Search NASA⌕ Search

SEARCH · Search NASA

Results for “Maximum likelihood estimation (MLE)”

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.

32 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Maximum likelihood techniques applied to quasi-elastic light scattering

There is a necessity of having an automatic procedure for reliable estimation of the quality of the measurement of particle size from QELS (Quasi-Elastic Light Scattering). Getting the measurement itself, before any error estimates can be made, is a problem because it is obtained by a very indirect measurement of a signal derived from the motion of particles in the system and requires the solution of an inverse problem. The eigenvalue structure of the transform that generates the signal is such that an arbitrarily small amount of noise can obliterate parts of any practical inversion spectrum. This project uses the Maximum Likelihood Estimation (MLE) as a framework to generate a theory and a functioning set of software to oversee the measurement process and extract the particle size information, while at the same time providing error estimates for those measurements. The theory involved verifying a correct form of the covariance matrix for the noise on the measurement and then estimating particle size parameters using a modified histogram approach.

Edwards, Robert V.↗
NASA NTRS1997

Biweekly Maps of Wind Stress for the North Pacific from the ERS-1 Scatterometer

The European Remote-sensing Satellite (ERS-1) was launched in July 1991 and contained several instruments for observing the Earth's ocean including a wind scatterometer. The scatterometer measurements were processed by the European Space Agency (ESA) and the Jet Propulsion Laboratory (JPL). JPL reprocessed (Freilich and Dunbar, 1992) the ERS-1 backscatter measurements to produced a 'value added' data set that contained the ESA wind vector as well as a set of up to four ambiguities. These ambiguities were further processed using a maximum-likelihood estimation (MLE) and a median filter to produce a 'selected vector.' This report describes a technique developed to produce time-averaged wind field estimates with their expected errors using only scatterometer wind vectors. The processing described in this report involved extracting regions of interest from the data tapes, checking the quality and creating the wind field estimate. This analysis also includes the derivation of biweekly average wind vectors over the North Pacific Ocean at a resolution of 0.50 x 0.50. This was done with an optimal average algorithm temporally and an over-determined biharmonic spline spatially. There have been other attempts at creating gridded wind files from ERS-1 winds, e.g., kriging techniques (Bentamy et al., 1996) and successive corrections schemes (Tang and Liu, 1996). There are several inherent problems with the ERS-1 scatterometer. Since this is a multidisciplinary mission, the satellite is flown in different orbits optimized for each phase of the mission. The scatterometer also shares several sub-systems with the Synthetic Aperture Radar (SAR) and cannot be operated while the SAR is in operation. The scatterometer is also a single-sided instrument and only measures backscatter along the right side of the satellite. The processing described here generates biweekly wind maps during the wktwo years analysis period regardless of the satellite orbit or missing data.

SYNTHETIC APERTURE RADAR↗
NASA NTRS1995

Reliability Stress-Strength Models for Dependent Observations with Applications in Clinical Trials

We consider the applications of stress-strength models in studies involving clinical trials. When studying the effects and side effects of certain procedures (treatments), it is often the case that observations are correlated due to subject effect, repeated measurements and observing many characteristics simultaneously. We develop maximum likelihood estimator (MLE) and uniform minimum variance unbiased estimator (UMVUE) of the reliability which in clinical trial studies could be considered as the chances of increased side effects due to a particular procedure compared to another. The results developed apply to both univariate and multivariate situations. Also, for the univariate situations we develop simple to use lower confidence bounds for the reliability. Further, we consider the cases when both stress and strength constitute time dependent processes. We define the future reliability and obtain methods of constructing lower confidence bounds for this reliability. Finally, we conduct simulation studies to evaluate all the procedures developed and also to compare the MLE and the UMVUE.

Kushary, Debashis↗
NASA NTRS2005

Statistical Considerations of Data Processing in Giovanni Online Tool

The GES DISC Interactive Online Visualization and Analysis Infrastructure (Giovanni) is a web-based interface for the rapid visualization and analysis of gridded data from a number of remote sensing instruments. The GES DISC currently employs several Giovanni instances to analyze various products, such as Ocean-Giovanni for ocean products from SeaWiFS and MODIS-Aqua; TOMS & OM1 Giovanni for atmospheric chemical trace gases from TOMS and OMI, and MOVAS for aerosols from MODIS, etc. (http://giovanni.gsfc.nasa.gov) Foremost among the Giovanni statistical functions is data averaging. Two aspects of this function are addressed here. The first deals with the accuracy of averaging gridded mapped products vs. averaging from the ungridded Level 2 data. Some mapped products contain mean values only; others contain additional statistics, such as number of pixels (NP) for each grid, standard deviation, etc. Since NP varies spatially and temporally, averaging with or without weighting by NP will be different. In this paper, we address differences of various weighting algorithms for some datasets utilized in Giovanni. The second aspect is related to different averaging methods affecting data quality and interpretation for data with non-normal distribution. The present study demonstrates results of different spatial averaging methods using gridded SeaWiFS Level 3 mapped monthly chlorophyll a data. Spatial averages were calculated using three different methods: arithmetic mean (AVG), geometric mean (GEO), and maximum likelihood estimator (MLE). Biogeochemical data, such as chlorophyll a, are usually considered to have a log-normal distribution. The study determined that differences between methods tend to increase with increasing size of a selected coastal area, with no significant differences in most open oceans. The GEO method consistently produces values lower than AVG and MLE. The AVG method produces values larger than MLE in some cases, but smaller in other cases. Further studies indicated that significant differences between AVG and MLE methods occurred in coastal areas where data have large spatial variations and a log-bimodal distribution instead of log-normal distribution.

Suhung, Shen↗
NASA NTRS2015

Validation of Rain Rate Retrievals for the Airborne Hurricane Imaging Radiometer (HIRAD)

The NASA Hurricane and Severe Storm Sentinel (HS3) mission is an aircraft field measurements program using NASA's unmanned Global Hawk aircraft system for remote sensing and in situ observations of Atlantic and Caribbean Sea hurricanes. One of the principal microwave instruments is the Hurricane Imaging Radiometer (HIRAD), which measures surface wind speeds and rain rates. For validation of the HIRAD wind speed measurement in hurricanes, there exists a comprehensive set of comparisons with the Stepped Frequency Microwave Radiometer (SFMR) with in situ GPS dropwindsondes [1]. However, for rain rate measurements, there are only indirect correlations with rain imagery from other HS3 remote sensors (e.g., the dual-frequency Ka- & Ku-band doppler radar, HIWRAP), which is only qualitative in nature. However, this paper presents results from an unplanned rain rate measurement validation opportunity that occurred in 2013, when HIRAD flew over an intense tropical squall line that was simultaneously observed by the Tampa NEXRAD meteorological radar (Fig. 1). During this experiment, Global Hawk flying at an altitude of 18 km made 3 passes over the rapidly propagating thunderstorm, while the TAMPA NEXRAD perform volume scans on a 5-minute interval. Using the well-documented NEXRAD Z-R relationship, 2D images of rain rate (mm/hr) were obtained at two altitudes (3 km & 6 km), which serve as surface truth for the HIRAD rain rate retrievals. A preliminary comparison of HIRAD rain rate retrievals (image) for the first pass and the corresponding closest NEXRAD rain image is presented in Fig. 2 & 3. This paper describes the HIRAD instrument, which 1D synthetic-aperture thinned array radiometer (STAR) developed by NASA Marshall Space Flight Center [2]. The rain rate retrieval algorithm, developed by Amarin et al. [3], is based on the maximum likelihood estimation (MLE) technique, which compares the observed Tb's at the HIRAD operating frequencies of 4, 5, 6 and 6.6 GHz with corresponding theoretical Tb values from a forward radiative transfer model (RTM). The optimum solution is the integrated rain rate that minimizes the difference between RTM and observed values. Because the excess Tb from rain comes from the direct upwelling and the indirect reflected downwelling paths through the atmosphere, there are several assumptions made for the 2D rain distribution in the antenna incident plane (crosstrack to flight direction). The opportunity to knowing 2D rain surface truth from NEXRAD at two different altitudes will enable a comprehensive evaluation to be preformed and reported in this paper.

hurricane↗
NASA NTRS2017

Trajectory Dispersed Vehicle Process for Space Launch System

The Space Launch System (SLS) vehicle is part of NASA's deep space exploration plans that includes manned missions to Mars. Manufacturing uncertainties in design parameters are key considerations throughout SLS development as they have significant effects on focus parameters such as lift-off-thrust-to-weight, vehicle payload, maximum dynamic pressure, and compression loads. This presentation discusses how the SLS program captures these uncertainties by utilizing a 3 degree of freedom (DOF) process called Trajectory Dispersed (TD) analysis. This analysis biases nominal trajectories to identify extremes in the design parameters for various potential SLS configurations and missions. This process utilizes a Design of Experiments (DOE) and response surface methodologies (RSM) to statistically sample uncertainties, and develop resulting vehicles using a Maximum Likelihood Estimate (MLE) process for targeting uncertainties bias. These vehicles represent various missions and configurations which are used as key inputs into a variety of analyses in the SLS design process, including 6 DOF dispersions, separation clearances, and engine out failure studies.

Statham, Tamara↗
NASA NTRS2018

Modeling of Time-Dependent Strength Degradation of SiC/SiC Ceramic Matrix Composites via MAC/GMC Computer Code

Silicon carbide fiber reinforced silicon carbide (SiC/SiC) ceramic matrix composites (CMCs) display time-dependent strength degradation at intermediate temperatures (600 to 900 degrees Centigrade). This is generally believed to be an oxidation induced phenomenon. The understanding of the effect of temperature with environment (oxidation) is key towards development of SiC/SiC CMCs with a reliable load carrying capacity. Various theories have been proposed to explain the strength degradation. One suggests that the boron nitride (BN) coating deposited on the fibers oxidizes causing fusion of fibers. Another theory proposes that the SiC fibers are oxidized forming a silica scale leading to premature fiber failure. A more recent theory suggests that SiC fiber strength is intrinsically time-dependent due to slow crack growth of flaws in the fibers. An empirical model, termed as a "fiber classic model," which is based on a standard slow crack growth type power-law, has been implemented within NASA's micromechanics-based MAC/GMC computer code as a user routine. Model parameters for this "classic model" were calibrated from stress-rupture data of Hi-Nicalon (TM) monofilaments using the maximum likelihood estimation (MLE) technique. This new capability in the MAC/GMC computer code was then used to predict the stress-rupture behavior of Hi-Nicalon (TM) tows as well as 2-D SiC/SiC composites reinforced with Hi-Nicalon (TM) fibers. Results demonstrate that the MAC/GMC with this new capability successfully predicts the time-to-failure vs. applied stress within the intermediate temperature range at various scales as well as laminated composites in an oxidizing environment.

Environmental degradation↗
NASA NTRS2022

Vision-based Velocimetry over Unknown Terrain with a Low-Noise IMU

This paper presents a novel approach to terrain-relative navigation with a visual camera and Inertial Measurement Unit (IMU). The proposed algorithm uses an Extended Kalman Filter (EKF) to combine an IMU propagated state estimate with batch correction estimates computed over a sliding window of measurements. The batch correction algorithm follows the Maximum Likelihood Estimation (MLE) approach used in other Bundle Adjustment systems. Unlike other systems, the proposed system parameterizes the state over the entire window in terms of the state at a single epoch. By ignoring IMU error over the window duration, we obtain a state epoch MLE that jointly estimates the epoch state and terrain parameters with drastically reduced computationally cost. This paper presents the general architecture which can be adapted for various state parameterizations and measurement inputs. For space applications with high-accuracy IMUs, the reduction in computational cost comes with only a modest increase in estimation errors. The increase in error is quantified via a linear covariance analysis presented in this paper. Furthermore, we present simulation results which show the applicability of this algorithm to planetary landing problems.

San Martin, A. Miguel↗
DOE OSTI2025

ASCR Workshop Position Paper: Challenges and Opportunities in High Energy Physics

High energy particle physics and cosmology concern themselves with estimating fundamental parameters of nature, such as the masses and interactions of fundamental particles like the Higgs boson and the rate of expansion of the universe. In doing so, they analyze exabyte-scale datasets, some of the largest in all of science, and face many challenges in subsequent data analysis. These challenges are shared between the two disciplines, but we focus on particle physics to highlight one specific domain. In particle physics, the standard method for estimating parameters involves performing Monte Carlo (MC) integration as a function of both parameters of interest and nuisance parameters using an expensive simulator, counting the number of observed collision events (i.i.d. samples) from an experiment in the corresponding integration domains, and forming a Poisson likelihood function. This likelihood function is then used in a Frequentist manner to construct a maximum likelihood point estimate (MLE) and confidence set for the parameters. To sufficiently populate the high-dimensional integration domains, simulators consume billions of CPU-hours annually and produce hundreds of petabytes of intermediate output data. Several techniques have been developed to: optimize definitions of the integration domains so as to be maximally sensitive to a particular subset of parameters, efficiently estimate the integrals, and build robust surrogate models by interpolating between integral evaluations at different parameter points. One can view this whole endeavor as classical Simulation-Based Inference (SBI).

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Using PyBioNetFit to leverage qualitative and quantitative data in biological model parameterization and uncertainty quantification

Data generated in studies of cellular regulatory systems are often qualitative. For example, measurements of signaling readouts in the presence and absence of mutations may reveal a rank ordering of responses across conditions but not the precise extents of mutation-induced differences. Qualitative data are often ignored by mathematical modelers or are considered in an ad hoc manner, as in the study of Kocieniewski and Lipniacki (2013) [Phys Biol 10: 035006], which was focused on the roles of MEK isoforms in ERK activation. In this earlier study, model parameter values were tuned manually to obtain consistency with a combination of qualitative and quantitative data. This approach is not reproducible, nor does it provide insights into parametric or prediction uncertainties. Here, starting from the same data and the same ordinary differential equation (ODE) model structure, we generate formalized statements of qualitative observations, making these observations more reusable, and we improve the model parameterization procedure by applying a systematic and automated approach enabled by the software package PyBioNetFit. We also demonstrate uncertainty quantification (UQ), which was absent in the original study. Our results show that PyBioNetFit enables qualitative data to be leveraged, together with quantitative data, in parameterization of systems biology models and facilitates UQ. These capabilities are important for reliable estimation of model parameters and model analyses in studies of cellular regulatory systems and reproducibility.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2012

Experimental Validation of Pulse Phase Tracking for X-Ray Pulsar Based

Pulsars are a form of variable celestial source that have shown to be usable as aids for autonomous, deep space navigation. Particularly those sources emitting in the X-ray band are ideal for navigation due to smaller detector sizes. In this paper X-ray photons arriving from a pulsar are modeled as a non-homogeneous Poisson process. The method of pulse phase tracking is then investigated as a technique to measure the radial distance traveled by a spacecraft over an observation interval. A maximum-likelihood phase estimator (MLE) is used for the case where the observed frequency signal is constant. For the varying signal frequency case, an algorithm is used in which the observation window is broken up into smaller blocks over which an MLE is used. The outputs of this phase estimation process were then looped through a digital phase-locked loop (DPLL) in order to reduce the errors and produce estimates of the doppler frequency. These phase tracking algorithms were tested both in a computer simulation environment and using the NASA Goddard Space flight Center X-ray Navigation Laboratory Testbed (GXLT). This provided an experimental validation with photons being emitted by a modulated X-ray source and detected by a silicon-drift detector. Models of the Crab pulsar and the pulsar B1821-24 were used in order to generate test scenarios. Three different simulated detector trajectories were used to be tracked by the phase tracking algorithm: a stationary case, one with constant velocity, and one with constant acceleration. All three were performed in one-dimension along the line of sight to the pulsar. The first two had a constant signal frequency and the third had a time varying frequency. All of the constant frequency cases were processed using the MLE, and it was shown that they tracked the initial phase within 0.15% for the simulations and 2.5% in the experiments, based on an average of ten runs. The MLE-DPLL cascade version of the phase tracking algorithm was used in the varying frequency case. This resulted in tracking of the phase and frequency by the DPLL outputs in both the simulation and experimental environments. The crab pulsar was experimentally tested with a trajectory with a higher acceleration. In this case the phase error tended toward zero as the observation extended to 250 seconds and the doppler frequency error tended to zero in under 100 seconds.

Experimental↗
NASA NTRS1981

Software models: A Bayesian approach to parameter estimation in the Jelenski-Moranda software reliability model

Maximum likelihood estimation procedures for the Jelinski-Moranda software reliability model often give misleading answers. A reparameterization and a Bayesian analysis eliminate some of the problems incurred by MLE methods and often give better predictions on sets of real and simulated data. Practical difficulties in estimating the initial number of errors N and the failure rate of each error phi by the method of maximum likelihood are: N, the MLE of N, is occasionally infinite (i.e., the routines for calculating N and phi do not converge). It is shown that N is finite sub i only if the regression line of the interevent times t sub i vs. i has positive slope. A serious problem is that often N approximates n, the sample size, and sometimes N = n. Thus the MLE predicts that the program is perfect even when it is far from being so. Only when almost all failures have been removed can N and phi be trusted near the end of debugging.

Littlewood, B.↗
NASA NTRS1984

A Monte Carlo comparison of the recovery of winds near upwind and downwind from the SASS-1 model function by means of the sum of squares algorithm and a maximum likelihood estimator

Backscatter measurements at upwind and crosswind are simulated for five incidence angles by means of the SASS-1 model function. The effects of communication noise and attitude errors are simulated by Monte Carlo methods, and the winds are recovered by both the Sum of Square (SOS) algorithm and a Maximum Likelihood Estimater (MLE). The SOS algorithm is shown to fail for light enough winds at all incidence angles and to fail to show areas of calm because backscatter estimates that were negative or that produced incorrect values of K sub p greater than one were discarded. The MLE performs well for all input backscatter estimates and returns calm when both are negative. The use of the SOS algorithm is shown to have introduced errors in the SASS-1 model function that, in part, cancel out the errors that result from using it, but that also cause disagreement with other data sources such as the AAFE circle flight data at light winds. Implications for future scatterometer systems are given.

Pierson, W. J., Jr.↗
NASA NTRS1977

F-8C adaptive flight control laws

Three candidate digital adaptive control laws were designed for NASA's F-8C digital flyby wire aircraft. Each design used the same control laws but adjusted the gains with a different adaptative algorithm. The three adaptive concepts were: high-gain limit cycle, Liapunov-stable model tracking, and maximum likelihood estimation. Sensors were restricted to conventional inertial instruments (rate gyros and accelerometers) without use of air-data measurements. Performance, growth potential, and computer requirements were used as criteria for selecting the most promising of these candidates for further refinement. The maximum likelihood concept was selected primarily because it offers the greatest potential for identifying several aircraft parameters and hence for improved control performance in future aircraft application. In terms of identification and gain adjustment accuracy, the MLE design is slightly superior to the other two, but this has no significant effects on the control performance achievable with the F-8C aircraft. The maximum likelihood design is recommended for flight test, and several refinements to that design are proposed.

Hartmann, G. L.↗