Search NASA⌕ Search

SEARCH · Search NASA

Results for “fast machine learning”

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 559 records · Page 31

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Fast jet tagging with MLP-Mixers on FPGAs

We explore the innovative use of MLP-Mixer models for real-time jet tagging and establish their feasibility on resource-constrained hardware like FPGAs. MLP-Mixers excel in processing sequences of jet constituents, achieving state-of-the-art performance on datasets mimicking Large Hadron Collider conditions. By using advanced optimization techniques such as High-Granularity Quantization and Distributed Arithmetic, we achieve unprecedented efficiency. These models match or surpass the accuracy of previous architectures, reduce hardware resource usage by up to 97%, double the throughput, and half the latency. Additionally, non-permutation-invariant architectures enable smart feature prioritization and efficient FPGA deployment, setting a new benchmark for machine learning in real-time data processing at particle colliders.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Benchmarking FFTF LOFWOS Test# 13 using SAM code: Baseline model development and uncertainty quantification

The development and deployment of advanced reactors, such as the sodium-cooled fast reactor (SFR), relies on sophisticated modeling tools to ensure the safety of the design under various transients. The predictive capability of these advanced modeling tools requires validation to garner trust in supporting the licensing of the advanced reactors. For this reason, the International Atomic Energy Agency (IAEA) initiated a coordinated research project (CRP) in 2018 for the analysis of the Fast Flux Test Facility (FFTF) Loss of Flow Without Scram (LOFWOS) Test #13.In this study, we present and discuss the benchmarking efforts of the modern system code SAM on the FFTF LOFWOS Test #13. Further, the SAM baseline model was developed according to the benchmark specification, which included a detailed core model with reactivity feedback. Generally, good agreement was observed between the baseline results and benchmark measurements; however, discrepancies persisted, particularly in predicted fuel assembly coolant outlet temperatures. Utilizing the baseline model, uncertainty quantification (UQ) and sensitivity analysis (SA) were conducted with the assistance of various statistical learning and machine learning methods, including kernel density estimation, Gaussian processes, and Sobol indices. Following the baseline model prediction and UQ and SA results, we discuss the reasons for the simulation discrepancies and propose further improvements to the model. This benchmarking effort adheres to the best-estimate plus uncertainty approach and can serve as a valuable example for supporting risk-informed licensing of advanced reactors.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

MACAW v1.0

The ability to embed molecules in a numeric space is essential in order to build mathematical and machine-learning models describing molecular properties or other processes affected by molecules. MACAW is a cheminformatic tool that allows embedding small molecules into a multidimensional numeric space. In the embedding, each molecule is assigned a numeric vector that captures information of the molecule in relation to other molecules, and that vector can be used as input to mathematical models. Molecules that are more similar to each other are embedded closer in this numeric space, whereas molecules that are more different are embedded further away. One advantage of the MACAW embedding technology compared to established alterantives is that it is fast and does not require extensive computational resources or expertise. In particular, MACAW embeddings can be used as input to mathematical models without the need for variable cleaning or feature selection, saving time and simplifying their use. On the other hand, MACAW also contains methods to generate new molecules and to recommend new molecules satisfying a desired molecular property. The generation of new molecules can be biased based on an input set of molecules, effectively generating molecular diversity around it. In its turn, MACAW's molecular recommendation tool is a novel method for evolving molecules in silico towards a desired molecular specification. In this method, the biased molecular generator tool is applied iteratively in combination with a molecular selection step. As a result, in each iteration the molecules selected by the software are increasingly closer to the desired specification. Both the molecular generation and the molecular recommendation tools are very fast, efficient, and intuitive to use.

Roger, VincentBlay↗

Artificial Intelligence and Machine Learning Support for Probabilistic Fracture Mechanics

In this research, artificial intelligence and machine learning (ML) methods are used to search an uncertain parameter space more efficiently for the most important inputs with respect to response sensitivities. These methods are applied to the Extremely Low Probability of Rupture (xLPR) probabilistic fracture mechanics code used at the U.S. Nuclear Regulatory Commission (NRC) in support of nuclear regulatory research. This report documents two separate but related sub-tasks: (1) ranking important uncertain input features with respect to target outputs, determined by convergence in confidence intervals for increasing sample sizes using simple random sampling; and (2) implementation of a reduced-order surrogate model for fast, approximate sample generation. Unoptimized readily available off-the-shelf ML models were used in both sub-tasks.

97 MATHEMATICS AND COMPUTING↗

Machine Learning for the Zwicky Transient Facility

The Zwicky Transient Facility is a large optical survey in multiple filters producing hundreds of thousands of transient alerts per night. We describe here various machine learning (ML) implementations and plans to make the maximal use of the large data set by taking advantage of the temporal nature of the data, and further combining it with other data sets. We start with the initial steps of separating bogus candidates from real ones, separating stars and galaxies, and go on to the classification of real objects into various classes. Besides the usual methods (e.g., based on features extracted from light curves) we also describe early plans for alternate methods including the use of domain adaptation, and deep learning. In a similar fashion we describe efforts to detect fast moving asteroids. We also describe the use of the Zooniverse platform for helping with classifications through the creation of training samples, and active learning. Finally we mention the synergistic aspects of ZTF and LSST from the ML perspective.

Ashish Mahabal↗

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118- and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

alternating direction method of multipliers↗

Performance Validation of Pulsed Thermal Imaging System for In-Service Applications

Additive manufacturing (AM) is an emerging method for cost-efficient fabrication of complex topology nuclear reactor parts from high-strength corrosion resistance alloys, such as stainless steel and Inconel. AM of metallic structures for nuclear energy applications is currently based on laser powder bed fusion (LPBF) process, which has the capability of melting metallic powder and net shaping the structures with relatively high precision. Some of the challenges with using LPBF method for nuclear manufacturing include the possibility of introducing pores into metallic structures. Integrity of AM structures needs to be evaluated nondestructively because material flaws could lead to premature failures in high temperature nuclear reactor environment. Currently, there exist limited capabilities to evaluate actual AM structures non-destructively. Pulsed Thermography Imaging (PTI) provides a capability for non-destructive evaluation (NDE) of subsurface defects in arbitrary size structures. The PTI method is based on recording material surface temperature transients with infrared (IR) camera following thermal pulse delivered on material surface with flash light. The PTI method has advantages for NDE of actual AM structures because the method involves one-sided non-contact measurements and fast processing of large sample areas captured in one image. Following initial qualification of an AM component for deployment in a nuclear reactor, a PTI system can also be used for in-service nondestructive evaluation (NDE) applications. In this report, we describe recent progress in enhancing PTI capabilities in detecting microscopic defects in metallic specimens. SS316 and IN718 specimens were developed with a pattern of subsurface calibrated flat bottom hole (FBH) defects with diameters from 500µm to 200µm. FBH’s were created with EDM (electron discharge machining) drill. PTI imaging data was processed Spatial Temporal Denoised Thermal Source Separation (STDTSS) unsupervised machine learning (ML) algorithm. We show that defects as small as 200µm in SS316 and IN718 can be detected with STDTSS algorithm. To the best of our knowledge, these are the smallest detected defects which are reported in literature.

42 ENGINEERING↗

2019 Budget Request for the DOE Computational Science Graduate Fellowship (CSGF) Grant

The Department of Energy Computational Science Graduate Fellowship (DOE CSGF) is necessary to meet the continual challenging national workforce needs that arise as computational science and engineering problems continue to grow in scope and complexity. Computational science and engineering (CSE) is a multidisciplinary approach that uses scientific computing to solve practical problems methods and to supply technical tools across the scientific discovery spectrum. In particular, the DOE CSGF emphasizes high-performance computing (HPC) that enables CSE that advances science and engineering in directions important to the DOE and the economy in general. Over the past half-century, HPC has been an essential tool for DOE’s success. During this period, important missions, such as nuclear stockpile stewardship, have turned to HPC as an essential technology. Entire science disciplines, such as biology and cosmology, have been transformed through the augmentation of scientific observation via HPC. At government laboratories and in industry, DOE CSGF alumni are helping push traditional HPC boundaries while contributing to discoveries in high-energy physics, renewable energy, fusion-reactor design, additive manufacturing, nanomaterials for next-generation batteries and transistors, and turbine and advanced nuclear reactor modeling. In addition, HPC is used to address national health needs that will eventually point to cures both by helping cancer researchers manage and analyze huge troves of data, by simulating biological mechanisms, and by accelerating drug development — including continuing to rise to the challenge of pandemic-related research. A 2023 report from the ASCAC Subcommittee on American Competitiveness and Innovation to the ASCR office, “Can the United States Maintain Its Leadership in High-Performance Computing?” says of the Program, “The CSGF program provides a barometer for disciplines that will be of interest to future DOE computing.” An explosion in scientific and technological data has driven the need for increasingly sophisticated HPC to transform those data into scientific understanding. With access to more and more data and the proliferation of HPC, Machine Learning and Artificial Intelligence are experiencing a renaissance, complementing the now well-established use of computational simulation. Indeed, in its September 2020 subcommittee report on “AI/ML, Data Intensive Science and High-Performance Computing”, the DOE Advanced Scientific Computing Advisory Committee (ASCAC) explicitly called for a fellowship program to train computational and data scientists to tackle exascale and data-intensive computing challenges. This collaboration of empirical and theory-based modeling will increasingly inform federal policymakers whose decisions affect American society and future generations, and it requires highly skilled and intellectually agile computational scientists who can support the fast-moving DOE National Laboratory research environment. In fact, the DOE CSGF program has explicitly and consistently addressed this need.

97 MATHEMATICS AND COMPUTING↗

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We suggest a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118-and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Quantum learning without quantum memory

A quantum learning machine for binary classification of qubit states that does not require quantum memory is introduced and shown to perform with the minimum error rate allowed by quantum mechanics for any size of the training set. This result is shown to be robust under (an arbitrary amount of) noise and under (statistical) variations in the composition of the training set, provided it is large enough. This machine can be used an arbitrary number of times without retraining. Its required classical memory grows only logarithmically with the number of training qubits, while its excess risk decreases as the inverse of this number, and twice as fast as the excess risk of an ‘‘estimate-and-discriminate’’ machine, which estimates the states of the training qubits and classifies the data qubit with a discrimination protocol tailored to the obtained estimates.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Rapid failure mode classification and quantification in batteries: A deep learning modeling framework

Unique, rapid identification and quantification of the dominant aging modes in lithium-ion batteries (LiBs) with early and non-specialized test data is a significant scientific challenge. Leveraging synthetic-data, deep-learning (DL) techniques have great potential to enable fast and robust classification and quantification of battery aging modes that produce different patterns of cell aging. This study, for the first time, presents a synthetic–data-based DL modeling framework for rapid and automatic classification and quantification of battery-aging modes and resultant aging with experimental validation. Availing synthetic dQ.dV -1 curves for ~26000 initial conditions and aging modes, the framework classified the dominant aging modes, for cells undergoing fast charge, in fewer than 100 cycles. Upon classification, the framework quantified the evolution of the aging modes, which were often nonuniform with cycling, for 22 gr/NMC532 pouch cells tested up to 600 cycles at different charging rates (1C–9C).

25 ENERGY STORAGE↗

Evaluating Material Design Principles for Calcium-Ion Mobility in Intercalation Cathodes

Multivalent-ion batteries offer an alternative to Li-based technologies, with the potential for greater sustainability, improved safety, and higher energy density, primarily due to their rechargeable system featuring a passivating metal anode. Although a system based on the Ca 2+ /Ca couple is particularly attractive given the low electrochemical plating potential of Ca 2+ , the remaining challenge for a viable rechargeable Ca battery is to identify Ca cathodes with fast ion transport. In this work, a high-throughput computational pipeline is adapted to (1) discover novel Ca cathodes in a largely unexplored space of empty intercalation hosts and (2) develop material design rules for Ca-ion mobility. One candidate from the screening, W 2 O 3 (PO 4 ) 2 , is confirmed to have a low Nudged Elastic Band (NEB) barrier of 168 meV within a one-dimensional (1D) ion percolation topology. This candidate is subsequently synthesized and electrochemically tested, achieving reversible Ca cycling with a capacity of 25 mA h/g. To further accelerate the screening for promising Ca intercalation electrodes, machine learning (ML) Random Forest (RF) and Extreme Gradient Boosting (XGB) classification models are created with local environment descriptors based on a large, structurally and chemically diverse dataset of minimum energy pathways, spanning over 5,000 density functional theory (DFT) site energy calculations. Accuracies of 92% are achieved, material design metrics are quantified, ML force-fields are leveraged in an accelerated iteration of the screening, and a total of 27 novel Ca cathode materials are highlighted for further investigation.

25 ENERGY STORAGE↗

The Effects of Compounded Model Size Reductions on Adversarial Robustness

Recent advances in Edge AI and Tiny Machine Learning (TinyML) have enabled the deployment of machine learning models on resource-constrained environments. However, deploying these models on edge devices, such as micro-controllers, requires significant model footprint reduction through a variety of techniques such as quantization, pruning, and clustering. While these optimization methods offer considerable advantages, they potentially introduce AI-related security vulnerabilities, particularly concerning model robustness with respect to adversarial AI attacks. Prior research has extensively examined the impact of quantization on adversarial robustness; however, the effects of alternative reduction techniques and their combinations remain understudied. This paper investigates the impact of model size reduction techniques on adversarial robustness, when applied individually and combined. We utilized Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks to generate adversarial perturbations for both training and testing data, and then evaluated the models' accuracy under adversarial training conditions. Our findings revealed that reduction techniques generally diminished robustness; although, combining techniques was not found to make robustness any worse than when applied individually. Moreover, specific techniques can potentially enhance resistance to small size perturbations. This research provides insights into the trade-offs between model size reduction and security, establishing a foundation for future investigations into improving adversarial training techniques and methodologies for maintaining robustness while preserving memory footprint benefits.

Austria, Phillipe [ORNL] (ORCID:0000000236223973)↗

Super resolution for root imaging

Premise High‐resolution cameras are very helpful for plant phenotyping as their images enable tasks such as target vs. background discrimination and the measurement and analysis of fine above‐ground plant attributes. However, the acquisition of high‐resolution images of plant roots is more challenging than above‐ground data collection. An effective super‐resolution (SR) algorithm is therefore needed for overcoming the resolution limitations of sensors, reducing storage space requirements, and boosting the performance of subsequent analyses. Methods We propose an SR framework for enhancing images of plant roots using convolutional neural networks. We compare three alternatives for training the SR model: (i) training with non‐plant‐root images, (ii) training with plant‐root images, and (iii) pretraining the model with non‐plant‐root images and fine‐tuning with plant‐root images. The architectures of the SR models were based on two state‐of‐the‐art deep learning approaches: a fast SR convolutional neural network and an SR generative adversarial network. Results In our experiments, we observed that the SR models improved the quality of low‐resolution images of plant roots in an unseen data set in terms of the signal‐to‐noise ratio. We used a collection of publicly available data sets to demonstrate that the SR models outperform the basic bicubic interpolation, even when trained with non‐root data sets. Discussion The incorporation of a deep learning–based SR model in the imaging process enhances the quality of low‐resolution images of plant roots. We demonstrate that SR preprocessing boosts the performance of a machine learning system trained to separate plant roots from their background. Our segmentation experiments also show that high performance on this task can be achieved independently of the signal‐to‐noise ratio. We therefore conclude that the quality of the image enhancement depends on the desired application.

Ruiz‐Munoz, Jose F.↗

Explainability and human intervention in autonomous scanning probe microscopy

The broad adoption of machine learning (ML)-based autonomous experiments (AEs) in material characterization and synthesis requires strategies development for understanding and intervention in the experimental workflow. Here, we introduce and realize a post-experimental analysis strategy for deep kernel learning-based autonomous scanning probe microscopy. This approach yields real-time and post-experimental indicators for the progression of an active learning process interacting with an experimental system. We further illustrate how this approach can be applied to human-in-the-loop AEs, where human operators make high-level decisions at high latencies setting the policies for AEs, and the ML algorithm performs low-level, fast decisions. The proposed approach is universal and can be extended to other techniques and applications such as combinatorial library analysis.

47 OTHER INSTRUMENTATION↗

Integrating Learning and Physics based Computation for Fast Online Transient Analysis

In this work, a novel method that integrates learning and physics based computation is developed for greatly accelerating the simulation of full power system transient trajectories. To solve the dynamic algebraic equations, the method replaces the time-consuming dynamic computation for generator dynamics with trained predictors, while retaining the time-efficient algebraic computation of solving AC-power flow (PF) for power systems. In particular, a predictor is trained for each generator, and the system trajectories are computed by alternating steps of calling the predictors and solving AC-PF. The proposed method also allows fully parallelizable training strategies and a flexible trade-off between training time and testing accuracy. Comprehensive evaluations of the proposed method for transient/dynamic contingency analysis of the New York/New England 16-machine 68-bus power systems demonstrate excellent performance and significant acceleration of computation.

24 POWER TRANSMISSION AND DISTRIBUTION↗

The Feasibility of Incorporating a 3D Velocity Model Into Earthquake Location Around Salt Lake City, UT Using a Physics Informed Neural Network

Earthquake location algorithms typically require travel time calculation. Doing this calculation in 3D, despite advances in algorithm efficiency and computational power, can still be prohibitively expensive in terms of resources and storage. Implementation of high-resolution 3D models in routine earthquake location would be a significant step forward in most of the world. Machine learning algorithms have potential to act as substitutes for travel time calculation algorithms or stored travel time tables. We investigate EikoNet - a physics informed neural network machine learning model that estimates travel times very quickly and comes with negligible memory-overhead. Specifically, we apply EikoNet to the Wasatch Fault Community Velocity Model (WFCVM), a highly detailed and complex 3D velocity model of the Salt Lake City, UT region. While routine locations in the area and studies of the 2020 Magna, UT earthquake sequence used a 1D velocity model, a 3D model may help better our understanding the structure of the major fault in the region. Our primary goal was to test the speed, memory requirements, and accuracy of EikoNet compared to a reference eikonal solver. We find that while the EikoNet is exceedingly fast and requires little memory overhead, achieving acceptable accuracy in estimated travel times is difficult and requires extensive computational resources.

58 GEOSCIENCES↗