SEARCH · Search NASA

Results for “Distributed 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 19 records

All sources NASA NTRS DOE OSTI

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

HydraGNN v4.0

The new version of HydraGNN v4.0 provides additional core capabilities, such as: Inclusion of multi-body atomistic cluster expansion MACE, polarizable atom interaction neural network PAINN, and equivariant principal neighborhood aggregation (PNAEq) among the message passing layers supported -Inclusion of graph transformers to directly model long-range interactions between nodes that are distant in the graph topology Integration of graph transformers with message passing layers by combining the graph embedding generated by the two mechanisms, which allows for an improved expressivity of the HydraGNN architecture Improved re-implementation of multi-task learning (MTL) to allow its use for stabilized training across imbalanced, multi-source, multi-fidelity data Introduction of multi-task parallelism, a newly proposed type of model parallelism specifically for MTL architectures, which allows to dispatch different output decoding heads to different GPU devices Integration of multi-task parallelism with pre-existing distributed data parallelism to enable a 2D parallelization for distributed training Improved portability of the distributed training across Intel GPUs, which has been testes on ALCF exascale supercomputer Aurora Inclusion of 2-level fine-grained energy profilers portable across NVIDIA, AMD, and Intel GPUs to monitor the power and energy consumption associated with different functions executed by the HydraGNN code during data pre-load and training Restructuring of previous examples and inclusion of new sets of examples to illustrate the download, preprocess, and training of HydraGNN models on new large-scale open-source datasets for atomistic materials modeling (e.g., Alexandria, Transition1x, OMat24, OMol25)

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗

DOE OSTI2025

Optimizing temperature distributions for training neural quantum states using parallel tempering

Parametrized artificial neural networks (ANNs) can be very expressive ansatzes for variational algorithms, reaching state-of-the-art energies on many quantum many-body Hamiltonians. Nevertheless, the training of the ANN can be slow and stymied by the presence of local minima in the parameter landscape. One approach to mitigate this issue is to use parallel tempering methods, and in this work, we focus on the role played by the temperature distribution of the parallel tempering replicas. Using an adaptive method that adjusts the temperatures in order to equate the exchange probability between neighboring replicas, we show that this temperature optimization can significantly increase the success rate of the variational algorithm with negligible computational cost by eliminating bottlenecks in the replicas' random walk. Furthermore, we demonstrate this using two different neural networks, a restricted Boltzmann machine and a feedforward network, which we use to study a toy problem based on a permutation invariant Hamiltonian with a pernicious local minimum and the 𝐽 1 −𝐽 2 model on a rectangular lattice.

Neural network simulations↗

DOE OSTI2025

5G integrated edge computing platform for efficient component monitoring in coal-fired power plants

This project developed a cutting-edge 5G-integrated edge computing framework to enhance operational efficiency and reliability in coal-fired power plants through real-time component monitoring and anomaly detection. The initiative focused on leveraging distributed machine learning, federated learning, and 5G-based dynamic network slicing to support scalable, fault-tolerant monitoring environments to meet the operational requirements in industrial control systems. With a Distributed Edge Computing Service (DECS) orchestration, this project enabled federated learning at edge for condition monitoring and introduced adaptive client selection strategies to minimize communication overhead. Scalable distributed training was achieved using the Horovod framework, thus enhancing performance across edge nodes. In the realm of 5G networking, the project designed and deployed reconfigurable, QoS-aware network slicing tailored for operational technology (OT) environments, integrating software-defined networks to bolster cyber-resilience and enabling dynamic slicing for federated learning workloads. A significant milestone was the development of a virtualized ICS environment with 5G core integration—which allowed elastic and fault tolerant distributed training on real-world datasets such as NASA Bearings, Hydraulic Systems, and TEP. To broaden the impact of the project, a TRL-3 virtualized ICS testbed for research and education was designed. This project engaged several graduate and undergraduate students to conduct research on the cutting-edge technology, and it resulted in one PhD dissertation, one MS thesis, and over 14 peer-reviewed publications. With the support of this project students also participated in national cybersecurity competitions to improve their professional development skills.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2026

Active learning enables generation of molecules that advance the known Pareto front

Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the properties of the structures represented in the training distribution. We find that this limitation arises not only from the molecule generation process itself, but also from the poor generalization capabilities of molecular property predictors. We address this challenge by creating a closed-loop molecule generation pipeline with iterative retraining on new quantum chemical simulation data. Compared against static, single-pass generative modeling approaches, only our closed-loop iterative workflow generates molecules with properties extending beyond the training distribution (up to 0.44 standard deviations beyond the original range) and achieves a 79% improvement in out-of-distribution molecule classification accuracy. Furthermore, by conditioning molecular generation on thermodynamic stability data obtained during the iterative loop, the proportion of stable and hence potentially synthesizable molecules generated is 3.5x higher than the next-best model.

Chemistry↗

DOE OSTI2024

Assessing Membership Inference Attacks under Distribution Shifts

Membership inference attacks (MIAs) exploit machine learning models to infer whether a data point was in the training set, posing significant privacy risks even with limited black-box access. These attacks rely on the attacker approximating the target model’s training distribution, yet the impact of distribution shifts between target and shadow models on MIA success remains underexplored. We systematically evaluate five types of distribution shifts —-cutout, jitter, Gaussian noise, label shift, and attribute shift —- at varying intensities. Our results reveal that these shifts affect MIA effectiveness in nuanced ways, with some reducing attack success while others exacerbate vulnerabilities, and the same shift can have opposite effects depending on the type of MIA. This highlights the complex interplay between distributional differences and attack performance, offering critical insights for improving model defenses against MIAs.

Shi, Yichuan [Massachusetts Institute of Technolog↗

DOE OSTI2024

Out-of-Distribution Detection and Radiological Data Monitoring Using Statistical Process Control

Abstract Machine learning (ML) models often fail with data that deviates from their training distribution. This is a significant concern for ML-enabled devices as data drift may lead to unexpected performance. This work introduces a new framework for out of distribution (OOD) detection and data drift monitoring that combines ML and geometric methods with statistical process control (SPC). We investigated different design choices, including methods for extracting feature representations and drift quantification for OOD detection in individual images and as an approach for input data monitoring. We evaluated the framework for both identifying OOD images and demonstrating the ability to detect shifts in data streams over time. We demonstrated a proof-of-concept via the following tasks: 1) differentiating axial vs. non-axial CT images, 2) differentiating CXR vs. other radiographic imaging modalities, and 3) differentiating adult CXR vs. pediatric CXR. For the identification of individual OOD images, our framework achieved high sensitivity in detecting OOD inputs: 0.980 in CT, 0.984 in CXR, and 0.854 in pediatric CXR. Our framework is also adept at monitoring data streams and identifying the time a drift occurred. In our simulations tracking drift over time, it effectively detected a shift from CXR to non-CXR instantly, a transition from axial to non-axial CT within few days, and a drift from adult to pediatric CXRs within a day—all while maintaining a low false positive rate. Through additional experiments, we demonstrate the framework is modality-agnostic and independent from the underlying model structure, making it highly customizable for specific applications and broadly applicable across different imaging modalities and deployed ML models.

Zamzmi, Ghada↗

DOE OSTI2025

Prediction of carbon nanostructure mechanical properties and the role of defects using machine learning

Graphene-based nanostructures hold immense potential as strong and lightweight materials, however, their mechanical properties such as modulus and strength are difficult to fully exploit due to challenges in atomic-scale engineering. This study presents a database of over 2,000 pristine and defective nanoscale CNT bundles and other graphitic assemblies, inspired by microscopy, with associated stress–strain curves from reactive molecular dynamics (MD) simulations using the reactive INTERFACE force field (IFF-R). These 3D structures, containing up to 80,000 atoms, enable detailed analyses of structure-stiffness-failure relationships. By leveraging the database and physics- and chemistry-informed machine learning (ML), accurate predictions of elastic moduli and tensile strength are demonstrated at speeds 1,000 to 10,000 times faster than efficient MD simulations. Hierarchical Graph Neural Networks with Spatial Information (HS-GNNs) are introduced, which integrate chemistry knowledge. HS-GNNs as well as extreme gradient boosted trees (XGBoost) achieve forecasts of mechanical properties of arbitrary carbon nanostructures with only 3 to 6% mean relative error. The reliability equals experimental accuracy and is up to 20 times higher than other ML methods. Predictions maintain 8 to 18% accuracy for large CNT bundles, CNT junctions, and carbon fiber cross-sections outside the training distribution. The physics- and chemistry-informed HS-GNN works remarkably well for data outside the training range while XGBoost works well with limited training data inside the training range. The carbon nanostructure database is designed for integration with multimodal experimental and simulation data, scalable beyond 100 nm size, and extendable to chemically similar compounds and broader property ranges. The ML approaches have potential for applications in structural materials, nanoelectronics, and carbon-based catalysts.

Winetrout, Jordan J.↗

NASA NTRS2013

Adaptive Distributed Environment for Procedure Training (ADEPT)

ADEPT (Adaptive Distributed Environment for Procedure Training) is designed to provide more effective, flexible, and portable training for NASA systems controllers. When creating a training scenario, an exercise author can specify a representative rationale structure using the graphical user interface, annotating the results with instructional texts where needed. The author's structure may distinguish between essential and optional parts of the rationale, and may also include "red herrings" - hypotheses that are essential to consider, until evidence and reasoning allow them to be ruled out. The system is built from pre-existing components, including Stottler Henke's SimVentive instructional simulation authoring tool and runtime. To that, a capability was added to author and exploit explicit control decision rationale representations. ADEPT uses SimVentive's Scalable Vector Graphics (SVG)- based interactive graphic display capability as the basis of the tool for quickly noting aspects of decision rationale in graph form. The ADEPT prototype is built in Java, and will run on any computer using Windows, MacOS, or Linux. No special peripheral equipment is required. The software enables a style of student/ tutor interaction focused on the reasoning behind systems control behavior that better mimics proven Socratic human tutoring behaviors for highly cognitive skills. It supports fast, easy, and convenient authoring of such tutoring behaviors, allowing specification of detailed scenario-specific, but content-sensitive, high-quality tutor hints and feedback. The system places relatively light data-entry demands on the student to enable its rationale-centered discussions, and provides a support mechanism for fostering coherence in the student/ tutor dialog by including focusing, sequencing, and utterance tuning mechanisms intended to better fit tutor hints and feedback into the ongoing context.

Domeshek, Eric↗

DOE OSTI2024

Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers

We present a new class of AI models for the detection of quasi-circular, spinning, non-precessing binary black hole mergers whose waveforms include the higher order gravitational wave modes ($\ell$, |m|) = {(2,2), (2,1), (3,3), (3,2), (4,4)}, and mode mixing effects in the $\ell$ = 3, |m| = 2 harmonics. These AI models combine hybrid dilated convolution neural networks to accurately model both short- and long-range temporal sequential information of gravitational waves; and graph neural networks to capture spatial correlations among gravitational wave observatories to consistently describe and identify the presence of a signal in a three detector network encompassing the Advanced LIGO and Virgo detectors. We first trained these spatiotemporal-graph AI models using synthetic noise, using 1.2 million modeled waveforms to densely sample this signal manifold, within 1.7 h using 256 NVIDIA A100 GPUs in the Polaris supercomputer at the Argonne Leadership Computing Facility. This distributed training approach exhibited optimal classification performance, and strong scaling up to 512 NVIDIA A100 GPUs. With these AI ensembles we processed data from a three detector network, and found that an ensemble of 4 AI models achieves state-of-the-art performance for signal detection, and reports two misclassifications for every decade of searched data. We distributed AI inference over 128 GPUs in the Polaris supercomputer and 128 nodes in the Theta supercomputer, and completed the processing of a decade of gravitational wave data from a three detector network within 3.5 h. Finally, we fine-tuned these AI ensembles to process the entire month of February 2020, which is part of the O3b LIGO/Virgo observation run, and found 6 gravitational waves, concurrently identified in Advanced LIGO and Advanced Virgo data, and zero false positives. This analysis was completed in one hour using one NVIDIA A100 GPU.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2024

A Strong Gravitational Lens Is Worth a Thousand Dark Matter Halos: Inference on Small-scale Structure Using Sequential Methods

Strong gravitational lenses are a singular probe of the Universe’s small-scale structure—they are sensitive to the gravitational effects of low-mass (<10 10 M ⊙ ) halos even without a luminous counterpart. Recent strong-lensing analyses of dark matter structure rely on simulation-based inference (SBI). Modern SBI methods, which leverage neural networks as density estimators, have shown promise in extracting the halo-population signal. However, it is unclear whether the constraints from these models are limited by the methodology or the data. In this study, we introduce an accelerator-optimized simulation pipeline that can generate lens images with realistic subhalo populations in milliseconds. Leveraging this simulator, we identify the main limitation of our fiducial SBI analysis: training set size. We then adopt a sequential neural posterior estimation (SNPE) approach, allowing us to refine the training distribution to align with the observed data. Using only one-fifth as many mock Hubble Space Telescope images, SNPE matches the constraints on the low-mass halo population produced by our best nonsequential model. Our experiments suggest that an over 3 order-of-magnitude increase in training set size and GPU hours would be required to achieve an equivalent result without sequential methods. While the full potential of the existing lens sample remains to be explored, the notable improvement in constraining power enabled by our sequential approach highlights that current constraints are limited primarily by methodology and not the data itself. Moreover, our results emphasize the need to treat training set generation and model optimization as interconnected stages of any cosmological analysis using SBI.

79 ASTRONOMY AND ASTROPHYSICS↗

NASA NTRS2019

Accelerated Simulation of Air Pollution Using NVIDIA RAPIDS

Atmospheric chemistry models are a central tool to study and forecast the impact of air pollution on the environment, vegetation, and human health. However, the numerical simulation of chemical kinetics is computationally expensive due to the stiffness of the system of ordinary differential equations that describes atmospheric chemistry. Here we present an alternative approach to the computation of atmospheric chemistry based on machine learning. Our training data set is produced using the NASA Goddard Earth Observing System (GEOS) model with GEOS-Chem chemistry, run on the NASA Center for Climate Simulation (NCCS) Discover supercomputing cluster on 384 Intel Xeon Haswell cores. This model spends more than 50% of total run time on solving atmospheric chemistry. The data set contains as input features the air pollution concentrations before solving the differential equations, together with some key physical parameters such as temperature and sun intensity. As target variables we define the air pollution concentrations after solving the differential equations. Using Dask-cuDF and Dask-XGBoost on the NVIDIA RAPIDS platform on 8 Tesla V100 GPUs, we generate from this training set gradient boosted decision tree models that can reproduce the simulation of chemical kinetics. We do this on the NCCS Advanced Data Analytics Platform (ADAPT) science cloud environment. Our application takes full advantage of recent advances in Dask-XGBoost, such as multi-node and multi-GPU scaling for distributed training with large data sets. The increase in training data size enabled by this is critical to capture the full range of chemical environments encountered across the globe and all annual seasons.The boosted tree models offer good predictability and show many of the features of the full chemistry reference simulation. Further improvements can be achieved through mass balance considerations and by accounting for error correlations. We incorporate the boosted tree models into the GEOS reference model using XGBoost's C API. This enables a seamless integration of the GPU trained models into GEOS-Chem, which is written in Fortran and optimized for use in a massively parallel CPU environment. We show the benefits of this approach and discuss the potential speedup of this machine learning accelerated atmospheric chemistry model.

Keller, Christoph A.↗

DOE OSTI2024

Integrated edge-to-exascale workflow for real-time steering in neutron scattering experiments

We introduce a computational framework that integrates artificial intelligence (AI), machine learning, and high-performance computing to enable real-time steering of neutron scattering experiments using an edge-to-exascale workflow. Focusing on time-of-flight neutron event data at the Spallation Neutron Source, our approach combines temporal processing of four-dimensional neutron event data with predictive modeling for multidimensional crystallography. At the core of this workflow is the Temporal Fusion Transformer model, which provides voxel-level precision in predicting 3D neutron scattering patterns. The system incorporates edge computing for rapid data preprocessing and exascale computing via the Frontier supercomputer for large-scale AI model training, enabling adaptive, data-driven decisions during experiments. This framework optimizes neutron beam time, improves experimental accuracy, and lays the foundation for automation in neutron scattering. Although real-time experiment steering is still in the proof-of-concept stage, the demonstrated potential of this system offers a substantial reduction in data processing time from hours to minutes via distributed training, and significant improvements in model accuracy, setting the stage for widespread adoption across neutron scattering facilities and more efficient exploration of complex material systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction

Detector simulation and reconstruction are a significant computational bottleneck in particle physics. Here, we develop particle-flow neural-assisted simulations (parnassus) to address this challenge. Our deep learning model takes as input a point cloud (particles impinging on a detector) and produces a point cloud (reconstructed particles). By combining detector simulations and reconstruction into one step, we aim to minimize resource utilization and enable fast surrogate models suitable for application both inside and outside large collaborations. We demonstrate this approach using a publicly available dataset of jets passed through the full simulation and reconstruction pipeline of the Compact Muon Solenoid (CMS) experiment. We show that parnassus accurately mimics the CMS particle flow algorithm on the (statistically) same events it was trained on and can generalize to jet momentum and type outside of the training distribution.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2026

HydraGNN v5.0

HydraGNN v5.0 expands the code base into a more portable, scalable, and flexible framework for scientific graph learning, with particular strength in atomistic machine-learning interatomic potentials and large-scale distributed training. The release adds Fully Sharded Data Parallel (FSDP) support alongside existing DDP and DeepSpeed paths, including FSDP-aware checkpointing and optimizer integration, and introduces a configurable multi-precision training workflow supporting FP32, BF16, and FP64 across GPUs and Intel XPUs. For atomistic modeling, HydraGNN v5.0 strengthens its MLIP capabilities through dynamic graph construction at every forward pass, energy-conserving force prediction via automatic differentiation, and per-atom energy loss formulations, while extending EGNN models to properly handle periodic boundary conditions. The release also broadens model expressiveness through graph-level attribute conditioning, adds new multi-task and model-parallel extensions such as MACE support and encoder/decoder branch optimization, and expands application coverage with integrated examples for datasets including OC25, Nabla2-DFT, QCML, Open Polymers 2026, and OPF. In parallel, HydraGNN v5.0 improves production readiness through performance optimizations for large-scale runs, stratified sampling and linear-regression preprocessing utilities, and tested installation scripts for DOE supercomputers including Frontier, Aurora, Perlmutter, and Andes. Overall, the release advances HydraGNN as a robust software platform for scalable graph neural networks across materials science, chemistry, and scientific machine learning workflows

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗

DOE OSTI2025

Uncertainty quantification and sensitivity analysis of a nuclear thermal propulsion reactor startup sequence

The research presented in this article describes progress in applying stochastic methods, uncertainty quantification, parametric studies, and variance-based sensitivity analysis (also known as Sobol sensitivity analysis) to a full-core model of a nuclear thermal propulsion (NTP) system simulated via the radiation transport code Griffin to simulate neutronics. Our goal is to develop a reduced-order (surrogate) model that can be rapidly sampled with perturbations to multiple input parameters. In this NTP system, reactivity and power feedback affect the rotation of control drums (CDs), which is itself controlled by a hybrid proportional-integral-derivative (PID) controller actuated by the power demand and reactivity feedback from the numerical model. This model uses reactor kinetic feedback (mean generation time [Λ] and effective delayed neutron fraction [ β eff ] from a transient Griffin simulation executed via Griffin’s improved quasi-static solver to provide the kinetic parameters) as inputs to functions that control the CD rotation angle. By investigating numerous stochastic approaches, we developed a dual-purpose surrogate model of the NTP system, using polynomial regression in the Multiphysics Object-Oriented Simulation Environment (MOOSE) Stochastic Tools Module (STM). The trained model can be rapidly sampled while simultaneously perturbing various input parameters, such as coefficients on the PID control or temperature (directly affecting the neutron cross section). The surrogate model delivers accurate (within 5%) results at speeds orders of magnitude faster (minutes, not days of computational time) than the base model. Once the surrogate model has been trained, distributions of the uncertain parameters can be changed at will to investigate the effects of perturbing multiple inputs as well as the effects of these inputs on the model output. For example, coefficients used in the PID control system may vary due to some type of physical interference, or uncertainty may exist in the temperature of the neutron cross sections in various regions of the reactor. A distribution can be placed on these parameters, and operational boundaries can be determined. The goal of this work is to support development of an advanced control system for operating CDs in a functioning NTP system. This work is a scoping study of the MOOSE STM.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗

NASA NTRS2017

Operating Small Sat Swarms as a Single Entity: Introducing SODA

NASA's decadal survey determined that simultaneous measurements from a 3D volume of space are advantageous for a variety of studies in space physics and Earth science. Therefore, swarm concepts with multiple spacecraft in close proximity are a growing topic of interest in the small satellite community. Among the capabilities needed for swarm missions is a means to maintain operator-specified geometry, alignment, or separation. Swarm stationkeeping poses a planning challenge due to the limited scalability of ground resources. To address scalable control of orbital dynamics, we introduce SODA - Swarm Orbital Dynamics Advisor - a tool that accepts high-level configuration commands and provides the orbital maneuvers needed to achieve the desired type of swarm relative motion. Rather than conventional path planning, SODA's innovation is the use of artificial potential functions to define boundaries and keepout regions. The software architecture includes high fidelity propagation, accommodates manual or automated inputs, displays motion animations, and returns maneuver commands and analytical results. Currently, two swarm types are enabled: in-train distribution and an ellipsoid volume container. Additional swarm types, simulation applications, and orbital destinations are in planning stages.

Conn, Tracie↗

NASA NTRS2017

Operating Small Sat Swarms as a Single Entity: Introducing SODA

Conn, Tracie↗