Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine architecture”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Cross-domain digital twin architecture for predictive maintenance via machine learning and Large Language Models

This research introduces a comprehensive framework for creating and deploying a digital twin platform for continuous monitoring and predictive maintenance within industrial settings. Through utilizing advanced technologies, including Unreal Engine 5, Unity 3D, the Message Queue Telemetry Transport protocol, Random Forest machine learning algorithms, and Large Language Models (LLMs), we establish a platform that digitally reproduces physical equipment and translates digital controls into real-world actions. This facilitates preventive maintenance approaches and improves operational effectiveness. The digital twin platform gathers sensor data from operational equipment, analyzes it using machine learning, and delivers practical insights to prevent potential malfunctions and enhance equipment performance. Furthermore, the incorporation of a web portal enables efficient monitoring and access to historical data, educational materials, and equipment status information. Preliminary findings indicate that digital twins can transform industrial equipment management and maintenance methodologies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Normal or abnormal? Machine learning for the leakage detection in carbon sequestration projects using pressure field data

The international commitments for atmospheric carbon reduction will require a rapid increase in carbon capture and storage (CCS) projects. The key to any successful CCS project lies in the long term storage and prevention of leakage of stored carbon dioxide (CO 2 ). In addition to being a greenhouse gas, CO 2 leaks reaching the surface can accumulate in low-lying areas resulting in a serious health risk. Among several alternatives, some of the more promising CCS storage formations are depleted oil and gas reservoirs, where the reservoirs had good geological seals prior to hydrocarbon extraction. With more CCS wells coming online, it is imperative to implement permanent, automated monitoring tools. We apply machine learning models to automate the leakage detection process in carbon storage reservoirs using rates of (CO 2 ) injection and pressure data measured by simple harmonic pulse testing (HPT). To validate the feasibility of this machine learning based workflow, we use data from HPT experiments carried out in the Cranfield oil field, Mississippi, USA. The data consist of a series of pulse tests conducted with baseline parameters and with an artificially introduced leak. Here, in this study, we pose the leakage detection task as an anomaly detection problem where deviation from the predicted behavior indicates leaks in the reservoir. Results show that different machine learning architectures such as multi-layer feed forward network, Long Short-Term Memory, and convolutional neural network are able to identify leakages and can provide early warning. These warnings can then be used to take remedial measures.

58 GEOSCIENCES↗
DOE OSTI2023

Machine Learning Models for Predicting Molecular UV–Vis Spectra with Quantum Mechanical Properties

Accurate understanding of Ultraviolet–visible (UV–Vis) spectra is critical for highthroughput design of compounds for drug discovery. Experimentally determining UV–Vis spectra can become expensive when dealing with a large quantity of novel molecules. This provides us an opportunity to drive computational advances in molecular property predictions using quantum mechanics and machine learning. In this work, we use both Quantum Mechanically (QM) predicted and measured UV–Vis spectra as input to modify four different machine learning architectures: UVvis-SchNet, UVvis- DTNN, UVvis-Transformer, and UVvis-MPNN. Here we find that the UVvis-MPNN model outperforms the other models when using optimized 3D coordinates and QM predicted spectra as input features. This model has the highest performance for predicting UVVisible spectra with a training RMSE of 0.06 and validation RMSE of 0.08.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost

Machine-learned interatomic potentials (MLIPs) are revolutionizing computational materials science and chemistry by offering an efficient alternative to ab initio molecular dynamics (MD) simulations. However, fitting high-quality MLIPs remains a challenging, time-consuming, and computationally intensive task where numerous trade-offs have to be considered, e.g., How much and what kind of atomic configurations should be included in the training set? Which level of ab initio convergence should be used to generate the training set? Which loss function should be used for fitting the MLIP? Which machine learning architecture should be used to train the MLIP? The answers to these questions significantly impact both the computational cost of MLIP training and the accuracy and computational cost of subsequent MLIP MD simulations. In this study, we use a configurationally diverse beryllium dataset and quadratic spectral neighbor analysis potential. We demonstrate that joint optimization of energy versus force weights, training set selection strategies, and convergence settings of the ab initio reference simulations, as well as model complexity can lead to a significant reduction in the overall computational cost associated with training and evaluating MLIPs. This opens the door to computationally efficient generation of high-quality MLIPs for a range of applications which demand different accuracy versus training and evaluation cost trade-offs.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Investigating boosted decision trees as a guide for inertial confinement fusion design

Inertial confined fusion experiments at the National Ignition Facility have recently entered a new regime approaching ignition. Improved modeling and exploration of the experimental parameter space were essential to deepening our understanding of the mechanisms that degrade and amplify the neutron yield. The growing prevalence of machine learning in fusion studies opens a new avenue for investigation. Here in this paper, we have applied the Gradient-Boosted Decision Tree machine-learning architecture to further explore the parameter space and find correlations with the neutron yield, a key performance indicator. We find reasonable agreement between the measured and predicted yield, with a mean absolute percentage error on a randomly assigned test set of 35.5%. This model finds the characteristics of the laser pulse to be the most influential in prediction, as well as the hohlraum laser entrance hole diameter and an enhanced capsule fabrication technique. We used the trained model to scan over the design space of experiments from three different campaigns to evaluate the potential of this technique to provide design changes that could improve the resulting neutron yield. While these data-driven model cannot predict ignition without examples of ignited shots in the training set, it can be used to indicate that an unseen shot design will at least be in the upper range of previously observed neutron yields.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

‘Flux+Mutability’: a conditional generative approach to one-class classification and anomaly detection

Abstract Anomaly Detection is becoming increasingly popular within the experimental physics community. At experiments such as the Large Hadron Collider, anomaly detection is growing in interest for finding new physics beyond the Standard Model. This paper details the implementation of a novel Machine Learning architecture, called Flux+Mutability, which combines cutting-edge conditional generative models with clustering algorithms. In the ‘flux’ stage we learn the distribution of a reference class. The ‘mutability’ stage at inference addresses if data significantly deviates from the reference class. We demonstrate the validity of our approach and its connection to multiple problems spanning from one-class classification to anomaly detection. In particular, we apply our method to the isolation of neutral showers in an electromagnetic calorimeter and show its performance in detecting anomalous dijets events from standard QCD background. This approach limits assumptions on the reference sample and remains agnostic to the complementary class of objects of a given problem. We describe the possibility of dynamically generating a reference population and defining selection criteria via quantile cuts. Remarkably this flexible architecture can be deployed for a wide range of problems, and applications like multi-class classification or data quality control are left for further exploration.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Understanding the Interplay between Hardware Errors and User Job Characteristics on the Titan Supercomputer

Designing dependable supercomputers begins with an understanding of errors in real-world, large-scale systems. The Titan supercomputer at Oak Ridge National Laboratory provides a unique opportunity to investigate errors when an actual system is actively used by multiple concurrent users and workloads from diverse domains at varying scales. This study presents a thorough analysis of 6, 908, 497 hardware errors from 18, 688 compute nodes of Titan for 312, 215 user jobs over a 3-year time period. Through careful joining of two system logs – the Machine Check Architecture (MCA) log and the job scheduler log – we show the correlated pattern of hardware errors for each job and user, in addition to individual descriptive statistics of errors, jobs, and users. Since the majority of hardware errors are memory errors, this study also shows the importance of error correcting in memory systems.

Lim, Seung-Hwan↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
DOE OSTI2024

Hyperparameter Studies for Vision Transformers Trained on High-Fidelity Simulations

This library is a collection of python modules that define, train, and analyze vision-transformer (ViT) machine learning models. The code implements, with mild modifications, ViT models that have been made publicly available through publication and GitHub code. The training data for these models is hydrodynamic simulation output in the form of numpy arrays. This library contains code to train these ViT models on the hydrodynamic simulation output with a variety of hyperparameters, and to compare the results of such models. Furthermore, the library contains definitions of simple convolutional neural network (CNN) machine learning architectures which can be trained on the same hydrodynamic simulation output. These are included as a reference point to compare the ViT models to. Additionally, the library includes trained ViT and CNN models and example input data for demonstration purposes. The code is based on the PyTorch python library.

Callis, Skylar↗
DOE OSTI2025

Moltensaltpropnet

MoltenSaltPropnet is a physics-informed machine learning framework that aims to predict the thermophysical properties of molten fluoride and chloride salt mixtures, which are crucial for the design and safety of Generation IV molten salt reactors. The code processes data from the Molten-Salt Thermal Properties Database (MSTDB-TP) and the Janz compendium, converting critically evaluated correlations into fast, differentiable surrogate models for density, viscosity, thermal conductivity, and heat capacity across 448 distinct salt systems. The implementation consists of several key components: 1. Data Curation: The code parses and cleans the raw data, normalizing elemental mole fractions and extracting relevant regression coefficients for various thermophysical properties. 2. Feature Engineering: It generates fixed-length numerical descriptors that encapsulate the composition and temperature, incorporating polynomial interaction terms and dimensionality-reduction techniques to optimize model performance. 3. Coefficient Learning: Four different machine learning architectures are employed: a deep residual network (ResNet), a Kolmogorov–Arnold network (KAN), a sparsity-inducing neural network (SNN), and classical regression models. Each model learns to predict coefficients that define the temperature-dependent correlations for the thermophysical properties. 4. Property Reconstruction: The predicted coefficients are used to compute temperature-dependent property values, ensuring positivity and monotonic trends through a composite loss function that enforces physical constraints. 5. User Interface: An open-source web application enables users to filter the database, train task-specific models, and visualize the results, allowing for rapid exploration of candidate salt mixtures. MoltenSaltPropnet bridges the gap between limited experimental data and high-fidelity reactor simulations, providing a powerful tool for researchers in the field of molten salt reactors and advanced nuclear energy systems.

Retamales, Mauricio Eduardo Tano [Idaho National L↗
DOE OSTI2026

Machine Protection Studies of Fast Instability-Driven Beam Losses in the EIC Electron Storage Ring

Fast transverse beam instabilities represent one of the most challenging protection scenarios for the Electron-Ion Collider (EIC) electron storage ring (ESR). Coherent betatron oscillations driven by collective effects can grow rapidly and lead to substantial beam losses within only a few tens of turns, posing a threat to collimators, superconducting (SC) magnets, cryogenic systems, and detector components. A dedicated simulation framework based on distributed transverse excitations was developed to evaluate instability-driven beam losses in the ESR. A conservative instability rise time on the order of 10 turns was used to define a bounding protection scenario. Simulations show that the original two-collimator configuration is insufficient to localize losses under all operating conditions, whereas an optimized four-collimator configuration reduces loss leakage into protected regions by more than two orders of magnitude. Nevertheless, the most severe instability scenarios produce catastrophic beam impacts, with nearly half of the stored beam being intercepted by the collimators within a single turn, exceeding the preliminary estimated survivability limits of the baseline collimator design. The results demonstrate that collimation alone is insufficient to guarantee safe ESR operation and must be complemented by a fast machine-protection system. Dedicated turn-by-turn beam-position monitors and fast beam-loss monitors provide sufficient advance warning to detect instability growth and initiate a beam abort before equipment-damaging loss levels are reached. These findings establish quantitative requirements for the ESR machine-protection architecture and support the implementation of a multilayer protection strategy for both accelerator and detector systems.

43 PARTICLE ACCELERATORS↗
DOE OSTI2021

Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture

Abstract Recently, machine learning (ML) has been used to address the computational cost that has been limiting ab initio molecular dynamics (AIMD). Here, we present GNNFF, a graph neural network framework to directly predict atomic forces from automatically extracted features of the local atomic environment that are translationally-invariant, but rotationally-covariant to the coordinate of the atoms. We demonstrate that GNNFF not only achieves high performance in terms of force prediction accuracy and computational speed on various materials systems, but also accurately predicts the forces of a large MD system after being trained on forces obtained from a smaller system. Finally, we use our framework to perform an MD simulation of Li 7 P 3 S 11 , a superionic conductor, and show that resulting Li diffusion coefficient is within 14% of that obtained directly from AIMD. The high performance exhibited by GNNFF can be easily generalized to study atomistic level dynamics of other material systems.

Chemistry↗
DOE OSTI2020

Comparison of Linear and Rotary Electric Machine Topologies for a Hybrid Hydraulic Electric Architecture of Off-Highway Vehicles

Electrification of off-highway vehicles offers the benefits of improved energy efficiency, enhanced controllability, and reduction in greenhouse gas emissions. However, progress towards electrification has been limited by the low power density of electric components compared to hydraulic components. A recently proposed hybrid hydraulic electric vehicle architecture provides a potential solution to these power density challenges by minimizing the required power rating of the electric components. This paper investigates the optimal design of linear and rotary electric machines for this new system architecture. Key performance metrics are identified for the electric machine, several variants of electric machines are analytically sized and compared for two different power levels, and an FEA-assisted design optimization is performed on promising candidates. Based on the optimization results, it is shown that an axial flux rotary machine is most suitable for implements requiring high power ratings, while the linear machine's form factor makes it a compelling candidate for lower power implements.

42 ENGINEERING↗
DOE OSTI2021

Optimal Control of the Energy-Saving Hybrid Hydraulic-Electric Architecture (HHEA) for Off-Highway Mobile Machines

Most off-highway constructions and agriculture equipment use hydraulics, which has unmatched power density, for power transmission and throttling as a means for control. A novel hybrid hydraulic-electric architecture (HHEA) has recently been proposed to improve efficiency for high-power machines that would have been cost-prohibitive to electrify directly. HHEA uses a set of common pressure rails (CPRs) to transmit the majority of power hydraulically and small electric motor drives to modulate that power and to achieve precise control. This article proposes a computationally efficient Lagrange multiplier method (LMM) for computing the optimal sequence of pressure rail selections to minimize energy use. This is needed to evaluate HHEA's energy-saving potential and for iterative architecture design and sizing. An interesting complication is that the cost function is not fully defined until the candidate control sequence is fully specified. This issue is dealt with by decomposing the original problem into a set of sub-problems with additional constraints that can be solved efficiently. Computational effort can be further reduced if actuators are optimized individually instead of together. However, additional steps are required to prevent the constraint functions from becoming discontinuous with respect to the Lagrange multipliers, which is necessary for meeting the constraints. Lastly, a case study of a construction machine demonstrates the efficacy of the method and shows that the HHEA reduces energy consumption by 68%-73% compared to the baseline load-sensing architecture.

Lagrange multiplier↗
DOE OSTI2025

A hybrid neural architecture: Online attosecond x-ray characterization

The emergence of high-repetition-rate x-ray free-electron lasers (XFELs), such as SLAC’s LCLS-II, serves as our canonical example for autonomous controls that necessitate high-throughput diagnostics paired with streaming computational pipelines capable of single-shot analysis with extremely low latency. We present the deterministic characterization with an integrated parallelizable hybrid resolver architecture, a hybrid machine learning framework designed for fast, accurate analysis of XFEL diagnostics using angular streaking-based sinogram images. This architecture integrates convolutional neural networks and bidirectional long short-term memory models to denoise input, identify x-ray sub-spike features, and extract sub-spike relative delays with sub-30 attosecond temporal resolution. Deployed on low-latency hardware, it achieves over 10 kHz throughput with 168.3 μs inference latency, indicating scalability to 14 kHz with field-programmable gate array integration. By transforming regression tasks into classification problems and leveraging optimized error encoding, we achieve high precision with low-latency performance that is critical for real-time streaming event selection and experimental control feedback signals. This represents a key development in real-time control pipelines for next-generation autonomous science, generally, and high repetition-rate x-ray experiments in particular.

Accelerator Physics (physics.acc-ph)↗
DOE OSTI2025

Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025).

This data release provides all data and code used in the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025)" to model stream temperature, evaluate, and assess results. The associated manuscript explores the effect of different ensemble construction techniques across different common machine learning (ML) architectures for predictions in unmonitored basins. Modeling was done using long short-term memory (LSTM), gated recurrent unit (GRU), temporal convolution network (TCN), and extreme gradient boosting (XGBoost) models, and stream site coverage spans 1362 locations across the conterminous United States. The ensemble construction techniques investigated include ensemble by random weight initialization, differing hyperparameters, different random subsets of training data, different subselections of input features, different architectures, and Monte Carlo Dropout. The data is organized into these items items:Code repository and data for the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025).Code: stream_temp_ml_regionalization.zip contains the code repositoryData to run the code:- data_dir.zip -- contains all files that should be moved to the "DATA_DIR" variable defined in the "set_env_vars.sh" script in the code repository- metadata_dir.zip -- contains all files that should be moved to the "METADATA_DIR" variable defined in the "set_env_vars.sh" script in the code repositoryData produced by the code and used in the paper:- outputs_dir.zip - contains model output and results (outputs_dir/results), model weights (outputs_dir/models), and all other outputs used for the paper including feature importances.To cite this code, please use the following BibTeX or MLA entries:bibtex:@misc{willard2025streamensembles,author = {Jared Willard and Charuleka Varadharajan},title = {Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification"},year = {2024},doi = {10.15485/2527393},publisher = {ESS-DIVE Repository},url = {https://data.ess-dive.lbl.gov/datasets/doi:10.15485/2527393}}MLA: Willard, Jared, et al. Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification". 2025. ESS-DIVE Repository, doi:10.15485/2448016.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Performance Results on CPU/GPU Exascale Architectures for OMEGA: The Ocean Model for E3SM Global Applications

The US Department of Energy (DOE) conducts climate simulations on some of the world’s largest supercomputers. These exascale machines use heterogeneous architectures with both CPUs and GPUs, and scientific codes must adapt to make full use of this computing power. Los Alamos National Lab is developing Omega: The Ocean Model for E3SM Global Applications, which is specifically designed for modern exascale computers. It uses external libraries that have been optimized for a variety of architectures to run on different supercomputers. Omega is an unstructured-mesh ocean model based on TRiSK numerical methods. It will be the new ocean component of the DOE’s Energy Exascale Earth System Model (E3SM). The algorithms in Omega follow those of the current ocean component, MPAS-Ocean, but it will be written in C++ rather than Fortran to take advantage of the Kokkos performance portability library. Omega spatial operators are written as Kokkos kernels to run efficiently on both CPUs and GPUs. Work on Omega began in 2023 with a new C++ framework for unstructured mesh partitioning, halo exchanges, parallel IO, and Kokkos interfaces. The current version, Omega-0, is being developed to solve the shallow water equations and at present includes all of the tendency terms but not time stepping. Here we share the results of Omega-0 verification and performance testing. Verification includes unit tests implemented with CTest as well as convergence tests in Polaris, an in-house python package with a large suite of test problems. Performance tests compare simulations conducted on CPUs versus GPUs and across different architectures: tests are run on Frontier, which has AMD “Optimized 3rd Gen EPYC” CPUs and AMD MI250X GPUs, as well as Perlmutter, which is composed of AMD EPYC 7763 CPUs and NVIDIA A100 GPUs.

58 GEOSCIENCES↗