Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Likelihood Functions”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 37 records · Page 2

Classification by means of B-spline potential functions with applications to remote sensing

A method is presented for using B-splines as potential functions in the estimation of likelihood functions (probability density functions conditioned on pattern classes), or the resulting discriminant functions. The consistency of this technique is discussed. Experimental results of using the likelihood functions in the classification of remotely sensed data are given.

Bennett, J. O.↗

A BAYESIAN ASSESSMENT OF P-VALUES FOR SIGNIFICANCE ESTIMATION OF POWER SPECTRA AND AN ALTERNATIVE PROCEDURE, WITH APPLICATION TO SOLAR NEUTRINO DATA

The usual procedure for estimating the significance of a peak in a power spectrum is to calculate the probability of obtaining that value or a larger value by chance (known as the 'p-value'), on the assumption that the time series contains only noise-typically that the measurements are derived from random samplings of a Gaussian distribution. However, since the use of p-values in other contexts is known to be misleading, it seems prudent to examine the implications of using p-values for significance estimation of power spectra. We really need to know the probability that the time series is-or is not-compatible with the 'null hypothesis' that the measurements are derived from noise. This probability can be calculated by Bayesian analysis, but this requires one to specify and evaluate a second hypothesis that the time series does contain a contribution other than noise. We show that the requirement that the p-value should be identical to the probability that the null hypothesis is true leads to an unacceptable form for the likelihood function associated with this hypothesis. We claim that, for this reason, the p-value is not an acceptable method for significance estimation of a power spectrum. In order to obtain an acceptable significance estimate, it is necessary to explicitly consider a second hypothesis, and the key challenge is to identify an appropriate likelihood function for this hypothesis. We first propose four simple conditions that it seems reasonable to impose on this function. We then examine a general functional form for the function, and find the simplest form (which has one free parameter) that meets these conditions. We then define two different ways of combining information derived from two independent power estimates. One procedure is to calculate the post-probabilities of the null hypothesis, convert these to odds-values, and sum the log-odds. The second procedure is to combine the p-values using a procedure due to R.A. Fisher, and to calculate the corresponding post-probability and hence the corresponding log-odds. It seems sensible-even if not logically essential-to seek a likelihood function for which the two procedures lead to the same answer. We find that this consistency condition may be satisfied, to good approximation, by a special case of the previously proposed likelihood function. We find that the resulting significance estimates are considerably more conservative than those usually associated with the p-values. As two examples, we apply the new procedure to two recent analyses of solar neutrino data: (1) power spectrum analysis of Super-Kamiokande data and (2) the combined analysis of radiochemical neutrino data and irradiance data.

79 ASTRONOMY AND ASTROPHYSICS↗

Determining frequentist confidence limits using a directed parameter space search

We consider the problem of inferring constraints on a high-dimensional parameter space with a computationally expensive likelihood function. We propose a machine learning algorithm that maps out the Frequentist confidence limit on parameter space by intelligently targeting likelihood evaluations so as to quickly and accurately characterize the likelihood surface in both low- and high-likelihood regions. We compare our algorithm to Bayesian credible limits derived by the well-tested Markov Chain Monte Carlo (MCMC) algorithm using both multi-modal toy likelihood functions and the seven yr Wilkinson Microwave Anisotropy Probe cosmic microwave background likelihood function. We find that our algorithm correctly identifies the location, general size, and general shape of high-likelihood regions in parameter space while being more robust against multi-modality than MCMC.

79 ASTRONOMY AND ASTROPHYSICS↗

Bayesian optimization of generalized data

Direct application of Bayes' theorem to generalized data yields a posterior probability distribution function (PDF) that is a product of a prior PDF of generalized data and a likelihood function, where generalized data consists of model parameters, measured data, and model defect data. The prior PDF of generalized data is defined by prior expectation values and a prior covariance matrix of generalized data that naturally includes covariance between any two components of generalized data. A set of constraints imposed on the posterior expectation values and covariances of generalized data via a given model is formally solved by the method of Lagrange multipliers. Posterior expectation values of the constraints and their covariance matrix are conventionally set to zero, leading to a likelihood function that is a Dirac delta function of the constraining equation. It is shown that setting constraints to values other than zero is analogous to introducing a model defect. Since posterior expectation values of any function of generalized data are integrals of that function over all generalized data weighted by the posterior PDF, all elements of generalized data may be viewed as nuisance parameters marginalized by this integration. One simple form of posterior PDF is obtained when the prior PDF and the likelihood function are normal PDFs. For linear models without a defect this PDF becomes equivalent to constrained least squares (CLS) method, that is, the χ2 minimization method.

Arbanas, Goran↗

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↗

Analysis of small-scale microwave background radiation anisotropy in the presence of foreground contamination

Many of the current round of experiments searching for anisotropies in the microwave background radiation (MBR) are confronting the problem of how to disentangle the cosmic signal from contamination due to Galactic and intergalactic foreground sources. Here we show how commonly used likelihood function techniques can be generalized to account for foreground. Specifically we set some restrictions on the spectrum of foreground contamination but allow the amplitude to vary arbitrarily. The likelihood function thus generalized gives reasonable limits on the MBR anisotropy which, in some cases, are not much less restrictive than what one would get from more detailed modeling of the foreground. Furthermore, the likelihood function is exactly the same as one would obtain by simply projecting out foreground contamination and looking at the reduced data set. We apply this generalized analysis to the recent medium-angle data sets of ACME-HEMT (Gaier et al. 1992; Schuster et al. 1993) and MAX (Meinhold et al. 1993; Gunderson et al. 1993). The resulting analysis constrains the one free parameter in the standard cold dark matter theory to be Q(sub rms-ps) = 18(sub -5 sup +8) microKelvin. This best fit value, although in striking agreement with the normalization from Cosmic Background Explorer (COBE), is not a very good fit, with an overall chi-squared/degrees of freedom = 208/168. We also argue against three commonly used methods of dealing with foreground: (1) ignoring it completely; (2) subtracting off a best-fit foreground and treating the residuals as if uncontaminated; and (3) culling data which appears to be contaminated by foreground.

Dodelson, Scott↗

Improved estimates of coordinate error for molecular replacement

A function for estimating the effective root-mean-square deviation in coordinates between two proteins has been developed that depends on both the sequence identity and the size of the protein and is optimized for use with molecular replacement in Phaser. A top peak translation-function Z-score of over 8 is found to be a reliable metric of when molecular replacement has succeeded. The estimate of the root-mean-square deviation (r.m.s.d.) in coordinates between the model and the target is an essential parameter for calibrating likelihood functions for molecular replacement (MR). Good estimates of the r.m.s.d. lead to good estimates of the variance term in the likelihood functions, which increases signal to noise and hence success rates in the MR search. Phaser has hitherto used an estimate of the r.m.s.d. that only depends on the sequence identity between the model and target and which was not optimized for the MR likelihood functions. Variance-refinement functionality was added to Phaser to enable determination of the effective r.m.s.d. that optimized the log-likelihood gain (LLG) for a correct MR solution. Variance refinement was subsequently performed on a database of over 21 000 MR problems that sampled a range of sequence identities, protein sizes and protein fold classes. Success was monitored using the translation-function Z-score (TFZ), where a TFZ of 8 or over for the top peak was found to be a reliable indicator that MR had succeeded for these cases with one molecule in the asymmetric unit. Good estimates of the r.m.s.d. are correlated with the sequence identity and the protein size. A new estimate of the r.m.s.d. that uses these two parameters in a function optimized to fit the mean of the refined variance is implemented in Phaser and improves MR outcomes. Perturbing the initial estimate of the r.m.s.d. from the mean of the distribution in steps of standard deviations of the distribution further increases MR success rates.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Extreme-Scale Bayesian Inference for Uncertainty Quantification of Complex Simulations

Uncertainty quantification (UQ)—that is, quantifying uncertainties in complex mathematical models and their large-scale computational implementations—is widely viewed as one of the outstanding challenges facing the field of CS&E over the coming decade. The EUREKA project set to address the most difficult class of UQ problems: those for which both the underlying PDE model as well as the uncertain parameters are of extreme scale. In the project we worked on these extreme-scale challenges in the following four areas: 1. Scalable parallel algorithms for sampling and characterizing the posterior distribution that exploit the structure of the underlying PDEs and parameter-to-observable map. These include structure-exploiting versions of the randomized maximum likelihood method, which aims to overcome the intractability of employing conventional MCMC methods for solving extreme-scale Bayesian inversion problems by appealing to and adapting ideas from large-scale PDE-constrained optimization, which have been very successful at exploring high-dimensional spaces. 2. Scalable parallel algorithms for construction of prior and likelihood functions based on learning methods and non-parametric density estimation. Constructing problem-specific priors remains a critical challenge in Bayesian inference, and more so in high dimensions. Another challenge is construction of likelihood functions that capture unmodeled couplings between observations and parameters. We will create parallel algorithms for non-parametric density estimation using high dimensional N-body methods and combine them with supervised learning techniques for the construction of priors and likelihood functions. 3. Bayesian inadequacy models, which augment physics models with stochastic models that represent their imperfections. The success of the Bayesian inference framework depends on the ability to represent the uncertainty due to imperfections of the mathematical model of the phenomena of interest. This is a central challenge in UQ, especially for large-scale models. We propose to develop the mathematical tools to address these challenges in the context of extreme-scale problems. 4. Parallel scalable algorithms for Bayesian optimal experimental design (OED). Bayesian inversion yields quantified uncertainties in the model parameters, which can be propagated forward through the model to yield uncertainty in outputs of interest. This opens the way for designing new experiments to reduce the uncertainties in the model parameters and model predictions. Such experimental design problems have been intractable for large-scale problems using conventional methods; we will create OED algorithms that exploit the structure of the PDE model and the parameter-to-output map to overcome these challenges. Parallel algorithms for these four problems were created, analyzed, prototyped, implemented, tuned, and scaled up for leading-edge supercomputers, including UT-Austin’s own 10 petaflops Stampede system, ANL’s Mira system, and ORNL’s Titan system. While our focus is on fundamental mathematical/computational methods and algorithms, we will assess our methods on model problems derived from several DOE mission applications, including multiscale mechanics and ice sheet dynamics.

97 MATHEMATICS AND COMPUTING↗

Topics in inference and decision-making with partial knowledge

Two essential elements needed in the process of inference and decision-making are prior probabilities and likelihood functions. When both of these components are known accurately and precisely, the Bayesian approach provides a consistent and coherent solution to the problems of inference and decision-making. In many situations, however, either one or both of the above components may not be known, or at least may not be known precisely. This problem of partial knowledge about prior probabilities and likelihood functions is addressed. There are at least two ways to cope with this lack of precise knowledge: robust methods, and interval-valued methods. First, ways of modeling imprecision and indeterminacies in prior probabilities and likelihood functions are examined; then how imprecision in the above components carries over to the posterior probabilities is examined. Finally, the problem of decision making with imprecise posterior probabilities and the consequences of such actions are addressed. Application areas where the above problems may occur are in statistical pattern recognition problems, for example, the problem of classification of high-dimensional multispectral remote sensing image data.

Safavian, S. Rasoul↗

Physicochemical/Thermodynamic Framework for the Interpretation of Peptide Tandem Mass Spectra

The interpretation of tandem mass spectra of peptides from collision-induced dissociation is discussed from the perspective of a multinomial data analysis problem and from the perspective of statistical mechanics. Both approaches use the same statistical likelihood function, and it is shown that this statistical likelihood is equivalent to an information theory entropy when scaled appropriately. The likelihood function provides a physically and chemically principled way to incorporate intensity information into the interpretation of tandem mass spectra and enables the use of predictive modeling and simulation to inform the peptide identification process.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A search for resonant production of tt pairs in 4.8 fb -1 of integrated luminosity of pp collisions at √s=1.96 TeV

We search for resonant production of tt pairs in 4.8 fb -1 integrated luminosity of pp collision data at √s = 1.96 TeV in the lepton+jets decay channel, where one top quark decays leptonically and the other hadronically. A matrix element reconstruction technique is used; for each event a probability density function (pdf) of the tt candidate invariant mass is sampled. These pdfs are used to construct a likelihood function, whereby the cross section for resonant tt production is estimated, given a hypothetical resonance mass and width. The data indicate no evidence of resonant production of tt pairs. A benchmark model of leptophobic Z' → tt is excluded with m Z' < 900 GeV at 95% confidence level.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Accuracy of maximum likelihood estimates of a two-state model in single-molecule FRET

Photon sequences from single-molecule Förster resonance energy transfer (FRET) experiments can be analyzed using a maximum likelihood method. Parameters of the underlying kinetic model (FRET efficiencies of the states and transition rates between conformational states) are obtained by maximizing the appropriate likelihood function. In addition, the errors (uncertainties) of the extracted parameters can be obtained from the curvature of the likelihood function at the maximum. We study the standard deviations of the parameters of a two-state model obtained from photon sequences with recorded colors and arrival times. The standard deviations can be obtained analytically in a special case when the FRET efficiencies of the states are 0 and 1 and in the limiting cases of fast and slow conformational dynamics. These results are compared with the results of numerical simulations. The accuracy and, therefore, the ability to predict model parameters depend on how fast the transition rates are compared to the photon count rate. In the limit of slow transitions, the key parameters that determine the accuracy are the number of transitions between the states and the number of independent photon sequences. In the fast transition limit, the accuracy is determined by the small fraction of photons that are correlated with their neighbors. The relative standard deviation of the relaxation rate has a “chevron” shape as a function of the transition rate in the log-log scale. The location of the minimum of this function dramatically depends on how well the FRET efficiencies of the states are separated.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Procedure for estimating stability and control parameters from flight test data by using maximum likelihood methods employing a real-time digital system

A maximum likelihood parameter estimation procedure and program were developed for the extraction of the stability and control derivatives of aircraft from flight test data. Nonlinear six-degree-of-freedom equations describing aircraft dynamics were used to derive sensitivity equations for quasilinearization. The maximum likelihood function with quasilinearization was used to derive the parameter change equations, the covariance matrices for the parameters and measurement noise, and the performance index function. The maximum likelihood estimator was mechanized into an iterative estimation procedure utilizing a real time digital computer and graphic display system. This program was developed for 8 measured state variables and 40 parameters. Test cases were conducted with simulated data for validation of the estimation procedure and program. The program was applied to a V/STOL tilt wing aircraft, a military fighter airplane, and a light single engine airplane. The particular nonlinear equations of motion, derivation of the sensitivity equations, addition of accelerations into the algorithm, operational features of the real time digital system, and test cases are described.

Grove, R. D.↗

Two stochastic models useful in petroleum exploration

A model of the petroleum exploration process that tests empirically the hypothesis that at an early stage in the exploration of a basin, the process behaves like sampling without replacement is proposed along with a model of the spatial distribution of petroleum reserviors that conforms to observed facts. In developing the model of discovery, the following topics are discussed: probabilitistic proportionality, likelihood function, and maximum likelihood estimation. In addition, the spatial model is described, which is defined as a stochastic process generating values of a sequence or random variables in a way that simulates the frequency distribution of areal extent, the geographic location, and shape of oil deposits

Kaufman, G. M.↗

Determining Physical Parameters of Shielded Uranium using Gamma Spectroscopy and the Differential Evolution Adaptive Metropolis (DREAM) Method

Inverse radiation transport is a well-established method for determining unknown parameters within a system that exhibits particle leakage. Two significant challenges of solving inverse transport problems are (1) to determine multiple unknowns without false convergence on local minima and (2) to be able to quantify uncertainty. It was recently demonstrated that the Differential Evolution Adaptive Metropolis (DREAM) method effectively meets both of these challenges. In Bledsoe's 2014 article, the DREAM method was only applied to numerical test cases in which measured data were simulated using MCNP. This paper provides results of research conducted at Oak Ridge National Laboratory (ORNL) in which DREAM was applied to two-dimensional inverse transport problems using real-world measurements. The DREAM method uses a Markov chain Monte Carlo (MCMC) method to obtain a posterior distribution of unknown parameters. In this application, the posterior distribution is determined by using a uniform prior distribution and a likelihood function. The goal of the inverse problem is to find the regions in which the likelihood function is at or near its maximum. In the traditional MCMC approach, a single Markov chain is employed. In practice, MCMC approaches have a high acceptance rate to solutions that are near the current point of sampling, but they exhibit slow convergence to solutions far from the sampling point. The DREAM algorithm was designed to alleviate this issue by initiating multiple Markov chains and using the differential evolution algorithm to generate trial points for each chain. Solving for the mass of radioactive material within a voluminous source is a challenging problem for gamma-ray spectroscopy. Inverse gamma-ray transport can supply a range of possible material compositions, but reducing the differences between predicted and actual measurements can lead to false results. DREAM is a rapid technique for determining the most likely solution for several unknown parameters in an inverse transport problem. This work applies DREAM to a series of gamma spectroscopy experiments performed at ORNL.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Flexible and scalable methods for quantifying stochastic variability in the era of massive time-domain astronomical data sets

We present the use of continuous-time autoregressive moving average (CARMA) models as a method for estimating the variability features of a light curve, and in particular its power spectral density (PSD). CARMA models fully account for irregular sampling and measurement errors, making them valuable for quantifying variability, forecasting and interpolating light curves, and variability-based classification. We show that the PSD of a CARMA model can be expressed as a sum of Lorentzian functions, which makes them extremely flexible and able to model a broad range of PSDs. We present the likelihood function for light curves sampled from CARMA processes, placing them on a statistically rigorous foundation, and we present a Bayesian method to infer the probability distribution of the PSD given the measured light curve. Because calculation of the likelihood function scales linearly with the number of data points, CARMA modeling scales to current and future massive time-domain data sets. We conclude by applying our CARMA modeling approach to light curves for an X-ray binary, two active galactic nuclei, a long-period variable star, and an RR Lyrae star in order to illustrate their use, applicability, and interpretation.

79 ASTRONOMY AND ASTROPHYSICS↗

Evaluation of LANDSAT-D Orbit Determination Using a Filter/Smoother (PREFER)

Simulated range and range rate data for five tracking stations were first generated using batch least squares orbit determination (GTDS). Then GTDS was used (in the differential correction mode) to produce a nominal trajectory which was input to PREFER. The GTDS differential correction (DC) run was made using models which differed from those used to produce the simulated data. These model differences were chosen to be fairly realistic approximations to the errors in the models actually used for operational orbit determination. Several different simulation runs were made with different types of model errors in order to determine the sensitivity to these errors. The nominal trajectory and the simulated measurement data were input to PREFER to produce a smoothed ephemeris file. Numerous runs of PREFER were made in which parameters describing the statistics of the model errors were varied. The likelihood function computed by the Kalman filter determined the ""best'' choice of input parameters. There was strong negative correlation between the likelihood function and the errors in the smoothed ephemeris.

Gibbs, B. P.↗