SEARCH · Engineering Papers

Results for “Training Time”

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.

SourceResearch connectionFrom yearThrough year

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

At least 325 records · Page 18

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Enabling Real-Time Communication in Multi-Agent Systems: A Graph Neural Network Based Approach

Global connectivity enables effective coordination in Multi-Agent Systems (MAS). Solving these connection problems under hardware constraints is an NP-hard non-Euclidean Degree Constrained Minimum Spanning Tree (DCMST) problem. Prior MAS controllers coordinate team movement for task completion and collision avoidance; some considering Line-of-Sight (LOS) maintenance but prioritizing flexibility over guarantees. Evolutionary Algorithms (EA) have been shown to find good solutions for DCMST, but their performance degrades with larger populations required to support a large MAS. We present a method based on edge graph attention networks, trained offline to reduce online computation times. Empirical comparisons with greedy polynomial-time solvers and EA show that our method leverages latent graph information to consistently find constraint-satisfying solutions in less time.

connectivity maintenance↗

DOE OSTI2025

Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem

Three-dimensional target identification using scattering techniques requires high accuracy solutions and very fast computations for real-time predictions in some critical applications. We first train a deep neural operator (DeepONet) to solve wave propagation problems described by the Helmholtz equation in a domain without scatterers but at different wavenumbers and with a complex absorbing boundary condition. We then design two classes of fast meta-solvers by combining DeepONet with either relaxation methods, such as Jacobi and Gauss-Seidel, or with Krylov methods, such as GMRES and BiCGStab, using the trunk basis of DeepONet as a coarse-scale preconditioner. We leverage the spectral bias of neural networks to account for the lower part of the spectrum in the error distribution while the upper part is handled inexpensively using relaxation methods or fine-scale preconditioners. The meta-solvers are then applied to solve scattering problems with different shape of scatterers, at no extra training cost. We first demonstrate that the resulting meta-solvers are shape-agnostic, fast, and robust, whereas the standard standalone solvers may even fail to converge without the DeepONet. We then apply both classes of meta-solvers to scattering from a submarine, a complex three-dimensional problem. We achieve very fast solutions, especially with the DeepONet-Krylov methods, which require orders of magnitude fewer iterations than any of the standalone solvers.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Large Scale Caching and Streaming of Training Data for Online Deep Learning

The training of deep neural network models on large data remains a difficult problem, despite progress towards scalable techniques. In particular, there is a mismatch between the random but predetermined order in which AI flows select training samples and the streaming I/O patterns for which traditional HPC data storage (e.g., parallel file systems) are designed. In addition, as more data are obtained, it is feasible neither simply to train learning models incrementally, due to catastrophic forgetting (i.e., bias towards new samples), nor to train frequently from scratch, due to prohibitive time and/or resource constraints. In this paper, we study data management techniques that combine caching and streaming with rehearsal support in order to enable efficient access to training samples in both offline training and continual learning. We revisit state-of-art streaming approaches based on data pipelines that transparently handle prefetching, caching, shuffling, and data augmentation, and discuss the challenges and opportunities that arise when combining these methods with data-parallel training techniques. We also report on preliminary experiments that evaluate the I/O overheads involved in accessing the training samples from a parallel file system (PFS) under several concurrency scenarios, highlighting the impact of the PFS on the design of the data pipelines.

data pipelines↗

DOE OSTI2020

PRIME: a real-time cyber-physical systems testbed: from wide-area monitoring, protection, and control prototyping to operator training and beyond

As the power grid continues to evolve with advanced wide-area monitoring, protection, and control (WAMPAC) algorithms, there is an increasing need for realistic testbed environments with industry-grade software and hardware-in-the-loop (HIL) to perform verification and validation studies. Such testbed environments serve as ideal platforms to perform WAMPAC prototyping, operator training, and also to study the impacts of different types of cyberattack scenarios on the operation of the grid. In this paper, we introduce PRIME (PNNL cybeR physIcal systeMs tEstbed): the testbed that integrates real-time transmission system simulator with commercial industry grade energy management system (EMS) software and remote hardware-in-the-loop (RHIL). PRIME is an end-to-end, modular testbed that allows high-fidelity RHIL experimentation of a power system. We present two detailed case studies (fault location and clearing in transmission system, and operator training) to showcase the capabilities of our PRIME testbed. Finally, we briefly discuss some of the potential limitations of our testbed in terms of scalability and flexibility to setup larger test systems and identify directions for future work to address those limitations.

42 ENGINEERING↗

DOE OSTI2025

Towards AI Based Data Classification for Decision Making During Testing

During the development of high-consequence items, test systems should be capable of differentiating between test failures resulting from narrowly missing requirements versus those indicating potentially catastrophic faults. In many instances, classifying the data corresponds to simply identifying whether measured waveforms have approximately the anticipated shape. Cast in this light, the problem reduces to converting raw data into a form optimal for use with neural network classifiers. This manuscript investigates different means of representing raw data for image classification. Raw data plots and Short Time Fourier Transform (STFT) spectrograms are classified by both custom built, small-scale, Convolution Neural Networks (CNN) and open-source, multi-million parameter, pre-trained deep CNNs. In the case of time varying frequency content, the STFTs provide images with greater detail and can be accurately classified with simpler networks. This requires less memory and runs faster than classifying the raw data using the more sophisticated options—making STFTs optimal for applications with memory constraints. STFTs are not a panacea. In some cases the time-domain signal contains useful information that should not be discarded. Rather than using raw data or STFTs, the images can be constructed from both by using red and green channels of an RGB image to visualize the real and imaginary components of the transform, with the raw data occupying the blue channel.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Fermilab Booster loss modelling and rebalancing using Bayesian methods

To meet PIP-II upgrade requirements, Fermilab Booster losses need to be reduced by 50% compared to present levels. So far, simulations are not good enough to predict loss patterns. Thus, an extensive Booster tune up will be necessary to achieve required performance. In this paper we present an effort to build a data-driven loss model using Bayesian techniques, and subsequently to rebalance losses for higher trip margins. We first created several sets of spatially and temporally isolated orbit and optics knobs, and trained Gaussian process models for each beam loss monitor as well as beam current. Novel techniques of uncertainty constraints and approximate GP fitting were introduced to handle safety and timing requirements. We then performed single and multi-objective tuning using scalarized objectives comprised of critical beam loss locations. We achieved significant rebalancing of losses, increasing margins by 25%, as well as an overall improvement in transmission efficiency of 0.4%. Automated data collection is being developed so that more accurate surrogate models can be trained over time.

Kuklev, N. [Fermilab]↗

DOE OSTI2020

Automatic Classification of Biological Targets in a Tidal Channel Using a Multibeam Sonar

Multibeam sonars are widely used for environmental monitoring of fauna at marine renewable energy sites. However, they can rapidly accrue vast volumes of data, which poses a challenge for data processing. Here, using data from a deployment in a tidal channel with peak currents of 1–2 m s –1 , we demonstrate the data-reduction benefits of real-time automatic classification of targets detected and tracked in multibeam sonar data. First, we evaluate classification capabilities for three machine learning algorithms: random forests, support vector machines, and k-nearest neighbors. For each algorithm, a hill-climbing search optimizes a set of hand-engineered attributes that describe tracked targets. Here, the random forest algorithm is found to be most effective—in postprocessing, discriminating between biological and nonbiological targets with a recall rate of 0.97 and a precision of 0.60. In addition, 89% of biological targets are correctly classified as either seals, diving birds, fish schools, or small targets. Model dependence on the volume of training data is evaluated. Second, a real-time implementation of the model is shown to distinguish between biological targets and nonbiological targets with nearly the same performance as in postprocessing. From this, we make general recommendations for implementing real-time classification of biological targets in multibeam sonar data and the transferability of trained models.

16 TIDAL AND WAVE POWER↗

DOE OSTI2021

Multiscale Data-Driven Seismic Full-Waveform Inversion With Field Data Study

Seismic full-waveform inversion (FWI), which uses iterative methods to estimate high-resolution subsurface models from seismograms, is a powerful imaging technique in exploration geophysics. In recent years, the computational cost of FWI has grown exponentially due to the increasing size and resolution of seismic data. Moreover, it is a nonconvex problem and can encounter local minima due to the limited accuracy of the initial velocity models or the absence of low frequencies in the measurements. To overcome these computational issues, we develop a multiscale data-driven FWI method based on fully convolutional networks (FCNs). In preparing the training data, we first develop a real-time style transform method to create a large set of synthetic subsurface velocity models from natural images. We then develop two convolutional neural networks with encoder-decoder structures to reconstruct the low- and high-frequency components of the subsurface velocity models, separately. To validate the performance of our data-driven inversion method and the effectiveness of the synthesized training set, we compare it with conventional physics-based waveform inversion approaches using both synthetic and field data. Finally, these numerical results demonstrate that, once our model is fully trained, it can significantly reduce the computation time and yield more accurate subsurface velocity models in comparison with conventional FWI.

58 GEOSCIENCES↗

DOE OSTI2020

Hindsight logging for model training

In modern Machine Learning, model training is an iterative, experimental process that can consume enormous computation resources and developer time. To aid in that process, experienced model developers log and visualize program variables during training runs. Exhaustive logging of all variables is infeasible, so developers are left to choose between slowing down training via extensive conservative logging, or letting training run fast via minimalist optimistic logging that may omit key information. As a compromise, optimistic logging can be accompanied by program checkpoints; this allows developers to add log statements post-hoc, and "replay" desired log statements from checkpoint---a process we refer to as hindsight logging. Unfortunately, hindsight logging raises tricky problems in data management and software engineering. Done poorly, hindsight logging can waste resources and generate technical debt embodied in multiple variants of training code. In this paper, we present methodologies for efficient and effective logging practices for model training, with a focus on techniques for hindsight logging. Our goal is for experienced model developers to learn and adopt these practices. To make this easier, we provide an open-source suite of tools for Fast Low-Overhead Recovery (flor) that embodies our design across three tasks: (i) efficient background logging in Python, (ii) adaptive periodic checkpointing, and (iii) an instrumentation library that codifies hindsight logging for efficient and automatic record-replay of model-training. Model developers can use each flor tool separately as they see fit, or they can use flor in hands-free mode, entrusting it to instrument their code end-to-end for efficient record-replay. Our solutions leverage techniques from physiological transaction logs and recovery in database systems. Evaluations on modern ML benchmarks demonstrate that flor can produce fast checkpointing with small user-specifiable overheads (e.g. 7%), and still provide hindsight log replay times orders of magnitude faster than restarting training from scratch.

Computer Science↗

DOE OSTI2023

classLog: Logistic regression for the classification of genetic sequences

Introduction Sequencing and phylogenetic classification have become a common task in human and animal diagnostic laboratories. It is routine to sequence pathogens to identify genetic variations of diagnostic significance and to use these data in realtime genomic contact tracing and surveillance. Under this paradigm, unprecedented volumes of data are generated that require rapid analysis to provide meaningful inference. Methods We present a machine learning logistic regression pipeline that can assign classifications to genetic sequence data. The pipeline implements an intuitive and customizable approach to developing a trained prediction model that runs in linear time complexity, generating accurate output rapidly, even with incomplete data. Our approach was benchmarked against porcine respiratory and reproductive syndrome virus (PRRSv) and swine H1 influenza A virus (IAV) datasets. Trained classifiers were tested against sequences and simulated datasets that artificially degraded sequence quality at 0, 10, 20, 30, and 40%. Results When applied to a poor-quality sequence data, the classifier achieved between >85% to 95% accuracy for the PRRSv and the swine H1 IAV HA dataset and this increased to near perfect accuracy when using the full dataset. The model also identifies amino acid positions used to determine genetic clade identity through a feature selection ranking within the model. These positions can be mapped onto a maximum-likelihood phylogenetic tree, allowing for the inference of clade defining mutations. Discussion Our approach is implemented as a python package with code available at https://github.com/flu-crew/classLog .

Zeller, Michael A.↗

DOE OSTI2021

Burst-mode dual-comb spectroscopy

We introduce a new modality of dual-comb spectroscopy that enables a simplified and powerful new approach for time-resolved measurements with increased acquisition rates. This "burst mode" form of dual-comb spectroscopy (BM-DCS) relies on the multiplexing of each probe pulse into a short train of pulses. With this approach we demonstrate a time-resolved series of absorption-based spectroscopic measurements of a laser-induced plasma using only a single laser ablation shot and identify 22 Nd lines not previously reported in the literature. The transmission spectra spanned 3.1 THz and were acquired at an effective acquisition rate of 25 kHz with 40 ms time-resolution. This simple modification to 100 MHz level dual-comb systems provides a flexible approach for studying transient and low duty-cycle events such as laser-induced plasmas, combustion, and explosive reactions.

(280.5395) Plasma Diagnostics, broadband laser spe↗

DOE OSTI2022

Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithms

Machine learning methods have been extensively used to study the dynamics of complex fluid flows. One such algorithm, known as adaptive neural fuzzy inference system (ANFIS), can generate data-driven predictions for flow fields, but has not been applied to natural geophysical flows in large-scale rivers. Herein, we demonstrate the potential of ANFIS to produce three-dimensional (3D) realizations of the instantaneous flood flow field in several large-scale, virtual meandering rivers. The 3D dynamics of flood flow in large-scale rivers were obtained using large-eddy simulation (LES). The LES results, i.e., the 3D velocity components, were employed to train the learnable coefficients of an ANFIS. Further, the trained ANFIS, along with a few time-steps of LES results (precursor data) were then used to produce 3D realizations of flood flow fields in large-scale rivers with geometries other than the one the ANFIS was trained with. We also used the trained ANFIS to generate 3D realizations of river flow at a discharge other than that the ANFIS was trained with. The flow field results obtained from ANFIS were validated using separate LES runs to assess the accuracy of the 3D instantaneous realizations of the machine learning algorithm. An error analysis was conducted to quantify the discrepancies among the ANFIS and LES results for various flood flow predictions in large-scale rivers.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Time-lapse seismic data inversion for estimating reservoir parameters using deep learning

Geologic carbon sequestration involves the injection of captured carbon dioxide ([Formula: see text]) into subsurface formations for long-term storage. The movement and fate of the injected [Formula: see text] plume is of great concern to regulators because monitoring helps to identify potential leakage zones and determines the possibility of safe long-term storage. To address this concern, we design a deep-learning framework for [Formula: see text] saturation monitoring to determine the geologic controls on the storage of the injected [Formula: see text]. We use different combinations of porosities and permeabilities for a given reservoir to generate saturation and velocity models. We train the deep-learning model with a few time-lapse seismic images and their corresponding changes in saturation values for a particular [Formula: see text] injection site. The deep-learning model learns the mapping from the change in the time-lapse seismic response to the change in [Formula: see text] saturation during the training phase. We then apply the trained model to data sets comprising different time-lapse seismic image slices (corresponding to different time instances) generated using different porosity and permeability distributions that are not part of the training to estimate the [Formula: see text] saturation values along with the plume extent. Our algorithm provides a deep-learning assisted framework for the direct estimation of [Formula: see text] saturation values and plume migration in heterogeneous formations using the time-lapse seismic data. Our method improves the efficiency of time-lapse inversion by streamlining the large number of intermediate steps in the conventional time-lapse inversion workflow. This method also helps to incorporate the geologic uncertainty for a given reservoir by accounting for the statistical distribution of porosity and permeability during the training phase. Tests on different examples verify the effectiveness of our approach.

Geochemistry & Geophysics↗

DOE OSTI2025

Breaking the barrier of human-annotated training data for machine learning-aided plant research using aerial imagery

Machine learning (ML) can accelerate biological research. However, the adoption of such tools to facilitate phenotyping based on sensor data has been limited by (i) the need for a large amount of human-annotated training data for each context in which the tool is used and (ii) phenotypes varying across contexts defined in terms of genetics and environment. This is a major bottleneck because acquiring training data is generally costly and time-consuming. This study demonstrates how a ML approach can address these challenges by minimizing the amount of human supervision needed for tool building. A case study was performed to compare ML approaches that examine images collected by an uncrewed aerial vehicle to determine the presence/absence of panicles (i.e. “heading”) across thousands of field plots containing genetically diverse breeding populations of 2 Miscanthus species. Automated analysis of aerial imagery enabled the identification of heading approximately 9 times faster than in-field visual inspection by humans. Leveraging an Efficiently Supervised Generative Adversarial Network (ESGAN) learning strategy reduced the requirement for human-annotated data by 1 to 2 orders of magnitude compared to traditional, fully supervised learning approaches. The ESGAN model learned the salient features of the data set by using thousands of unlabeled images to inform the discriminative ability of a classifier so that it required minimal human-labeled training data. This method can accelerate the phenotyping of heading date as a measure of flowering time in Miscanthus across diverse contexts (e.g. in multistate trials) and opens avenues to promote the broad adoption of ML tools.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

pixelvar79/ESGAN-Flowering-Detection-paper

Varela, Sebastian↗

DOE OSTI2021

Adaptive machine learning for time-varying systems: low dimensional latent space tuning

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map combinations of accelerator parameters and images which are 2D projections of the 6D phase space distributions of charged particle beams as they are transported between various particle accelerator locations. Despite their strengths, applying ML to time-varying systems, or systems with shifting distributions, is an open problem, especially for large systems for which collecting new data for re-training is impractical or interrupts operations. Particle accelerators are one example of large time-varying systems for which collecting detailed training data requires lengthy dedicated beam measurements which may no longer be available during regular operations. We present a novel method of adaptive ML for time-varying systems. Our approach is to map very high (N ≈ 100k) dimensional inputs (a combination of scalar parameters and images) into the low dimensional (N ≈ 2) latent space at the output of the encoder section of an encoder-decoder CNN. We then actively tune the low dimensional latent space-based representation of complex system dynamics by the addition of an adaptively tuned feedback vector directly before the decoder sections builds back up to our image-based high-dimensional phase space density representations. This method allows us to learn correlations within and to quickly tune the characteristics of incredibly large parameter space systems and to track their evolution in real time based on feedback without massive new data sets for re-training. We demonstrate that our method can accurately predict and track the phase space of charged particle beams at various locations in a particle accelerator by adaptively adjusting in real-time while the unknown input beam distribution of the accelerator is changing in shape, charge, and offset and while the RF system of the accelerator itself is also changing in an unpredictable way. For FACET-II we demonstrate that such an approach has the potential to use transverse deflecting cavity and energy spread spectrum beam measurements to accurately predict 2D projections of the 6D phase space of the electron beam at the plasma wakefield acceleration interaction point where such diagnostics are unavailable.

47 OTHER INSTRUMENTATION↗

DOE OSTI2022

Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination

Post-training model compression can reduce the inference costs of deep neural networks, but uncompressed training still consumes enormous hardware resources and energy. To enable low-energy training on edge devices, it is highly desirable to directly train a compact neural network from scratch with a low memory cost. Low-rank tensor decomposition is an effective approach to reduce the memory and computing costs of large neural networks. However, directly training low-rank tensorized neural networks is a very challenging task because it is hard to determine a proper tensor rank a priori, and the tensor rank controls both model complexity and accuracy. Here, this paper presents a novel end-to-end framework for low-rank tensorized training. We first develop a Bayesian model that supports various low-rank tensor formats (e.g., CANDECOMP/PARAFAC, Tucker, tensor-train, and tensor-train matrix) and reduces neural network parameters with automatic rank determination during training. Then we develop a customized Bayesian solver to train large-scale tensorized neural networks. Our training methods shows orders-of-magnitude parameter reduction and little accuracy loss (or even better accuracy) in the experiments. On a very large deep learning recommendation system with over 4.2 ×10 9 model parameters, our method can reduce the parameter number to 1.6 ×10 5 automatically in the training process (i.e., by 2.6 ×10 4 times) while achieving almost the same accuracy. Code is available at https://github.com/colehawkins/bayesian-tensor-rank-determination.

compact neural networks↗

DOE OSTI2024

Georgia Tech Accelerated, Compressed, and Regularized Compute of Kinetic-based PDEs (Final Report)

This report summarizes the collaborative effort between Lawrence Livermore National Laboratory and Georgia Tech to enhance the BoBa library for tensor train computation in PDE solvers, with a target on kinetic equations and their continuum limits. We aimed to reduce computational cost and memory usage by replacing traditional array-based computations with tensor trains. We examined the compressibility of time-evolving solutions to the Euler equations with discontinuities. We also explored using the first invsicid and linear regularization of the compressible flow equations via the information geometric regularization (IGR). We explored this in a tensor train formulation. To identify that inverse terms in the IGR equations pose problems for tensor train formulations and investigate efficient methods for batched inversion of tensor trains.

97 MATHEMATICS AND COMPUTING↗