Search NASA⌕ Search

SEARCH · Search NASA

Results for “statistical inference”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1983

A design methodology for nonlinear systems containing parameter uncertainty

In the present design methodology for nonlinear systems containing parameter uncertainty, a generalized sensitivity analysis is incorporated which employs parameter space sampling and statistical inference. For the case of a system with j adjustable and k nonadjustable parameters, this methodology (which includes an adaptive random search strategy) is used to determine the combination of j adjustable parameter values which maximize the probability of those performance indices which simultaneously satisfy design criteria in spite of the uncertainty due to k nonadjustable parameters.

Young, G. E.↗
NASA NTRS1990

Cloud optical parameters as derived from the multispectral cloud radiometer

Simultaneous measurements of the liquid water content and particle size have assumed an important role in cloud physics as they help elucidate the mechanism of cloud particle formation and the mechanism of air mass-mixing in stratus clouds. Such measurements can reveal the modification of cloud air masses by anthropogenic aerosol particles (Coakley et al. 1987, Durkee 1989). Studies of the climatic impact of these modification processes on cloud microphysics seems to be urgent for understanding mechanisms of climate change. General Circulation Model (GCM) simulations can be improved by introducing a parameterization of cloud optical properties in terms of integrated liquid water content (liquid water path) and particle size (Slingo 1989). Motivated by the above mentioned circumstances, remote sensing techniques were developed for simultaneously retrieving the cloud optical thickness and effective particle radius, from which the liquid water path can be inferred. Statistical features of the cloud optical thickness (or liquid water path) and effective particle size for marine stratocumulus clouds are presented. These results were obtained during 4 days (7, 10, 13, and 16 July 1987) of observations with the Multispectral Cloud Radiometer (ER-2) and the Thematic Mapper (LANDSAT-5) during the First ISCCP Regional Experiment (FIRE).

Nakajima, Teruyuki↗
NASA NTRS1990

A computationally efficient model for turbulent droplet dispersion in spray combustion

A novel model for turbulent droplet dispersion is formulated having significantly improved computational efficiency in comparison to the conventional point source stochastic sampling methodology. In the proposed model, a computational parcel representing a group of physical particles is considered to have a normal (Gaussian) probability density function (PDF) in three-dimensional space. The mean of each PDF is determined by Lagrangian tracking of each computational parcel, either deterministically or stochastically. The variance is represented by a turbulence-induced mean squared dispersion which is based on statistical inferences from the linearized direct modeling formulation for particle/eddy interactions. Convolution of the computational parcel PDF's produces a single PDF for the physical particle distribution profile. The validity of the new model is established by comparison with the conventional stochastic sampling method, where in each parcel is represented by a delta function distribution, for non-evaporating particles injected into simple turbulent air flows.

Litchford, Ron J.↗
NASA NTRS1990

Is it possible to identify a trend in problem/failure data

One of the major obstacles in identifying and interpreting a trend is the small number of data points. Future trending reports will begin with 1983 data. As the problem/failure data are aggregated by year, there are just seven observations (1983 to 1989) for the 1990 reports. Any statistical inferences with a small amount of data will have a large degree of uncertainty. Consequently, a regression technique approach to identify a trend is limited. Though trend determination by failure mode may be unrealistic, the data may be explored for consistency or stability and the failure rate investigated. Various alternative data analysis procedures are briefly discussed. Techniques that could be used to explore problem/failure data by failure mode are addressed. The data used are taken from Section One, Space Shuttle Main Engine, of the Calspan Quarterly Report dated April 2, 1990.

Church, Curtis K.↗
NASA NTRS1991

Reliability growth models for NASA applications

The objective of any reliability growth study is prediction of reliability at some future instant. Another objective is statistical inference, estimation of reliability for reliability demonstration. A cause of concern for the development engineer and management is that reliability demands an excessive number of tests for reliability demonstration. For example, the Space Transportation Main Engine (STME) program requirements call for .99 reliability at 90 pct. confidence for demonstration. This requires running 230 tests with zero failure if a classical binomial model is used. It is therefore also an objective to explore the reliability growth models for reliability demonstration and tracking and their applicability to NASA programs. A reliability growth model is an analytical tool used to monitor the reliability progress during the development program and to establish a test plan to demonstrate an acceptable system reliability.

Taneja, Vidya S.↗
NASA NTRS1991

Rule groupings in expert systems using nearest neighbour decision rules, and convex hulls

Expert System shells are lacking in many areas of software engineering. Large rule based systems are not semantically comprehensible, difficult to debug, and impossible to modify or validate. Partitioning a set of rules found in CLIPS (C Language Integrated Production System) into groups of rules which reflect the underlying semantic subdomains of the problem, will address adequately the concerns stated above. Techniques are introduced to structure a CLIPS rule base into groups of rules that inherently have common semantic information. The concepts involved are imported from the field of A.I., Pattern Recognition, and Statistical Inference. Techniques focus on the areas of feature selection, classification, and a criteria of how 'good' the classification technique is, based on Bayesian Decision Theory. A variety of distance metrics are discussed for measuring the 'closeness' of CLIPS rules and various Nearest Neighbor classification algorithms are described based on the above metric.

Anastasiadis, Stergios↗
NASA NTRS1992

More rain compensation results

To reduce the impact of rain-induced attenuation in the 20/30 GHz band, the attenuation at a specified signal frequency must be estimated and extrapolated forward in time on the basis of a noisy beacon measurement. Several studies have used model based procedures for solving this problem in statistical inference. Perhaps the most widely used model-based paradigm leads to the Kalman filter and its lineal variants. In this formulation, the dynamic features of the attenuation are represented by a state process (x(sub t)). The observation process (y(sub t)) is derived from beacon measurements. Some ideas relating to the signal processing problems related to uplink power control are presented. It is shown that some easily implemented algorithms hold promise for use in estimating rain induced fades. The algorithms were applied to actual data generated at the Virginia Polytechnic Institute and State University (VPI) test facility. Because only one such event was studied, it is not clear that the algorithms will have the same effectiveness when a wide range of events are studied.

Sworder, D. D.↗
NASA NTRS1992

Statistical modeling of software reliability

This working paper discusses the statistical simulation part of a controlled software development experiment being conducted under the direction of the System Validation Methods Branch, Information Systems Division, NASA Langley Research Center. The experiment uses guidance and control software (GCS) aboard a fictitious planetary landing spacecraft: real-time control software operating on a transient mission. Software execution is simulated to study the statistical aspects of reliability and other failure characteristics of the software during development, testing, and random usage. Quantification of software reliability is a major goal. Various reliability concepts are discussed. Experiments are described for performing simulations and collecting appropriate simulated software performance and failure data. This data is then used to make statistical inferences about the quality of the software development and verification processes as well as inferences about the reliability of software versions and reliability growth under random testing and debugging.

Miller, Douglas R.↗
NASA NTRS1991

Maximum entropy method applied to deblurring images on a MasPar MP-1 computer

A statistical inference method based on the principle of maximum entropy is developed for the purpose of enhancing and restoring satellite images. The proposed maximum entropy image restoration method is shown to overcome the difficulties associated with image restoration and provide the smoothest and most appropriate solution consistent with the measured data. An implementation of the method on the MP-1 computer is described, and results of tests on simulated data are presented.

Bonavito, N. L.↗
NASA NTRS1993

A statistical analysis of mesoscale rainfall as a random cascade

The paper considers the random cascade theory for spatial rainfall. Particular attention was given to the following four areas: (1) the relationship of the random cascade theory of rainfall to the simple scaling and the hierarchical cluster-point-process theories, (2) the mathematical foundations for some of the formalisms commonly applied in the develpment of statistical cascade theory, (3) the empirical evidence for a random cascade theory of rainfall, and (4) the way of using data for making estimates of parameters and for making statistical inference within this theoretical framework. An analysis of space-time rainfall data is presented. Cascade simulations are carried out to provide a comparison with methods of analysis that are applied to the rainfall data.

Gupta, Vijay K.↗
NASA NTRS1992

Restoration of HST images with missing data

Missing data are a fairly common problem when restoring Hubble Space Telescope observations of extended sources. On Wide Field and Planetary Camera images cosmic ray hits and CCD hot spots are the prevalent causes of data losses, whereas on Faint Object Camera images data are lossed due to reseaux marks, blemishes, areas of saturation and the omnipresent frame edges. This contribution discusses a technique for 'filling in' missing data by statistical inference using information from the surrounding pixels. The major gain consists in minimizing adverse spill-over effects to the restoration in areas neighboring those where data are missing. When the mask delineating the support of 'missing data' is made dynamic, cosmic ray hits, etc. can be detected on the fly during restoration.

Adorf, Hans-Martin↗
NASA NTRS1994

Software for Data Analysis with Graphical Models

Probabilistic graphical models are being used widely in artificial intelligence and statistics, for instance, in diagnosis and expert systems, as a framework for representing and reasoning with probabilities and independencies. They come with corresponding algorithms for performing statistical inference. This offers a unifying framework for prototyping and/or generating data analysis algorithms from graphical specifications. This paper illustrates the framework with an example and then presents some basic techniques for the task: problem decomposition and the calculation of exact Bayes factors. Other tools already developed, such as automatic differentiation, Gibbs sampling, and use of the EM algorithm, make this a broad basis for the generation of data analysis software.

Buntine, Wray L.↗
NASA NTRS2010

Simulation of Micron-Sized Debris Populations in Low Earth Orbit

The update of ORDEM2000, the NASA Orbital Debris Engineering Model, to its new version ORDEM2010, is nearly complete. As a part of the ORDEM upgrade, this paper addresses the simulation of micro-debris (greater than 10 m and smaller than 1 mm in size) populations in low Earth orbit. The principal data used in the modeling of the micron-sized debris populations are in-situ hypervelocity impact records, accumulated in post-flight damage surveys on the space-exposed surfaces of returned spacecrafts. The development of the micro-debris model populations follows the general approach to deriving other ORDEM2010-required input populations for various components and types of debris. This paper describes the key elements and major steps in the statistical inference of the ORDEM2010 micro-debris populations. A crucial step is the construction of a degradation/ejecta source model to provide prior information on the micron-sized objects (such as orbital and object-size distributions). Another critical step is to link model populations with data, which is rather involved. It demands detailed information on area-time/directionality for all the space-exposed elements of a shuttle orbiter and damage laws, which relate impact damage with the physical properties of a projectile and impact conditions such as impact angle and velocity. Also needed are model-predicted debris fluxes as a function of object size and impact velocity from all possible directions. In spite of the very limited quantity of the available shuttle impact data, the population-derivation process is satisfactorily stable. Final modeling results obtained from shuttle window and radiator impact data are reasonably convergent and consistent, especially for the debris populations with object-size thresholds at 10 and 100 m.

Xu, Y.-L.↗
NASA NTRS2010

Simulation of Micron-Sized Debris Populations in Low Earth Orbit

The update of ORDEM2000, the NASA Orbital Debris Engineering Model, to its new version . ORDEM2010, is nearly complete. As a part of the ORDEM upgrade, this paper addresses the simulation of micro-debris (greater than 10 micron and smaller than 1 mm in size) populations in low Earth orbit. The principal data used in the modeling of the micron-sized debris populations are in-situ hypervelocity impact records, accumulated in post-flight damage surveys on the space-exposed surfaces of returned spacecrafts. The development of the micro-debris model populations follows the general approach to deriving other ORDEM2010-required input populations for various components and types of debris. This paper describes the key elements and major steps in the statistical inference of the ORDEM2010 micro-debris populations. A crucial step is the construction of a degradation/ejecta source model to provide prior information on the micron-sized objects (such as orbital and object-size distributions). Another critical step is to link model populations with data, which is rather involved. It demands detailed information on area-time/directionality for all the space-exposed elements of a shuttle orbiter and damage laws, which relate impact damage with the physical properties of a projectile and impact conditions such as impact angle and velocity. Also needed are model-predicted debris fluxes as a function of object size and impact velocity from all possible directions. In spite of the very limited quantity of the available shuttle impact data, the population-derivation process is satisfactorily stable. Final modeling results obtained from shuttle window and radiator impact data are reasonably convergent and consistent, especially for the debris populations with object-size thresholds at 10 and 100 micron.

Xu, Y.-L.↗
NASA NTRS2015

Advanced Bayesian Method for Planetary Surface Navigation

Autonomous Exploration, Inc., has developed an advanced Bayesian statistical inference method that leverages current computing technology to produce a highly accurate surface navigation system. The method combines dense stereo vision and high-speed optical flow to implement visual odometry (VO) to track faster rover movements. The Bayesian VO technique improves performance by using all image information rather than corner features only. The method determines what can be learned from each image pixel and weighs the information accordingly. This capability improves performance in shadowed areas that yield only low-contrast images. The error characteristics of the visual processing are complementary to those of a low-cost inertial measurement unit (IMU), so the combination of the two capabilities provides highly accurate navigation. The method increases NASA mission productivity by enabling faster rover speed and accuracy. On Earth, the technology will permit operation of robots and autonomous vehicles in areas where the Global Positioning System (GPS) is degraded or unavailable.

Center, Julian↗
NASA NTRS2020

Conditions of Loss Cone Filling by Scattering on the Curved Field Lines for 30 keV Protons During Geomagnetic Storm as Inferred From Numerical Trajectory Tracing

The rate of pitch angle scattering on the curved magnetic field lines is well parameterized by the ratio of the minimum field line curvature radius to the maximum effective particle gyroradius (K = RC/rg). The critical value of this ratio (Kcr) corresponding to the loss cone filling is of special interest since it corresponds to the low altitude isotropic boundaries (IBs). The early theoretical estimates gave Kcr = 8, whereas recent estimations of the K parameter on the field lines corresponding to the observed IBs during the geomagnetic storms revealed KIB values in the range of 3–30. We numerically trace the trajectories of the 30 keV protons in the magnetic field of the global magnetohydrodynamic simulation of the intense storm in order to infer statistical distribution of Kcr. The electric field and effects of nonstationarity are neglected in this study. It is found that although the Kcr values do show some variations during the course of the storm, its range is rather narrow 4 < Kcr < 8. The result suggests that higher KIB values found in the observational studies, if not caused by the magnetosphere-ionosphere mapping error, should be attributed to some other mechanism of pitch angle scattering. The Kcr values tend to be lower (4–6) during the main phase because the region of low K values approaches the Earth and the equatorial loss cone size becomes larger due to a larger equatorial magnetic field in the near earth region. The remaining variation of Kcr is explained by the presence of the guide component of the magnetic field.

S Dubyagin↗
NASA NTRS2013

Monte Carlo Bayesian Inference on a Statistical Model of Sub-gridcolumn Moisture Variability Using High-resolution Cloud Observations : Sensitivity Tests and Results - Part II

Part I presented a Monte Carlo Bayesian method for constraining a complex statistical model of GCM sub-gridcolumn moisture variability using high-resolution MODIS cloud data, thereby permitting large-scale model parameter estimation and cloud data assimilation. This part performs some basic testing of this new approach, verifying that it does indeed significantly reduce mean and standard deviation biases with respect to the assimilated MODIS cloud optical depth, brightness temperature and cloud top pressure, and that it also improves the simulated rotational-Ramman scattering cloud optical centroid pressure (OCP) against independent (non-assimilated) retrievals from the OMI instrument. Of particular interest, the Monte Carlo method does show skill in the especially difficult case where the background state is clear but cloudy observations exist. In traditional linearized data assimilation methods, a subsaturated background cannot produce clouds via any infinitesimal equilibrium perturbation, but the Monte Carlo approach allows finite jumps into regions of non-zero cloud probability. In the example provided, the method is able to restore marine stratocumulus near the Californian coast where the background state has a clear swath. This paper also examines a number of algorithmic and physical sensitivities of the new method and provides guidance for its cost-effective implementation. One obvious difficulty for the method, and other cloud data assimilation methods as well, is the lack of information content in the cloud observables on cloud vertical structure, beyond cloud top pressure and optical thickness, thus necessitating strong dependence on the background vertical moisture structure. It is found that a simple flow-dependent correlation modification due to Riishojgaard (1998) provides some help in this respect, by better honoring inversion structures in the background state.

Monte Carlo Bayesian inference↗