Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Bayesian 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 19 records

Statistical data analysis of x-ray spectroscopy data enabled by neural network accelerated Bayesian inference

Bayesian inference applied to x-ray spectroscopy data analysis enables uncertainty quantification necessary to rigorously test theoretical models. However, when comparing to data, detailed atomic physics and radiation transfer calculations of x-ray emission from non-uniform plasma conditions are typically too slow to be performed in line with statistical sampling methods, such as Markov Chain Monte Carlo sampling. Furthermore, differences in transition energies and x-ray opacities often make direct comparisons between simulated and measured spectra unreliable. Here, we present a spectral decomposition method that allows for corrections to line positions and bound–bound opacities to best fit experimental data, with the goal of providing quantitative feedback to improve the underlying theoretical models and guide future experiments. In this work, we use a neural network (NN) surrogate model to replace spectral calculations of isobaric hot-spots created in Kr-doped implosions at the National Ignition Facility. The NN was trained on calculations of x-ray spectra using an isobaric hot-spot model post-processed with Cretin, a multi-species atomic kinetics and radiation code. The speedup provided by the NN model to generate x-ray emission spectra enables statistical analysis of parameterized models with sufficient detail to accurately represent the physical system and extract the plasma parameters of interest.

47 OTHER INSTRUMENTATION↗

Extending Parsimonious Bayesian Inference

Parsimonious Bayesian inference is a theoretical framework for efficient data assimilation that seeks to balance increased consistency between predictions and training data against corresponding increases in model complexity. Within this framework, over-training is understood as optimization that encodes excessive information within model parameters while only achieving small improvements between predictions and training data. This project aims to develop practical methods of limiting excess model information during optimization. One key observation is that practical heuristics for parsimonious learning in high-dimensions must balance expressivity, i.e. the ability of the model to capture diverse predictions with only a few non-zero parameters, against discoverability, i.e. the ability to train the model with gradient-based optimization and drive parameters to low information states. As such, we developed logical activation functions that are able to adaptively approximate arbitrary truth tables that define Boolean logic operations within a probabilistic framework. These functions have demonstrated the ability to learn exclusive disjunction (XOR) and conditioned disjunction (if [condition] then [result_if_true] else [result_if_false]) within a single layer of a neural network. To efficiently exploit these activation functions to drive parsimonious learning required several other advances within the domain of variational inference. The most efficient form of complexity suppression is structured sparsification, driving most model parameters to zero while achieving the structural coherence among nonzeros needed for bandwidth reduction. Such models are not only far more efficient at suppressing information-theoretic complexity, they also reduce the other forms of complexity (computations, communication, storage, and the number of dependencies needed to evaluate predictions). Aiming to support enhanced sparsification, this project examined new approaches to high-dimensional variational inference that allow us to calibrate and control parameter uncertainty during optimization. By identifying which parameters can sustain sparsifying perturbations with little impact on prediction quality, we can develop better pruning strategies by framing them as approximate Bayesian inference. These advances also open paths to mitigate concerns with deploying advanced learning methods in resource-constrained environments, such as running models on power-limited or communication-limited devices.

97 MATHEMATICS AND COMPUTING↗

Cataloging the visible universe through Bayesian inference in Julia at petascale

A key task in astronomy is to locate astronomical objects in images and to characterize them according to physical parameters such as brightness, color, and morphology. This task, known as cataloging, is challenging for several reasons: many astronomical objects are much dimmer than the sky background, labeled data is generally unavailable, overlapping astronomical objects must be resolved collectively, and the datasets are enormous – terabytes now, petabytes soon. In this work, we infer an astronomical catalog from 55 TB of imaging data using Celeste, a Bayesian variational inference code written entirely in the high-productivity programming language Julia. Using over 1.3 million threads on 650,000 Intel Xeon Phi cores of the Cori Phase II supercomputer, Celeste achieves a peak rate of 1.54 DP PFLOP/s. Celeste is able to jointly optimize parameters for 188 M stars and galaxies, loading and processing 178 TB across 8192 nodes in 14.6 min. To achieve this, Celeste exploits parallelism at multiple levels (cluster, node, and thread) and accelerates I/O through Cori’s burst buffer. Julia’s native performance enables Celeste to employ high-level constructs without resorting to hand-written or generated low-level code (C/C++/Fortran) while still achieving petascale performance.

Regier, Jeffrey↗

Development of a Weibull posterior distribution by combining a Weibull prior with an actual failure distribution using Bayesian inference

A Bayesian inference process for system logistical planning is presented which provides a method for incorporating actual failures with prediction data for an ongoing and improving reliability estimates. The process uses the Weibull distribution, and provides a means for examining and updating logistical and maintenance support needs.

Giuntini, Michael E.↗

Bayesian inference for heterogeneous caprock permeability based on above zone pressure monitoring

The presence of faults/ fractures or highly permeable zones in the primary sealing caprock of a CO2 storage reservoir can result in leakage of CO2. Monitoring of leakage requires the capability to detect and resolve the onset, location, and volume of leakage in a systematic and timely manner. Pressure-based monitoring possesses such capabilities. This study demonstrates a basis for monitoring network design based on the characterization of CO2 leakage scenarios through an assessment of the integrity and permeability of the caprock inferred from above zone pressure measurements. Four representative heterogeneous fractured seal types are characterized to demonstrate seal permeability ranging from highly permeable to impermeable. Based on Bayesian classification theory, the probability of each fractured caprock scenario given above zone pressure measurements with measurement error is inferred. The sensitivity to injection rate and caprock thickness is also evaluated and the probability of proper classification is calculated. The time required to distinguish between above zone pressure outcomes and the associated leakage scenarios is also computed.

54 ENVIRONMENTAL SCIENCES↗

Brittleness and Bayesian Inference

In a recent report, “Bayesian Brittleness: Why no Bayesian model is ‘good enough,’” (arXiv, 1304.6772v1) the authors prove rigorously that under a seemingly natural class of priors Π, the posterior expectation of a function Φ(θ) can achieve essentially any value that Φ(θ) alone can achieve, so that Bayesian inference appears to have no robustness whatsoever. We explain this puzzling result, and show why it does not imply a breakdown of Bayesian inference. The problem is that the priors leading to the extreme results depend on the observed data, which means they are not valid priors. The corresponding posteriors are also invalid, so the extreme variation in these posteriors does not imply that Bayesian inference is brittle. The report, however, provides a new framework which may be used for any assumed class of priors Π, and which we explain in detail. This framework may be a useful new tool for deriving quantitative robustness results.

97 MATHEMATICS AND COMPUTING↗

Metis: A Pure Metropolis Markov Chain Monte Carlo Bayesian Inference Library

The use of Bayesian inference in data analysis has become the standard for large scienti c experiments [1, 2]. The Monte Carlo Codes Group(XCP-3) at Los Alamos has developed a simple set of algorithms currently implemented in C++ and Python to easily perform at-prior Markov Chain Monte Carlo Bayesian inference with pure Metropolis sampling. These implementations are designed to be user friendly and extensible for customization based on speci c application requirements. This document describes the algorithmic choices made and presents two use cases.

97 MATHEMATICS AND COMPUTING↗

Bayesian inference of Stochastic reaction networks using Multifidelity Sequential Tempered Markov Chain Monte Carlo

Stochastic reaction network models are often used to explain and predict the dynamics of gene regulation in single cells.These models usually involve several parameters, such as the kinetic rates of chemical reactions, that are not directly measurable and must be inferred from experimental data. Bayesian inference provides a rigorous probabilistic frame-work for identifying these parameters by finding a posterior parameter distribution that captures their uncertainty.Traditional computational methods for solving inference problems such as Markov Chain Monte Carlo methods based on classical Metropolis-Hastings algorithm involve numerous serial evaluations of the likelihood function, which in turn requires expensive forward solutions of the chemical master equation (CME). We propose an alternate approach based on a multifidelity extension of the Sequential Tempered Markov Chain Monte Carlo (ST-MCMC) sampler. This algorithm is built upon Sequential Monte Carlo and solves the Bayesian inference problem by decomposing it into a sequence of efficiently solved subproblems that gradually increase both model fidelity and the influence of the observed data. We reformulate the finite state projection (FSP) algorithm, a well-known method for solving the CME, to produce a hierarchy of surrogate master equations to be used in this multifidelity scheme. To determine the appropriate fidelity, we introduce a novel information-theoretic criteria that seeks to extract the most information about the ultimate Bayesian posterior from each model in the hierarchy without inducing significant bias. This novel sampling scheme is tested with high performance computing resources using biologically relevant problems.

97 MATHEMATICS AND COMPUTING↗

SU-E-T-144: Bayesian Inference of Local Relapse Data Using a Poisson-Based Tumour Control Probability Model

Purpose: The purpose of this project is to develop a robust method of parameter estimation for a Poisson-based TCP model using Bayesian inference. Methods: Bayesian inference was performed using the PyMC3 probabilistic programming framework written in Python. A Poisson-based TCP regression model that accounts for clonogen proliferation was fit to observed rates of local relapse as a function of equivalent dose in 2 Gy fractions for a population of 623 stage-I non-small-cell lung cancer patients. The Slice Markov Chain Monte Carlo sampling algorithm was used to sample the posterior distributions, and was initiated using the maximum of the posterior distributions found by optimization. The calculation of TCP with each sample step required integration over the free parameter α, which was performed using an adaptive 24-point Gauss-Legendre quadrature. Convergence was verified via inspection of the trace plot and posterior distribution for each of the fit parameters, as well as with comparisons of the most probable parameter values with their respective maximum likelihood estimates. Results: Posterior distributions for α, the standard deviation of α (σ), the average tumour cell-doubling time (Td), and the repopulation delay time (Tk), were generated assuming α/β = 10 Gy, and a fixed clonogen density of 10{sup 7} cm−{sup 3}. Posterior predictive plots generated from samples from these posterior distributions are in excellent agreement with the observed rates of local relapse used in the Bayesian inference. The most probable values of the model parameters also agree well with maximum likelihood estimates. Conclusion: A robust method of performing Bayesian inference of TCP data using a complex TCP model has been established.

60 APPLIED LIFE SCIENCES↗

Is Bayesian inference "brittle"?

In a recent report, “Bayesian Brittleness: Why no Bayesian model is ‘good enough,’” (arXiv, 1304.6772v1) the authors prove rigorously that model variations that are arbitrarily small, in a particular technical sense, the posterior expectation of a function can achieve essentially any value that the function alone can achieve, so that Bayesian inference appears to have no robustness whatsoever. We explain this puzzling result, and show why it does not imply a breakdown of Bayesian inference. The explanation is that the models leading to the extreme results depend on the observed data.

97 MATHEMATICS AND COMPUTING↗

Simultaneous inversion of multiple microseismic data for event locations and velocity model with Bayesian inference

We have applied Bayesian inference for simultaneous inversion of multiple microseismic data to obtain event locations along with the subsurface velocity model. The traditional method of using a predetermined velocity model for event location may be subject to large uncertainties, particularly if the prior velocity model is poor. Our study indicated that microseismic data can help to construct the velocity model, which is usually a major source of uncertainty in microseismic event locations. The simultaneous inversion eliminates the requirement for an accurate predetermined velocity model in microseismic event location estimation.Here, we estimate the posterior probability density of the velocity model and microseismic event locations with the maximum a posteriori estimation, and the posterior covariance approximation under the Gaussian assumption. This provides an efficient and effective way to quantify the uncertainty of the microseismic location estimation and capture the correlation between the velocity model and microseismic event locations. We have developed successful applications on both synthetic examples and real data from the Newberry enhanced geothermal system. Comparisons with location results based on a traditional predetermined velocity model method demonstrated that we can construct a reliable effective velocity model using only microseismic data and determine microseismic event locations without prior knowledge of the velocity model.

58 GEOSCIENCES↗

Mobile sensing of point-source gas emissions using Bayesian inference: An empirical examination of the likelihood function

This paper evaluates likelihood function forms for Bayesian inference of point-source gas emissions using a mobile sensor. Whereas Bayesian inference has been successfully used to estimate emission rates from time-averaged concentration data measured by stationary sensors, data collected by mobile sensors do not represent ensemble or time-averaged conditions. To examine the potential impact of this contrast, controlled release experiments were conducted with a mobile sensor measuring concentrations repeatedly along transverse cross sections of the downwind plumes. Experiments were conducted with measurements made at different downwind distances, different sensor heights, and with different obstacle states. An examination is made between two commonly-used likelihood functions, the Gaussian and the log-normal. For experiments conducted in the absence of obstacles, the Bayesian estimates using the log-normal likelihood function yield a much smaller bias than those based on the Gaussian likelihood function. This finding is consistent with the non-Gaussian nature of concentration fluctuations near a point-source. For experiments conducted in the presence of obstacles, the Bayesian inference based on the Gaussian likelihood function exhibits a better performance. This can be explained by the enhanced turbulent mixing due to the obstacle-introduced wake eddies. Overall, we find that the selection of the likelihood function can be physically related to the underlying conditions, and the proper selection is critical to ensure the performance of the Bayesian inference for source characterization using mobile sensing data.

54 ENVIRONMENTAL SCIENCES↗

Bayesian inference and predictive performance of soil respiration models in the presence of model discrepancy

Bayesian inference of microbial soil respiration models is often based on the assumptions that the residuals are independent (i.e., no temporal or spatial correlation), identically distributed (i.e., Gaussian noise), and have constant variance (i.e., homoscedastic). In the presence of model discrepancy, as no model is perfect, this study shows that these assumptions are generally invalid in soil respiration modeling such that residuals have high temporal correlation, an increasing variance with increasing magnitude of CO 2 efflux, and non-Gaussian distribution. Relaxing these three assumptions stepwise results in eight data models. Data models are the basis of formulating likelihood functions of Bayesian inference. This study presents a systematic and comprehensive investigation of the impacts of data model selection on Bayesian inference and predictive performance. We use three mechanistic soil respiration models with different levels of model fidelity (i.e., model discrepancy) with respect to the number of carbon pools and the explicit representations of soil moisture controls on carbon degradation; therefore, we have different levels of model complexity with respect to the number of model parameters. The study shows that data models have substantial impacts on Bayesian inference and predictive performance of the soil respiration models such that the following points are true: (i) the level of complexity of the best model is generally justified by the cross-validation results for different data models; (ii) not accounting for heteroscedasticity and autocorrelation might not necessarily result in biased parameter estimates or predictions, but will definitely underestimate uncertainty; (iii) using a non-Gaussian data model improves the parameter estimates and the predictive performance; and (iv) accounting for autocorrelation only or joint inversion of correlation and heteroscedasticity can be problematic and requires special treatment. Although the conclusions of this study are empirical, the analysis may provide insights for selecting appropriate data models for soil respiration modeling.

58 GEOSCIENCES↗

An Adaptive Sparse-Grid High-Order Stochastic Collocation Method for Bayesian Inference in Groundwater Reactive Transport Modeling

Although Bayesian analysis has become vital to the quantification of prediction uncertainty in groundwater modeling, its application has been hindered due to the computational cost associated with numerous model executions needed for exploring the posterior probability density function (PPDF) of model parameters. This is particularly the case when the PPDF is estimated using Markov Chain Monte Carlo (MCMC) sampling. In this study, we develop a new approach that improves computational efficiency of Bayesian inference by constructing a surrogate system based on an adaptive sparse-grid high-order stochastic collocation (aSG-hSC) method. Unlike previous works using first-order hierarchical basis, we utilize a compactly supported higher-order hierar- chical basis to construct the surrogate system, resulting in a significant reduction in the number of computational simulations required. In addition, we use hierarchical surplus as an error indi- cator to determine adaptive sparse grids. This allows local refinement in the uncertain domain and/or anisotropic detection with respect to the random model parameters, which further improves computational efficiency. Finally, we incorporate a global optimization technique and propose an iterative algorithm for building the surrogate system for the PPDF with multiple significant modes. Once the surrogate system is determined, the PPDF can be evaluated by sampling the surrogate system directly with very little computational cost. The developed method is evaluated first using a simple analytical density function with multiple modes and then using two synthetic groundwater reactive transport models. The groundwater models represent different levels of complexity; the first example involves coupled linear reactions and the second example simulates nonlinear ura- nium surface complexation. The results show that the aSG-hSC is an effective and efficient tool for Bayesian inference in groundwater modeling in comparison with conventional MCMC sim- ulations. The computational efficiency is expected to be more beneficial to more computational expensive groundwater problems.

Zhang, Guannan↗

Sensitivity-Informed Bayesian Inference for Home PLC Network Models with Unknown Parameters

Bayesian inference is used to calibrate a bottom-up home PLC network model with unknown loads and wires at frequencies up to 30 MHz. A network topology with over 50 parameters is calibrated using global sensitivity analysis and transitional Markov Chain Monte Carlo (TMCMC). The sensitivity-informed Bayesian inference computes Sobol indices for each network parameter and applies TMCMC to calibrate the most sensitive parameters for a given network topology. A greedy random search with TMCMC is used to refine the discrete random variables of the network. This results in a model that can accurately compute the transfer function despite noisy training data and a high dimensional parameter space. The model is able to infer some parameters of the network used to produce the training data, and accurately computes the transfer function under extrapolative scenarios.

42 ENGINEERING↗