SEARCH · Search NASA

Results for “training”

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 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Stable Simulation of the Community Atmosphere Model Using Machine‐Learning Physical Parameterization Trained With Experience Replay

In recent years, machine learning (ML) models have been used to improve physical parameterizations of general circulation models (GCMs). A significant challenge of integrating ML models into GCMs is the online instability when they are coupled for long‐term simulation. We present a new strategy that demonstrates robust online stability when the physical parameterization package of an atmospheric GCM is replaced by a deep ML model. The method uses experience replay with a multistep training scheme of the ML model in which the model's own output at the previous time step is used in the training. Predicted physics tendencies in the replay buffer with the most recent errors in the training iterations are reused, making the ML model learn from its own errors. The training method reduces the gap between the offline and online environments of the ML model. The method is used to train the ML model as the physical parameterization of the Community Atmosphere Model (CAM5) with training data from the Multi‐scale Modeling Framework high resolution simulations. Three 6‐year online simulations of the CAM5 are carried out by using the ML physics package. The simulated spatial distributions of precipitation, surface temperature and zonally averaged atmospheric fields demonstrate overall better accuracy than that of the standard CAM5 and benchmark model even without the use of additional physical constraints or tuning. This work is the first to demonstrate a solution to address the online instability problem in climate modeling with ML physics by using experience replay.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Pre-training Vision Models for the Classification of Alerts from Wide-field Time-domain Surveys

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2026

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training

Distributed training increases the number of batches processed per iteration either by scaling-out (adding more nodes) or scaling-up (increasing the batch-size). However, the largest configuration does not necessarily yield the best performance. Horizontal scaling introduces additional communication overhead, while vertical scaling is constrained by computation cost and device memory limits. Thus, simply increasing the batch-size leads to diminishing returns: training time and cost decrease initially but eventually plateaus, creating a knee-point in the time/cost vs. batch-size pareto curve. The optimal batch-size therefore depends on the underlying model, data and available compute resources. Large batches also suffer from worse model quality due to the well-known “generalization gap”. In this paper, we present Tula, an online service that automatically optimizes time, cost, and convergence quality for large-batch training of convolutional models. It combines parallel-systems modeling with statistical performance prediction to identify the optimal batchsize. Tula predicts training time and cost within 7.5−14% error across multiple models, and achieves up to 20× overall speedup and improves test accuracy by ≈9% on average over standard large-batch training on various vision tasks, thus successfully mitigating the generalization gap and accelerating training at the same time.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)↗

DOE OSTI2025

A Parallel Alternative for Energy-Efficient Neural Network Training and Inferencing

Energy efficiency of training and inferencing with large neural network models is a critical challenge facing the future of sustainable large-scale machine learning workloads. This paper introduces an alternative strategy, called phantom parallelism, to minimize the net energy consumption of traditional tensor (model) parallelism, the most energy-inefficient component of large neural network training. The approach is presented in the context of feed-forward network architectures as a preliminary, but comprehensive, proof-of-principle study of the proposed methodology. We derive new forward and backward propagation operators for phantom parallelism, implement them as custom autograd operations within an end-to-end phantom parallel training pipeline and compare its parallel performance and energy-efficiency against those of conventional tensor parallel training pipelines. Formal analyses that predict lower bandwidth and FLOP counts are presented with supporting empirical results on up to 256 GPUs that corroborate these gains. Experiments are shown to deliver ∼50% reduction in the energy consumed to train FFNs using the proposed phantom parallel approach when compared with conventional tensor parallel methods. Additionally, the proposed approach is shown to train smaller phantom models to the same model loss on smaller GPU counts as larger tensor parallel models on larger GPU counts offering the possibility for even greater energy savings.

Seal, Sudip [ORNL] (ORCID:0000000332330656)↗

DOE OSTI2025

Efficient Training of Deep Neural Operator Networks via Randomized Sampling

Neural operators (NOs) employ deep neural networks to learn the mappings between infinitedimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex dynamics across various scientific and engineering applications. In this work, we introduce a random sampling technique to be adopted during the training of DeepONet, aimed at improving the generalization ability of the model, while significantly reducing the computational time. The proposed approach targets the trunk network of the DeepONet model that outputs the basis functions corresponding to the spatiotemporal locations of the bounded domain on which the physical system is defined. While constructing the loss function, DeepONet training traditionally considers a uniform grid of spatiotemporal points at which all the output functions are evaluated for each iteration. This approach leads to a larger batch size, resulting in poor generalization and increased memory demands, due to the limitations of the stochastic gradient descent (SGD) optimizer. The proposed random sampling over the inputs of the trunk net mitigates these challenges, improving generalization and reducing the memory requirements during training, resulting in significant computational gains. We validate our hypothesis through three benchmark examples, demonstrating substantial reductions in training time while achieving comparable or lower overall test errors relative to the traditional training approach. Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet, offering a promising avenue for improving the framework’s performance in modeling complex physical systems.

Karumuri, Sharmila [Department of Civil & Systems ↗

DOE OSTI2025

BOPTest As a Platform for Building Controls and Grid-Interactive Buildings Workforce Training

Building automation and controls are becoming increasingly complex with the emergence of Grid Integrated Efficient Buildings (GEBs) as well as new highly efficient sequences of operation and data-driven control schemes. However, there remains a significant gap in hands-on training opportunities for building operators and technicians to gain practical experience with advanced control systems in a low-risk environment. This paper presents BOPTEST (Building Optimization Performance Test) as a suitable platform for workforce training in building controls and GEB technologies. BOPTEST provides a suite of standardized building simulation test cases with a REST API, real-time control interfaces through BACnet, semantic models connecting users to building data, and built-in calculation of control metrics and performance indicators. The platform enables trainees to interact with virtual buildings using industry-standard protocols while learning how to implement and innovate control strategies. The training platform is designed to offer a structured and interactive learning experience for building engineers, helping them effectively develop, learn, and retain skills in fault identification, troubleshooting, and correction. The workflow is divided into three main phases: 1) Setup, 2) Exercise, and 3) Review, each comprising specific activities performed by either the instructor or the student. Initial pilot training sessions have yielded positive feedback from instructors and participants and demonstrates that BOPTEST effectively fills an industry need for a low-risk training resource via simulation of real building control systems, allowing trainees to gain practical experience before working in the field. The platform's ability to provide immediate performance feedback while maintaining familiar industry interfaces makes it particularly suitable for workforce development programs. This work provides a replicable model for leveraging building simulation in control education and training.

Paul, Lazlo↗

DOE OSTI2025

BOPTEST as a Platform for Building Controls and Grid-Interactive Buildings Workforce Training

Paul, Lazlo↗

NASA NTRS1976

Development and analysis of a modular approach to payload specialist training

A modular training approach for Spacelab payload crews is described. Representative missions are defined for training requirements analysis, training hardware, and simulations. Training times are projected for each experiment of each representative flight. A parametric analysis of the various flights defines resource requirements for a modular training facility at different flight frequencies. The modular approach is believed to be more flexible, time saving, and economical than previous single high fidelity trainer concepts. Block diagrams of training programs are shown.

Watters, H.↗

NASA NTRS1978

Transfer of training on manual control systems differing in short period frequency and damping characteristics

Each of four groups of 16 subjects was trained on one of four compensatory tracking tasks that differed with regard to short period natural frequency and damping characteristics. After completion of the training sessions, the members of each group either transferred to a task on which they had not been trained or continued with their original task. Analysis of the training data indicated that relative task difficulty was largely determined by system damping which, however, had little effect on the amount of transfer during the transfer trials. The effect of system frequency was essentially reversed, and a marked interaction between training and transfer frequencies was observed in the transfer data. Similar results were obtained both with relative error scores and transinformation scores. Positive transfer was exhibited by most of the groups when they transferred to tasks on which they had not been trained.

Lincoln, R. S.↗

DOE OSTI2025

GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism

Graph neural networks (GNNs), an emerging class of machine learning models for graphs, have gained popularity for their superior performance in various graph analytical tasks. Mini-batch training is commonly used to train GNNs on large graphs, and data parallelism is the standard approach to scale mini-batch training across multiple GPUs. Data parallel approaches contain redundant work as subgraphs sampled by different GPUs contain significant overlap. To address this issue, we introduce a hybrid parallel mini-batch training paradigm called Split parallelism. Split parallelism avoids redundant work by splitting the sampling, loading, and training of each mini-batch across multiple GPUs. Split parallelism, however, introduces communication overheads that can be more than the savings from removing redundant work. We further present a lightweight partitioning algorithm that probabilistically minimizes these overheads. We implement spllit parllelism in GSplit and show that it outperforms state-of-the-art mini-batch training systems like DGL, Quiver, and P3.

Lim, Seung-Hwan [ORNL] (ORCID:0000000194616866)↗

DOE OSTI2025

Biologically-informed excitatory and inhibitory ratio for robust spiking neural network training

Spiking neural networks drawing inspiration from biological constraints of the brain promise an energy-efficient paradigm for artificial intelligence. However, challenges exist in identifying guiding principles to train these networks in a robust fashion. In addition, training becomes an even more difficult problem when incorporating biological constraints of excitatory and inhibitory connections. In this work, we identify several key factors, such as low initial firing rates and diverse inhibitory spiking patterns, that determine the overall ability to train in the context of spiking networks with various ratios of excitatory to inhibitory neurons. The results indicate networks with biologically-realistic excitatory:inhibitory ratios can reliably train at low activity levels and in noisy environments. Additionally, the Van Rossum distance, a measure of spike train synchrony, provides insight into the importance of inhibitory neurons to increase network robustness to noise. This work supports further biologically-informed large-scale networks and energy efficient hardware implementations.

bio-inspired computing↗

DOE OSTI2025

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention mechanism, which is a critical component of transformer-based LLMs. In this paper, we investigate the impact of faults on LLM training, focusing on INF, NaN, and near-INF values in the computation results with systematic fault injection experiments. We observe the propagation patterns of these errors, which can trigger non-trainable states in the model and disrupt training, forcing the procedure to load from checkpoints. To mitigate the impact of these faults, we propose ATTNChecker, the first Algorithm-Based Fault Tolerance (ABFT) technique tailored for the attention mechanism in LLMs. ATTNChecker is designed based on fault propagation patterns of LLM and incorporates performance optimization to adapt to both system reliability and model vulnerability while providing lightweight protection for fast LLM training. Evaluations on four LLMs show that ATTNChecker on average incurs on average 7% overhead on training while detecting and correcting all extreme errors. Compared with the state-of-the-art checkpoint/restore approach, ATTNChecker reduces recovery overhead by up to 49×.

Liang, Yuhang [University of Alabama - Birmingham]↗

DOE OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗

DOE OSTI2025

TorchBraid: High-Performance Layer-Parallel Training of Deep Neural Networks with MPI and GPU Acceleration

TorchBraid is a high-performance implementation of layer-parallel training for deep neural networks (DNNs) supporting MPI-based parallelism and GPU acceleration. Layer-parallel training has been developed to overcome the serialization inherent in forward and backward propagation of DNNs that limits utilization of computational resources in the strong scaling limit. To achieve this, TorchBraid integrates the PyTorch neural network framework with the state-of-the-art XBraid time-parallel library. Furthermore, this article presents the use and performance of TorchBraid, in addition to solutions for overcoming the algorithmic challenges inherent in combining automatic differentiation with layer-parallel. Results are presented with and without GPU acceleration for the Tiny ImageNet and MNIST image classification data sets, as well as recurrent neural networks. Overall, TorchBraid enables fast training of DNNs, both in a strong and weak scaling context. In addition to the TorchBraid software, several new advances in applying layer-parallel algorithms are detailed. Integration of layer-parallel with data-parallel algorithms is presented for the first time, showing the computational advantages of the combination. Standard deep learning techniques, like batch-normalization, are developed for layer-parallel training. Finally, a new approach combining layer-parallel with spatial coarsening in order to accelerate training for 3D image classification shows roughly a 10× speedup over serial execution.

Layer-parallel↗

DOE OSTI2025

Fiats: Functional inference and training for surrogates

Fiats provides a platform for research on the training and deployment of neural-network surrogate models for computational science. Fiats also supports exploring, advancing, and combining functional, object-oriented, and parallel programming patterns in Fortran 2023. As such, the Fiats name has dual expansions: “Functional Inference And Training for Surrogates” or “Fortran Inference And Training for Science.” Fiats inference and training procedures are pure and therefore satisfy a language constraint imposed on procedure invocations inside Fortran’s parallel loop construct: do concurrent. Furthermore, the Fiats training procedures are built around a do concurrent parallel reduction. Several compilers can automatically parallelize do concurrent on Central Processing Units (CPUs) or Graphics Processing Units (GPUs). Fiats thus aims to achieve performance portability through standard language mechanisms.

Rouson, Damian [Lawrence Berkeley National Laborat↗

DOE OSTI2025

EV Champion Training Webinar 2: ZEV and EV Charging Planning [Slides]

The Electric Vehicle (EV) Champion Training Series, hosted by the National Renewable Energy Laboratory (NREL), is tailored for fleet managers, facility managers, and other stakeholders involved in the deployment of EVs and charging stations. This series equips participants with the skills and knowledge necessary to become subject matter experts in EV implementation. This is the second training in a four-part series and serves as an intermediate training. This training covers the first four steps in the ZEV Ready Center process, including how to identify and train your zero-emission vehicle (ZEV) team, align headquarters strategy with site-level planning, identify ZEV opportunities, and identify charging needs for your project sites. Participants will gain a solid foundation to support the effective deployment and management of EVs and their infrastructure.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2025

Building Datasets and Training Methods for ML Based Magnet Quench Detection

Detecting quenches in superconducting (SC) magnets during training is a challenging process that involves capturing physical events that occur at different frequencies and appear as various signal features. These events may be correlated across instrumentation type, thermal cycle, and ramp. These events together build a more complete picture of continuous processes occurring in the magnet, and may allow us to flag potential precursors for quench detection. We present our work on building an automatic machine learning (ML) based quench detection system. We build upon our existing work on unsupervised auto-encoders for acoustic sensors and quench antenna (QA) by first establishing a supervised ML training pipeline. We show the results of an event tagging, analysis, and simulation framework on our QA and acoustic data which are used concurrently to build a training dataset for a supervised implementation. We then show how this supervised training can be used as a prior in a semi-supervised framework and compare this to the unsupervised neural network auto-encoder performance.This allows us to have a more concrete understanding of the performance of our algorithms relative to physical events occurring in the magnet, and also provides a baseline software tool to generically evaluate our quench prediction autoencoders under completely unsupervised, supervised, and semi-supervised training conditions.

Khan, Maira [Fermilab]↗

DOE OSTI2025

Virtual Reality for Shoot/No-Shoot Decision Training in Law Enforcement: A Literature Review and Research Agenda

Virtual reality (VR) can materially improve “shoot / no-shoot” (SNS) training by giving officers realistic, repeatable practice making high-stakes decisions under pressure. Traditional tools—live-fire ranges and video simulators—build basics, but they cannot adapt to each officer in real time or fully mirror the complexity of the field. VR closes that gap by creating immersive scenarios that are safer, more flexible, easier to scale across units, and able to capture objective performance data. SNS decisions are not just about marksmanship; they rely on perception, judgment, memory, and the ability to hold fire when a threat is uncertain. Effective training therefore needs realism, decision complexity, and branching outcomes that reflect the true consequences of choices. These elements strengthen recognition of hostile intent while reducing false positives and building the self-control required in ambiguous situations. VR brings specific advantages: dynamic environments, full-body interaction, and the ability to measure performance with precision—enabling targeted feedback and better transfer of learning to the street. At the same time, responsible deployment must address scenario quality (credible environments and behaviors), lawful decision models, and user wellbeing (appropriate stress levels, comfort, and safety). Sandia’s VIPER Lab is positioned to lead this work. The team combines human-performance science, AI/ML, and VR/AR development with a deep equipment bench (e.g., omnidirectional treadmill, eye-tracking, haptics, multiple HMDs). This ecosystem supports building and validating next-generation SNS training that is immersive, measurable, and trustworthy. Bottom line: Investment in VR-enabled SNS training that blends evidence-based design with careful validation and legal safeguards is expected to pay off in safer, more consistent decision-making and improved community trust, delivered through training that is practical to deploy at scale.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗