Search NASA⌕ Search

SEARCH · Search NASA

Results for “Bayesian network”

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 397 records · Page 22

Methodology on cyber security evaluation in nuclear facilities considering I and C architecture - 224

Cyber security has become a major issue in nuclear facilities recently due to obsolescence of existing analog system and increasing the use of digital system for instrumentation and control (I and C) system. There are several cases which are similar to cyber-attacks in nuclear facilities such as Davis-Besse NPP, Browns Ferry NPP, Hatch NPP, Natanz Nuclear Facility, and Monju NPP. Since the cyber-attack called 'Stuxnet' occurred to a Natanz Nuclear Facility at 2010, the regulatory agencies have developed regulatory guidance for cyber security of nuclear facilities. In this paper, we will propose a methodology on cyber security evaluation in nuclear facilities considering I and C architecture. We will introduce the cyber security evaluation model for I and C system with Bayesian Belief Network (BBN). The cyber security evaluation model for nuclear facilities consists of I and C architecture, cyber threat such as malicious activity of attacker, and mitigation measure against malicious activity. In order to make benchmark model with I and C architecture, cyber threat, and mitigation measure, the likelihood and consequence concepts are used as prior information to the model. Bayesian update can be used to evaluate the cyber security for nuclear facility by calculating posterior information and comparing between prior information and posterior information with the model. Moreover, we will propose the methodology on application of the cyber security to existing PSA by using the cyber security evaluation model with BBN. It presents quantitative information for cyber security against cyber-attack and it is helpful to communicate between licensee and regulator on nuclear facilities. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Advanced data analysis in inertial confinement fusion and high energy density physics

Bayesian analysis enables flexible and rigorous definition of statistical model assumptions with well-characterized propagation of uncertainties and resulting inferences for single-shot, repeated, or even cross-platform data. This approach has a strong history of application to a variety of problems in physical sciences ranging from inference of particle mass from multi-source high-energy particle data to analysis of black-hole characteristics from gravitational wave observations. The recent adoption of Bayesian statistics for analysis and design of high-energy density physics (HEDP) and inertial confinement fusion (ICF) experiments has provided invaluable gains in expert understanding and experiment performance. In this Review, we discuss the basic theory and practical application of the Bayesian statistics framework. We highlight a variety of studies from the HEDP and ICF literature, demonstrating the power of this technique. Due to the computational complexity of multi-physics models needed to analyze HEDP and ICF experiments, Bayesian inference is often not computationally tractable. Two sections are devoted to a review of statistical approximations, efficient inference algorithms, and data-driven methods, such as deep-learning and dimensionality reduction, which play a significant role in enabling use of the Bayesian framework. We provide additional discussion of various applications of Bayesian and machine learning methods that appear to be sparse in the HEDP and ICF literature constituting possible next steps for the community. We conclude by highlighting community needs, the resolution of which will improve trust in data-driven methods that have proven critical for accelerating the design and discovery cycle in many application areas.

47 OTHER INSTRUMENTATION↗

Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial

On top of machine learning (ML) models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and reliability improvement of ML models empowered by UQ has the potential to significantly facilitate the broad adoption of ML solutions in high-stakes decision settings, such as healthcare, manufacturing, and aviation, to name a few. In this tutorial, we aim to provide a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks and the applications of these UQ methods in tackling engineering design as well as prognostics and health management problems. Towards this goal, we start with a comprehensive classification of uncertainty types, sources, and causes pertaining to UQ of ML models. Next, we provide a tutorial-style description of several state-of-the-art UQ methods: Gaussian process regression, Bayesian neural network, neural network ensemble, and deterministic UQ methods focusing on spectral-normalized neural Gaussian process. Established upon the mathematical formulations, we subsequently examine the soundness of these UQ methods quantitatively and qualitatively (by a toy regression example) to examine their strengths and shortcomings from different dimensions. Then, we review quantitative metrics commonly used to assess the quality of predictive uncertainty in classification and regression problems. Afterward, we discuss the increasingly important role of UQ of ML models in solving challenging problems in engineering design and health prognostics. In conclusion, two case studies with source codes available on GitHub are used to demonstrate these UQ methods and compare their performance in the life prediction of lithium-ion batteries at the early stage (case study 1) and the remaining useful life prediction of turbofan engines (case study 2).

97 MATHEMATICS AND COMPUTING↗

Operations for Learning with Graphical Models

This paper is a multidisciplinary review of empirical, statistical learning from a graphical model perspective. Well-known examples of graphical models include Bayesian net- works, directed graphs representing a Markov chain, and undirected networks representing a Markov field. These graphical models are extended to model data analysis and empirical learning using the notation of plates. Graphical operations for simplifying and manipulating a problem are provided including decomposition, differentiation, and the manipulation of probability models from the exponential family. These operations adapt existing techniques from statistics and automatic differentiation to graphs. Two standard algorithm schemes for learning are reviewed in a graphical framework: Gibbs sampling and the expectation maximization algorithm. Some algorithms are developed in this graphical framework including a generalized version of linear regression, techniques for feed-forward networks, and learning Gaussian and discrete Bayesian networks from data. The paper concludes by sketching some implications for data analysis and summarizing some popular algorithms that fall within the framework presented. The main original contributions here are the decomposition techniques and the demonstration that graphical models provide a framework for understanding and developing complex learning algorithms.

Buntine, Wray L.↗

Boron Coordination in Multicomponent Glasses: Analytical Models and Machine Learning With Uncertainty

Borosilicate glasses are extensively used in a variety of applications from kitchenware to nuclear waste immobilization due to the strong network formed by the Si-O-B bond that makes it resistant to chemical corrosion and gives it a low thermal expansion. Boron, however, exists in both trigonal BO3 and tetrahedral BO4 bonds in glass systems, which impacts the chemical durability and thermal resistance of the glass, amongst other properties. Boron coordination (N4), or the ratio of the amount of BO4 to BO3 within a glass, may aid in predicting these properties but is difficult to derive without experimental data due to the complexity of impacts from varied glass compositions and processing factors. For this reason, compositional models have been developed to predict boron coordination, but the models typically include a limited number of glass components. To help fill this gap in the models, in this work, a diverse multicomponent glass dataset of 809 glasses is compiled from a literature search, and then a number of analytical and machine learning (ML) models are trained on the dataset. Previously developed modified Bernstein and modified Du Stebbins analytical models were fitted to update parameters with the new dataset. Then, partially Bayesian neural networks, Gaussian process regressor, and heteroskedastic deterministic neural networks were evaluated. The ML models examined all have different strategies to overcome the potential for overfitting as a result of a limited training dataset, and return results that account for model uncertainty, which can be valuable for understanding model reliability. For the first time, cooling rate is introduced as an input parameter for ML models, showing consistent improvements in performance and solidifying the importance of including parameters outside of composition alone for N4 prediction. The machine learning models examined here show promise in accurate predictions of boron coordination in borosilicate glasses, all achieving R2 values of 0.91.

boron coordination↗

Crowdsourced reliable labeling of safety-rule violations on images of complex construction scenes for advanced vision-based workplace safety

Construction workplace hazard detection requires engineers to analyze scenes manually against many safety rules, which is time-consuming, labor-intensive, and error-prone. Computer vision algorithms are yet to achieve reliable discrimination of anomalous and benign object relations underpinning safety violation detections. Recently developed deep learning-based computer vision algorithms need tens of thousands of images, including labels of the safety rules violated, in order to train deep-learning networks for acquiring spatiotemporal reasoning capacity in complex workplaces. Such training processes need human experts to label images and indicate whether the relationship between the worker, resource, and equipment in the scenes violate spatiotemporal arrangement rules for safe and productive operations. False alarms in those manual labels (labeling no-violation images as having violations) can significantly mislead the machine learning process and result in computer vision models that produce inaccurate hazard detections. Compared with false alarms, another type of mislabels, false negatives (labeling images having violations as “no violations”), seem to have fewer impacts on the reliability of the trained computer vision models.

97 MATHEMATICS AND COMPUTING↗

Making inertial confinement fusion models more predictive

Computer models of inertial confinement fusion (ICF) implosions play an essential role in experimental design and interpretation as well as our understanding of fundamental physics under the most extreme conditions that can be reached in the laboratory. Building truly predictive models is a significant challenge, with the potential to greatly accelerate progress to high yield and ignition. One path to more predictive models is to use experimental data to update the underlying physics in a way that can be extrapolated to new experiments and regimes. We describe a statistical framework for the calibration of ICF simulations using data collected at the National Ignition Facility (NIF). We perform Bayesian inferences for a series of laser shots using an approach that is designed to respect the physics simulation as much as possible and then build a second model that links the individual-shot inferences together. We show that this approach is able to match multiple X-ray and neutron diagnostics for a whole series of NIF “BigFoot” shots. Within the context of 2D radiation hydrodynamic simulations, our inference strongly favors a significant reduction in fuel compression over other known degradation mechanisms (namely, hohlraum issues and engineering perturbations). This analysis is expanded using a multifidelity technique to pick fuel-ablator mix from several candidate causes of the degraded fuel compression (including X-ray preheat and shock timing errors). Finally, we use our globally calibrated model to investigate the extra laser drive energy that would be required to overcome the inferred fuel compression issues in NIF BigFoot implosions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Probabilistic Neural Computing with Stochastic Devices

Abstract The brain has effectively proven a powerful inspiration for the development of computing architectures in which processing is tightly integrated with memory, communication is event‐driven, and analog computation can be performed at scale. These neuromorphic systems increasingly show an ability to improve the efficiency and speed of scientific computing and artificial intelligence applications. Herein, it is proposed that the brain's ubiquitous stochasticity represents an additional source of inspiration for expanding the reach of neuromorphic computing to probabilistic applications. To date, many efforts exploring probabilistic computing have focused primarily on one scale of the microelectronics stack, such as implementing probabilistic algorithms on deterministic hardware or developing probabilistic devices and circuits with the expectation that they will be leveraged by eventual probabilistic architectures. A co‐design vision is described by which large numbers of devices, such as magnetic tunnel junctions and tunnel diodes, can be operated in a stochastic regime and incorporated into a scalable neuromorphic architecture that can impact a number of probabilistic computing applications, such as Monte Carlo simulations and Bayesian neural networks. Finally, a framework is presented to categorize increasingly advanced hardware‐based probabilistic computing technologies.

Misra, Shashank↗

Search for anomalous Wtb couplings and flavour-changing neutral currents in t-channel single top quark production in pp collisions at $\sqrt{s} =$ 7 and 8 TeV

Single top quark events produced in the t channel are used to set limits on anomalous Wtb couplings and to search for top quark flavour-changing neutral current (FCNC) interactions. The data taken with the CMS detector at the LHC in proton-proton collisions at $ \sqrt{s}=7 $ and 8 TeV correspond to integrated luminosities of 5.0 and 19.7 fb$^{−1}$, respectively. The analysis is performed using events with one muon and two or three jets. A Bayesian neural network technique is used to discriminate between the signal and backgrounds, which are observed to be consistent with the standard model prediction. The 95% confidence level (CL) exclusion limits on anomalous right-handed vector, and left- and right-handed tensor Wtb couplings are measured to be |f$_{V}^{R}$ | < 0.16, |f$_{T}^{L}$ | < 0.057, and − 0.049 < f$_{T}^{R}$ < 0.048, respectively. For the FCNC couplings κ$_{tug}$ and κ$_{tcg}$, the 95% CL upper limits on coupling strengths are |κ$_{tug}$|/Λ < 4.1 × 10$^{− 3}$ TeV$^{−1}$ and |κ$_{tcg}$|/Λ < 1.8 × 10$^{− 2}$ TeV$^{−1}$, where Λ is the scale for new physics, and correspond to upper limits on the branching fractions of 2.0 × 10$^{−5}$ and 4.1 × 10$^{−4}$ for the decays t → ug and t → cg, respectively.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Probabilistic Model-Based Diagnostic Framework for Nuclear Engineering Systems

A fault diagnostic framework was investigated in this study for applications in thermal–hydraulic systems of nuclear power plants. The proposed framework consists of quantitative model-based diagnosis, statistical change detection and probabilistic reasoning. The use of physics-based diagnostic models provides high detection sensitivity and allows noise and measurement uncertainty to be incorporated robustly. Performance-related parametric models for each component are constructed based on first principles. Numerical model residuals are generated using the concept of analytical redundancy. Statistical change detection methods are employed to detect non-zero residuals in the presence of uncertainty. The diagnosis task is performed using Bayesian inference to detect and localize possible faults. Application to a single-phase heat exchanger for demonstration showed that the proposed probabilistic framework can provide improved results in comparison with traditional approaches while remaining less sensitive to false alarms in the presence of measurement and modeling uncertainty.

Bayesian network↗

Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?

The Southern Photometric Local Universe Survey (S-PLUS) is a novel project that aims to map the Southern Hemisphere using a twelve filter system, comprising five broad-band SDSS-like filters and seven narrow-band filters optimized for important stellar features in the local universe. In this paper we use the photometry and morphological information from the first S-PLUS data release (S-PLUS DR1) cross-matched to unWISE data and spectroscopic redshifts from Sloan Digital Sky Survey DR15. We explore three different machine learning methods (Gaussian Processes with GPz and two Deep Learning models made with TensorFlow) and compare them with the currently used template-fitting method in the S-PLUS DR1 to address whether machine learning methods can take advantage of the twelve filter system for photometric redshift prediction. Using tests for accuracy for both single-point estimates such as the calculation of the scatter, bias, and outlier fraction, and probability distribution functions (PDFs) such as the Probability Integral Transform (PIT), the Continuous Ranked Probability Score (CRPS) and the Odds distribution, we conclude that a deep-learning method using a combination of a Bayesian Neural Network and a Mixture Density Network offers the most accurate photometric redshifts for the current test sample. In conclusion, it achieves single-point photometric redshifts with scatter (σ NMAD ) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r_auto magnitudes between 16 and 21.

79 ASTRONOMY AND ASTROPHYSICS↗

Integrating field observations and process-based modeling to predict watershed water quality under environmental perturbations

Watersheds play a critical role in supplying water resources needed for human use and ecosystem health. Understanding and predicting how, when, and where changes in the quantity and quality of water resources occur under different environmental stresses including extreme events is crucial for sustainable management of water resources under a changing environment. However, few studies have attempted to quantify or identify the factors and process interactions controlling the impact of extreme events across water-shed systems. Only few large-scale studies include coordinated monitoring and modeling efforts, which limits our ability to assess the large-scale impact of extreme events on water supply and quality. Methods are lacking to propagate uncertainty in process understanding through an integrated hydro-biogeochemical model framework and evaluate its importance, thus failing to take full advantage of the information potentially available through transformative advances in characterization technologies from high-resolution mass spectrometry to airborne and satellite-based remote sensing. There are consequent risks to our nations water security and to human and ecosystem health that may become exacerbated with the increasing frequency of extreme events that is projected for the coming decades. This paper reviews the current status of watershed science for both water quantity and quality and identifies critical gaps in our current knowledge and modeling capability in addressing the emergent needs in predicting watershed hydrologic and biogeochemical responses (i.e., water quantity and quality) under natural and anthropogenic perturbations. We highlight the need to (1) understand how environmental perturbations including extreme events like floods and droughts propagate through watershed systems and assess their short- and long-term impacts on watershed biogeochemistry, water quality and their recovery pathways; (2) develop and improve a watershed water quality model that reflects the state of scientific understanding gained from observations; and (3) construct a data-model fusion system for watershed characterization, process identification, and mechanistic model parameterization. A large base of modeling, monitoring and data capabilities have been built by various federal government agencies given the relevance of water to their critical missions. An emerging need is to build an integrated national capability for watershed water availability and quality that can address water-related missions across multiple federal agencies.

13 HYDRO ENERGY↗

Electronic structure prediction of multi-million atom systems through uncertainty quantification enabled transfer learning

The ground state electron density — obtainable using Kohn-Sham Density Functional Theory (KS-DFT) simulations — contains a wealth of material information, making its prediction via machine learning (ML) models attractive. However, the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation, making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system configurations. Here, we address this fundamental challenge by employing transfer learning to leverage the multi-scale nature of the training data, while comprehensively sampling system configurations using thermalization. Our ML models are less reliant on heuristics, and being based on Bayesian neural networks, enable uncertainty quantification. We show that our models incur significantly lower data generation costs while allowing confident — and when verifiable, accurate — predictions for a wide variety of bulk systems well beyond training, including systems with defects, different alloy compositions, and at multi-million-atom scales. Moreover, such predictions can be carried out using only modest computational resources.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Uranium particle age dating, aggregation, and model age best estimators

We present important aspects of uranium particle age dating by Large-Geometry Secondary Ion Mass Spectrometry (LG-SIMS) that can introduce bias and increase model age uncertainties, especially for small, young, and/or low-enriched particles. This metrology is important for applications related to International Nuclear Safeguards. We explore influential factors related to model age estimation, including the effects of evolving surface chemistry on inter-element measurements of particles (e.g., Th and U), detector background, and aggregation methods using simulated and actual particle samples. We introduce a new model age estimator, called “mid68”, that supplements 95% confidence intervals, providing a “best estimate” and uncertainty about the most likely age. The mid68 estimator can be calculated using the Feldman and Cousins method or Bayesian methods and provides a value with a symmetric uncertainty that can be used for calculations and approximate aggregation of processed model age values when the raw data and correction factors are not available. For particles yielding low 230 Th counts amidst nonzero detector background, their underlying model age probability distributions are asymmetric, so the mid68 estimator provides additional robust information regarding the underlying model age likelihood. This study provides a comprehensive and timely examination of critical aspects of uranium particle age dating as more laboratories establish particle chronometry capabilities.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Quantified uncertainties in fission yields from machine learning

As machine learning methods gain traction in the nuclear physics community, especially those methods that aim to propagate uncertainties to unmeasured quantities, it is important to understand how the uncertainty in the training data coming either from theory or experiment propagates to the uncertainty in the predicted values. Gaussian Processes and Bayesian Neural Networks are being more and more widely used, in particular to extrapolate beyond measured data. However, studies are typically not performed on the impact of the experimental errors on these extrapolated values. In this work, we focus on understanding how uncertainties propagate from input to prediction when using machine learning methods. We use a Mixture Density Network (MDN) to incorporate experimental error into the training of the network and construct uncertainties for the associated predicted quantities. Systematically, we study the effect of the size of the experimental error, both on the reproduced training data and extrapolated predictions for fission yields of actinides.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

EFIT-Prime: Probabilistic and physics-constrained reduced-order neural network model for equilibrium reconstruction in DIII-D

We introduce EFIT-Prime, a novel machine learning surrogate model for EFIT (Equilibrium FIT) that integrates probabilistic and physics-informed methodologies to overcome typical limitations associated with deterministic and ad hoc neural network architectures. EFIT-Prime utilizes a neural architecture search-based deep ensemble for robust uncertainty quantification, providing scalable and efficient neural architectures that comprehensively quantify both data and model uncertainties. Physically informed by the Grad–Shafranov equation, EFIT-Prime applies a constraint on the current density J tor and a smoothness constraint on the first derivative of the poloidal flux, ensuring physically plausible solutions. Furthermore, the spatial location of the diagnostics is explicitly incorporated in the inputs to account for their spatial correlation. Extensive evaluations demonstrate EFIT-Prime's accuracy and robustness across diverse scenarios, most notably showing good generalization on negative-triangularity discharges that were excluded from training. Timing studies indicate an ensemble inference time of 15 ms for predicting a new equilibrium, offering the possibility of plasma control in real-time, if the model is optimized for speed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Overview and Recommendations for Cyber Risk Assessment in Nuclear Power Plants

Digital instrumentation and control (I&C) systems are being deployed in nuclear power plants (NPPs) for both existing and advanced reactor designs. As I&C systems become more digitized to allow features like near autonomous control and remote operation, they introduce greater cyber risk to NPPs. Cyberattacks targeting industrial control systems (ICSs) are growing in both qualities and capabilities, which indicates that cybersecurity needs to be an integral part of risk assessment in the industry. Although there are some risk assessment methods in traditional information technology (IT) cybersecurity, the differences between IT and ICS cybersecurity make it infeasible to apply these risk assessment methods directly to ICSs. Some research has focused on risk assessment methods for ICSs, but few studies focus on applications to NPPs. Ideal risk frameworks for the nuclear industry are dynamic and account for system dependencies; this survey review focuses on such risk assessment methods both in and outside the nuclear field. In this article, the major challenges in cybersecurity risk assessment research are pointed out, and further research suggestions and considerations for cyber risk assessment in I&C systems are identified.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Deep inference of simulated strong lenses in ground-based surveys

The large number of strong lenses discoverable in future astronomical surveys will likely enhance the value of strong gravitational lensing as a cosmic probe of dark energy and dark matter. However, leveraging the increased statistical power of such large samples will require further development of automated lens modeling techniques. We show that deep learning and simulation-based inference (SBI) methods produce informative and reliable estimates of parameter posteriors for strong lensing systems in ground-based surveys. We present the examination and comparison of two approaches to lens parameter estimation for strong galaxy-galaxy lenses — Neural Posterior Estimation (NPE) and Bayesian Neural Networks (BNNs). We perform inference on 1-, 5-, and 12-parameter lens models for ground-based imaging data that mimics the Dark Energy Survey (DES). We find that NPE outperforms BNNs, producing posterior distributions that are more accurate, precise, and well-calibrated for most parameters. For the 12-parameter NPE model, the calibration is consistently within <10% of optimal calibration for all parameters, while the BNN is rarely within 20% of optimal calibration for any of the parameters. Similarly, residuals for most of the parameters are smaller (by up to an order of magnitude) with the NPE model than the BNN model. This work takes important steps in the systematic comparison of methods for different levels of model complexity.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗