induced Fluorescence Retrievals Using Machine Learning and Principal Component Analysis: Simulations and Applications to GOME-2 Satellite Retrievals

We use a spectral-based approach that employs principal component analysis along with a relatively shallow artificial neural network (NN) to substantially reduce noise and other artifacts in terrestrial chlorophyll solar-induced fluorescence (SIF) retrievals. SIF is a very small emission at red and far-red wavelengths that is difficult to measure and is highly sensitive to random errors and systematic artifacts. Our approach relies upon an assumption that a trained NN can effectively reconstruct the total SIF signal from a relatively small number of leading principal components of the satellite-observed far-red radiance spectra without using information from the trailing modes that contain most of the random errors. We test the approach with simulated reflectance spectra produced with a full atmospheric and surface radiative transfer model using different observing and geophysical parameters and various noise levels. Resulting noisy and noise-reduced retrieved SIF values are compared with true values to assess performance. We then apply our noise reduction approach to SIF derived from two different satellite spectrometers. For evaluation, since the truth in this case is unknown, we compare SIF retrievals from two independent sensors with each other. We also compare the noise-reduced SIF temporal variations with those from an independent gross primary product (GPP) product that should display similar variations. Results show that our noise reduction approach improves capture of SIF seasonal and inter-annual variability. Our approach should be applicable to many noisy data products derived from spectral measurements. Our methodology does not replace the original retrieval algorithms; rather the original noisy retrievals are needed as the target for the NN training process.

noise reduction, solar-induced fluorescence, SIF, ↗

NASA NTRS2003

Lessons Learned from using a Livingstone Model to Diagnose a Main Propulsion System

NASA researchers have demonstrated that qualitative, model-based reasoning can be used for fault detection in a Main Propulsion System (MPS), a complex, continuous system. At the heart of this diagnostic system is Livingstone, a discrete, propositional logic-based inference engine. Livingstone comprises a language for specifying a discrete model of the system and a set of algorithms that use the model to track the system's state. Livingstone uses the model to test assumptions about the state of a component - observations from the system are compared with values predicted by the model. The intent of this paper is to summarize some advantages of Livingstone seen through our modeling experience: for instance, flexibility in modeling, speed and maturity. We also describe some shortcomings we perceived in the implementation of Livingstone, such as modeling continuous dynamics and handling of transients. We list some upcoming enhancements to the next version of Livingstone that may resolve some of the current limitations.

Sweet, Adam↗

NASA NTRS2004

Cloud Detection from Satellite Imagery: A Comparison of Expert-Generated and Automatically-Generated Decision Trees

Automated cloud detection and tracking is an important step in assessing global climate change via remote sensing. Cloud masks, which indicate whether individual pixels depict clouds, are included in many of the data products that are based on data acquired on- board earth satellites. Many cloud-mask algorithms have the form of decision trees, which employ sequential tests that scientists designed based on empirical astrophysics studies and astrophysics simulations. Limitations of existing cloud masks restrict our ability to accurately track changes in cloud patterns over time. In this study we explored the potential benefits of automatically-learned decision trees for detecting clouds from images acquired using the Advanced Very High Resolution Radiometer (AVHRR) instrument on board the NOAA-14 weather satellite of the National Oceanic and Atmospheric Administration. We constructed three decision trees for a sample of 8km-daily AVHRR data from 2000 using a decision-tree learning procedure provided within MATLAB(R), and compared the accuracy of the decision trees to the accuracy of the cloud mask. We used ground observations collected by the National Aeronautics and Space Administration Clouds and the Earth s Radiant Energy Systems S COOL project as the gold standard. For the sample data, the accuracy of automatically learned decision trees was greater than the accuracy of the cloud masks included in the AVHRR data product.

Shiffman, Smadar↗

NASA NTRS2016

Exploration Clinical Decision Support System: Medical Data Architecture

The Exploration Clinical Decision Support (ECDS) System project is intended to enhance the Exploration Medical Capability (ExMC) Element for extended duration, deep-space mission planning in HRP. A major development guideline is the Risk of "Adverse Health Outcomes & Decrements in Performance due to Limitations of In-flight Medical Conditions". ECDS attempts to mitigate that Risk by providing crew-specific health information, actionable insight, crew guidance and advice based on computational algorithmic analysis. The availability of inflight health diagnostic computational methods has been identified as an essential capability for human exploration missions. Inflight electronic health data sources are often heterogeneous, and thus may be isolated or not examined as an aggregate whole. The ECDS System objective provides both a data architecture that collects and manages disparate health data, and an active knowledge system that analyzes health evidence to deliver case-specific advice. A single, cohesive space-ready decision support capability that considers all exploration clinical measurements is not commercially available at present. Hence, this Task is a newly coordinated development effort by which ECDS and its supporting data infrastructure will demonstrate the feasibility of intelligent data mining and predictive modeling as a biomedical diagnostic support mechanism on manned exploration missions. The initial step towards ground and flight demonstrations has been the research and development of both image and clinical text-based computer-aided patient diagnosis. Human anatomical images displaying abnormal/pathological features have been annotated using controlled terminology templates, marked-up, and then stored in compliance with the AIM standard. These images have been filtered and disease characterized based on machine learning of semantic and quantitative feature vectors. The next phase will evaluate disease treatment response via quantitative linear dimension biomarkers that enable image content-based retrieval and criteria assessment. In addition, a data mining engine (DME) is applied to cross-sectional adult surveys for predicting occurrence of renal calculi, ranked by statistical significance of demographics and specific food ingestion. In addition to this precursor space flight algorithm training, the DME will utilize a feature-engineering capability for unstructured clinical text classification health discovery. The ECDS backbone is a proposed multi-tier modular architecture providing data messaging protocols, storage, management and real-time patient data access. Technology demonstrations and success metrics will be finalized in FY16.

Biomedical support↗