Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “hyperparameter”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Hyper Parameter Tuning in Neural Optical Image Categorizer for the E-log (NOICE

The Fermilab Accelerator Division Electronic logbook (E-log) is a record of all the activities and events in the Division for the past 10 years and more. The Elog search function is a valuable resource and the institutional memory of the accelerator complex. About 300,000 files are stored in the E-log, of which the vast majority are images attached to entries and comments. The visual information contained in the images is not presently searchable. The goal of team NOICE (Neural Optical Image Categorizer for the E-log) was to design a neural network able to produce label categories for these images for use by searches. The group developed a dataset and trained a convolutional neural network (CNN) with optimized hyperparameter. Final performance metrics are presented.

Njekeu, Terence Franck↗
DOE OSTI2020

Updates to Relevance Vector Machine: Multiclass Classification, Variable Selection, and Proof-of-Concept Application to Safeguards Fresh Fuel Verification using List-Mode Neutron Collar Data

To expand the capabilities of safeguards authorities to verify the integrity of fresh fuel assemblies, Oak Ridge National Laboratory has retrofit the existing electronics of the JCC-71 uranium neutron coincidence collar, which contains 18 3 He neutron detectors and an external 241 AmLi(α, n) neutron interrogation source arranged to surround a fresh nuclear fuel assembly. The new electronics system allows analysts to record list-mode neutron multiplicity data in addition to the singles and doubles rates that are currently measured. Based on previous proof-of-concept research, analysis of these new data will identify off-normal fuel configurations in an assembly and characterize or localize the specific partial fuel defects. The purpose of this report it to document the analysis algorithm development and then to demonstrate its capability for the safeguards verification of fresh fuel assemblies using list mode neutron collar data. To analyze the complex list-mode data collected with the upgraded uranium neutron collar, multivariate classification algorithms are being developed using a novel classification method, the relevance vector machine. This approach may be applied to multiclass problems to estimate the probability that test data belongs to one of many possible classes of data. In addition, our method identifies the most useful variables/channels for making predictions, which illuminates the basis for the model’s predictions, and this interpretability is largely unique among data analytics methods. Variable selection occurs during model training and parameter tuning and does not need any external hyperparameter tuning routines. Finally, we apply the modified relevance vector machine to a simulated dataset of list-mode neutron collar data generated with the radiation transport code MCNP. The method can correctly identify off-normal fuel configurations, categorize the data according to four fuel defect scenarios, and rank the channels in the data according to prediction utility. For nuclear safeguards applications, it is concluded that this method has the potential to increase the sensitivity and reliability to detect missing fuel rods from a standard 17 x 17 Pressurized Water Reactor (PWR) fresh fuel assembly. Within this analysis, “off-normal” (i.e., missing fuel rods) were correctly classified in 17 simulated test scenarios with one quarter (25%) of the fresh fuel rods missing using a training data set of 58 simulated measurements.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2020

Random Forest Optimization for Radionuclide Identification

Radionuclide identification through gamma-ray spectroscopy is an indispensable tool in combatting the illicit smuggling of nuclear material. The radionuclide identification devices used in the field need to provide ready-made answers to non-experts, and therefore require sophisticated algorithms that can interpret the underlying data. We investigated the Random Forest classifier as a tool for identifying the radionuclide that is consistent with the data. We were provided with training and validations data sets and used them to optimize the two hyperparameters of the classifiers: maximum features required, and minimum samples used to split each node. The F1 score, a harmonic mean of precision and recall, was used to evaluate the performance of each built classifier. We found the optimal performance with minimum samples of 5 and maximum features of 50, with the F1 score of 0.95.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2020

Optimizing Classifiers for Radionuclide Identification

Identifying threat nuclear materials is a critical for the prevention of acts of nuclear terrorism on the homeland. For this purpose, many radionuclide identification devices are deployed in the field. However, these will not necessarily be in the hands of non-experts, therefore these devices need to provide ready-made answers for the personnel in the field. This is where advanced algorithms are employed to both interpret the data and provide the identification of the nuclear material being interrogated. We took a machine learning approach to identification, by using training and validation data sets to create and optimize classifiers which determine which radionuclide is consistent with the data. The classifiers investigated were the Random Forest, Decision Tree, Support Vector Machine, and XG Boost and their performance was judged using the F1 Score for both hyperparameter tuning and comparison. In the end, we found out that the Random Forest Classifier worked the best based off the F1 Score they got which was 0.98.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2021

Evaluating Scalograms for Seismic Event Denoising

Denoising contaminated seismic signals for later processing is a fundamental problem in seismic signals analysis. The most straightforward denoising approach, using spectral filtering, is not effective when noise and seismic signal occupy the same frequency range. Neural network approaches have shown success denoising local signal when trained on short-time Fourier transform spectrograms (Zhu et al 2018; Tibi et al 2021). Scalograms, a wavelet-based transform, achieved ~15% better reconstruction as measured by dynamic time warping on a seismic waveform test set than spectrograms, suggesting their use as an alternative for denoising. We train a deep neural network on a scalogram dataset derived from waveforms recorded by the University of Utah Seismograph Stations network. We find that initial results are no better than a spectrogram approach, with additional overhead imposed by the significantly larger size of scalograms. A robust exploration of neural network hyperparameters and network architecture was not performed, which could be done in follow on work.

58 GEOSCIENCES↗
DOE OSTI2021

A Projected Network Model of Online Disinformation Cascades

Within the past half-decade, it has become overwhelmingly clear that suppressing the spread of deliberate false and misleading information is of the utmost importance for protecting democratic institutions. Disinformation has been found to come from both foreign and domestic actors, but the effects from either can be disastrous. From the simple encouragement of unwarranted distrust to conspiracy theories promoting violence, the results of disinformation have put the functionality of American democracy under direct threat. Present scientific challenges posed by this problem include detecting disinformation, quantifying its potential impact, and preventing its amplification. We present a model on which we can experiment with possible strategies toward the third challenge: the prevention of amplification. This is a social contagion network model, which is decomposed into layers to represent physical, ''offline'', interactions as well as virtual interactions on a social media platform. Along with the topological modifications to the standard contagion model, we use state-transition rules designed specifically for disinformation, and distinguish between contagious and non-contagious infected nodes. We use this framework to explore the effect of grassroots social movements on the size of disinformation cascades by simulating these cascades in scenarios where a proportion of the agents remove themselves from the social platform. We also test the efficacy of strategies that could be implemented at the administrative level by the online platform to minimize such spread. These top-down strategies include banning agents who disseminate false information, or providing corrective information to individuals exposed to false information to decrease their probability of believing it. We find an abrupt transition to smaller cascades when a critical number of random agents are removed from the platform, as well as steady decreases in the size of cascades with increasingly more convincing corrective information. Finally, we compare simulated cascades on this framework with real cascades of disinformation recorded on Whatsapp surrounding the 2019 Indian election. We find a set of hyperparameter values that produces a distribution of cascades matching the scaling exponent of the distribution of actual cascades recorded in the dataset. We acknowledge the available future directions for improving the performance of the framework and validation methods, as well as ways to extend the model to capture additional features of social contagion.

42 ENGINEERING↗
DOE OSTI2021

Machine Learning Assisted Safety Modeling and Analysis of Advanced Reactors

With the advances in computational power and numerical methods, analysts can now rely on first-principle simulations to predict ultra-fine details in a variety of applications. Advances in machine learning (ML) have produced algorithms that can now learn high-level abstractions via hierarchical models. This project aims to leverage advances in ML techniques and the available high-resolution simulation data to develop a novel modeling and simulation (M\&S) methodology for reactor safety analysis. While application-agnostic ML techniques are available, complex physics constraints need to be incorporated into ML techniques to build ML-based closures for computationally efficient predictive simulations. This project intends to develop a physics-guided data-driven multi-scale methodology for M\&S of advanced reactors. The project focuses on thermal fluid (T/F) phenomena, which play major roles in advanced reactor safety. Specifically, we propose a data-driven coarse-mesh turbulence model based on local flow features for the transient analysis of thermal mixing and stratification in a sodium-cooled fast reactor (SFR). The model has a coarse-mesh setup to ensure computational efficiency, while it is trained by fine-mesh computational fluid dynamics (CFD) data with Reynolds-averaged Navier-Stokes (RANS) turbulence model to ensure accuracy. Three different neural networks are developed and tested for loss-of-flow transients in the hot pool of SFR, i.e. the densely connected convolutional neural network (DCNN), long-short-term-memory network based on proper orthogonal decomposition (POD-LSTM), and the DCNN informed by LSTM (DCNN-LSTM). The performances of these three neural networks are evaluated based on baseline models. The DCNN-LSTM model has been chosen for further hyperparameter optimization. Furthermore, based on a simplified two-dimensional case, uncertainty quantification (UQ) of the developed ML-based closure are investigated with three methods, i.e. Monte Carlo dropout, deep ensemble, and Bayesian neural network. The developed ML-based turbulent viscosity closure relation based on deep ensemble is then integrated into the system analysis module SAM and serves as a term in the conservation equations. Such a SAM-ML based procedure guarantees that the obtained results are consistent with the physical constraints of the thermal-fluid system. The SAM-ML simulation on the same loss-of-flow transient showed comparable accuracy with the CFD simulation but with a much coarser mesh setup. Last but not least, the ML-based closure improvement with the support of higher-fidelity data from large eddy simulation (LES) is discussed. As a first step towards this direction, a baseline LES simulation is performed to obtain comparable data with RANS results. Based on the early results, future investigation on further improving the ML-based closure is discussed. We believe the developed approach that combines scientific machine learning with nuclear system analysis code can benefit the advanced reactor community as more accurate safety analyses will better characterize reactor safety margins and reduce licensing efforts.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

User Manual - HydraGNN: Distributed PyTorch Implementation of Multi-Headed Graph Convolutional Neural Networks

This document serves as user manual for HydraGNN, a scalable graph neural network (GNN) architecture that allows for a simultaneous prediction of multiple target properties using multi-task learning (MTL). The HydraGNN architecture is constructed by successive superposition of three different sets of layers. The first set is made of message-passing layers to exchange information across nodes in the graph and use this to update the nodal features. The second set is made of global pooling layers that aggregate information from all the nodes in the graph and map it into a scalar, and is needed only for global target properties that are related to the entire graph. The third set of layers is dedicated to the implementation of MTL, which is enabled by forking of the architecture into separate heads, each one of them dedicated to the predictive task of one specific target property. Through an object-oriented programming paradigm, HydraGNN is templated over different message-passing policies, which allows for a user-friendly hyperparameter study to assess the sensitivity of the predictive performance of the HydraGNN architecture on a specific dataset with respect to the choice of the message-passing policy. The object-oriented paradigm used by HydraGNN also allows for a user-friendly inclusion of newly developed message passing policies within the existing framework. HydraGNN supports distributed computing capabilities for scalable data reading and scalable training on leadership-class supercomputers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Improved Subseasonal Forecasting of Extreme Polar Vortices Using Machine Learning

Our research was focused on forecasting the position and shape of the winter stratospheric polar vortex at a subseasonal timescale of 15 days in advance. To achieve this, we employed both statistical and neural network machine learning techniques. The analysis was performed on 42 winter seasons of reanalysis data provided by NASA giving us a total of 6,342 days of data. The state of the polar vortex for determined by using geometric moments to calculate the centroid latitude and the aspect ratio of an ellipse fit onto the vortex. Timeseries for thirty additional precursors were calculated to help improve the predictive capabilities of the algorithm. Feature importance of these precursors was performed using random forest to measure the predictive importance and the ideal number of precursors. Then, using the precursors identified as important, various statistical methods were tested for predictive accuracy with random forest and nearest neighbor performing the best. An echo state network, a type of recurrent neural network that features sparsely connected hidden layer and a reduced number of trainable parameters that allows for rapid training and testing, was also implemented for the forecasting problem. Hyperparameter tuning was performed for each methods using a subset of the training data. The algorithms were trained and tuned on the first 41 years of data, then tested for accuracy on the final year. In general, the centroid latitude of the polar vortex proved easier to predict than the aspect ratio across all algorithms. Random forest outperformed other statistical forecasting algorithms overall but struggled to predict extreme values. Forecasting from echo state network suggested a strong predictive capability past 15 days, but further work is required to fully realize the potential of recurrent neural network approaches.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

ARENA: Adversary-Resistant Evolving Neural Architectures

Neural networks are becoming the cornerstone for national security prediction tasks. However, designing them requires significant research and trial/error, as they have many hyperparameters, including their computation graph (“architecture”). Neural architecture search (NAS) employs secondary optimizers to search for architectures maximizing objectives like accuracy. Evolutionary algorithms (EAs) are the most used class of optimizer for NAS. However, existing Python libraries for writing EAs limit the complexity of experiments a user can design. In this project, we built ARENA, a Python framework that encodes complex, hyper-realistic EAs. ARENA collects detailed information as it runs and is flexible enough to encode non-EA search algorithms. We tested ARENA on 4 toy optimization problems by encoding 3 search algorithms for each—random search, an EA, and simulated annealing. We also designed an EA that performs NAS on the MNIST dataset. Our experiments suggest the potential for immediate mission impact through solving lab-wide optimization problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Correspondence of NNGP Kernel and the Matérn Kernel

Kernels representing limiting cases of neural network architectures have recently gained popularity. However, the application and performance of these new kernels compared to existing options, such as the Matérn kernel, is not well studied. We take a practical approach to explore the neural network Gaussian process (NNGP) kernel and its application to data in Gaussian process regression. We first demonstrate the necessity of normalization to produce valid NNGP kernels and explore related numerical challenges. We further demonstrate that the predictions from this model are quite inflexible, and therefore do not vary much over the valid hyperparameter sets. We then demonstrate a surprising result that the predictions given from the NNGP kernel correspond closely to those given by the Matérn kernel under specific circumstances, which suggests a deep similarity between overparameterized deep neural networks and the Matérn kernel. Finally, we demonstrate the performance of the NNGP kernel as compared to the Matérn kernel on three benchmark data cases, and we conclude that for its flexibility and practical performance, the Matérn kernel is preferred to the novel NNGP in practical applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Rapid Optimization of Total Variation with Applications in Imaging, Additive Manufacturing, and Qualification

Total Variation optimization penalizes the gradient of a control variable or state. While this work focuses on image processing in particular, it has also found applications in inverse problems and topology optimization. In image processing, the goal is to maintain faithfulness to the original image while denoising and/or deblurring. Additionally, bilevel optimization over the spatially varying regularization weights can illuminate interfaces such as damage regions and other anomalies. We will address two fundamental challenges with TV-optimization: (i) the typical slow convergence of existing TV-optimization methods, and (ii) the selection of spatially varying TV parameters to promote interface detection. Additionally, we will apply such techniques to image data collected in additive manufacturing. In said context, stochasticity in build events induces flaws in the manufactured piece, compromising the integrity of said part. There is a critical need for in-situ monitoring to spot anomalies once they form, and in this setting we apply our total variation and hyperparameter solvers. We will develop a customized algorithm based on for extreme-scale TV-optimization that achieves super-linear or quadratic-convergence, a critical property for real-time, image-by-image analysis. A worst-case outcome is a preprocessing step that enhances image quality in-situ, specifically for out-of-focus and noisy images.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Theoretical and methodological challenges in hierarchical Bayesian inference for model-form uncertainty

This report describes challenges associated with the hierarchical Bayesian approach to inform model-form uncertainty (MFU) representations, which are parameterized modifications to a mathematical models’ governing equations to express uncertainty in form of the equations. To inform model-form uncertainties, hierarchical Bayesian inference is often employed. Here, the MFU parameters are distributed parametrically, and the hyperparameters of the parametric distribution are informed through Bayesian inference, with the aim of determining the MFU parameter distribution that best agrees with calibration data. In practice, however, we have found the hierarchical Bayesian approach falls short of this aim. We discuss theoretical and methodological challenges of the approach, and we present several numerical demonstrations of these challenges. To conclude, we suggest promising alternative approaches for future investigation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

User Manual - HydraGNN v5.0: Distributed Implementation of Multi-Tasking Graph Neural Networks

This document serves as the user manual for HydraGNN v5.0, a scalable graph neural network (GNN) architecture for simultaneous prediction of multiple target properties using multi-task learning (MTL). This version of HydraGNN has been developed primarily to support the development, training, and deployment of predictive graph-based deep learning (DL) models for atomistic materials modeling. HydraGNN is templated over 13 message-passing policies, including invariant models (GIN, PNA, PNAPlus, GAT, MFC, CGCNN, SAGE, SchNet, DimeNet) and equivariant models (EGNN, PNAEq, PAINN, MACE), and supports distributed training via distributed data parallelism (DDP), DeepSpeed, and Fully Sharded Data Parallelism (FSDP) on leadership-class supercomputers. Although HydraGNN can be applied to problems beyond atomistic materials modeling, its current use is confined to homogeneous graphs. Additional capabilities include machine-learned interatomic potentials with energy-conserving forces, General, Powerful, and Scalable Graph Transformer (GraphGPS) global attention, periodic boundary conditions, hyperparameter optimization, mixed-precision training, and uncertainty quantification.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

An intelligent Data Delivery Service for and beyond the ATLAS experiment

The intelligent Data Delivery Service (iDDS) has been developed to cope with the huge increase of computing and storage resource usage in the coming LHC data taking. It has been designed to intelligently orchestrate workflows and data management systems, decoupling data pre-processing, delivery, and primary processing in large scale workflows. It is an experiment-agnostic service that has been deployed to serve data carousel (orchestrating efficient processing of tape-resident data), machine learning hyperparameter optimization, active learning, and other complex multi-stage workflows defined via DAG (Directed Acyclic Graph), CWL (Common Workflow Language) and other descriptions, including a growing number of analysis workflows. We will at first introduce some deployed use cases in a summary. Then we will focus on new improvements and use cases under developments in ATLAS, Rubin Observatory and sPHENIX, together with future efforts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Non-trivial symmetries in quantum landscapes and their resilience to quantum noise

Very little is known about the cost landscape for parametrized Quantum Circuits (PQCs). Nevertheless, PQCs are employed in Quantum Neural Networks and Variational Quantum Algorithms, which may allow for near-term quantum advantage. Such applications require good optimizers to train PQCs. Recent works have focused on quantum-aware optimizers specifically tailored for PQCs. However, ignorance of the cost landscape could hinder progress towards such optimizers. In this work, we analytically prove two results for PQCs: (1) We find an exponentially large symmetry in PQCs, yielding an exponentially large degeneracy of the minima in the cost landscape. Alternatively, this can be cast as an exponential reduction in the volume of relevant hyperparameter space. (2) We study the resilience of the symmetries under noise, and show that while it is conserved under unital noise, non-unital channels can break these symmetries and lift the degeneracy of minima, leading to multiple new local minima. Based on these results, we introduce an optimization method called Symmetry-based Minima Hopping (SYMH), which exploits the underlying symmetries in PQCs. Our numerical simulations show that SYMH improves the overall optimizer performance in the presence of non-unital noise at a level comparable to current hardware. Overall, this work derives large-scale circuit symmetries from local gate transformations, and uses them to construct a noise-aware optimization method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Neural Ordinary Differential Equations for Nonlinear System Identification

Neural ordinary differential equations (NODE) have been recently proposed as a promising approach for nonlinear system identification tasks. In this work, we systematically compare their predictive performance with current state-of-the-art nonlinear and classical linear methods. In particular, we present a quantitative study comparing NODE's performance against neural state-space models and classical linear system identification methods and evaluate their inference speed and prediction performance on open-loop errors across eight different dynamical systems. The experiments show that NODEs can consistently improve the prediction accuracy by order of magnitude compared to benchmark methods. Besides improved accuracy, we also observed that NODEs are less sensitive to hyperparameters compared to neural state-space models by paying the cost of increased computation at the inference time.

machine leaning, system identification, physics in↗