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 271 records · Page 15

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Artificial intelligence-based predictive modeling for imaging neutral particle analyzers on the DIII-D tokamak

The Imaging Neutral Particle Analyzer (INPA) at DIII-D is a diagnostic system used to accurately resolve the energy and spatial distributions of fast ions in fusion plasmas. A novel artificial intelligence (AI) technique named INPA-net is based on Reservoir Computing Networks and developed here to predict active and passive signals produced by charge-exchange reactions from injected and edge-cold neutrals, respectively, in magnetically confined fusion plasmas. This model is trained using a set of 21 time domain signals between 0 s to 3.35 s that includes injected beam and thermal plasma information, and 6444 real 2D experimental images of the INPA in 12 plasma discharges at DIII-D. The trained neural network is able to forecast experimental images in real-time. The model achieves an R-squared value of 0.91, which is higher than the 0.83 value achieved by a simple linear regression model. This improvement highlights the model's enhanced predictive accuracy for measured images from the validation set. This AI approach is valuable due to its rapid response times and potential for integration into real-time plasma control systems. A version of this model capable of generating syntehic images would be useful for the real-time monitoring of fast-ion transport. A comprehensive sensitivity study reveals that INPA-net maintains high performance even with variations in the input parameters, indicating the model's robustness and reliability. While developed for the INPA, the underlying architecture is adaptable and may be applied to various 2D imaging diagnostics in fusion research.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2023

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

Brewer, Wes↗

DOE OSTI2025

Surrogate models to optimize plasma-assisted atomic layer deposition in high aspect ratio features

In this work, we explore surrogate models to optimize plasma enhanced atomic layer deposition (PEALD) in high aspect ratio features. In plasma-based processes such as PEALD and atomic layer etching (ALE), surface recombination can dominate the reactivity of plasma species with the surface, which can lead to unfeasibly long exposure times to achieve full conformality inside nanostructures like high aspect ratio vias. Using a synthetic dataset based on simulations of PEALD, we train artificial neural networks to predict saturation times based on cross section thickness data obtained for partially coated conditions. The results obtained show that just two experiments in undersaturated conditions contain enough information to predict saturation times within 10% of the ground truth. A surrogate model trained to determine whether surface recombination dominates the plasma–surface interactions in a PEALD process achieves 99% accuracy. This demonstrates that machine learning can provide a new pathway to accelerate the optimization of PEALD processes in areas such as microelectronics. Our approach can be easily extended to ALE and more complex structures.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

Development of a machine learning model for polyethylene pyrolysis using a detailed reaction mechanism

Waste plastics have recently received significant attention as the issue of waste generation continues to increase. Thermal conversion processes, such as pyrolysis and gasification, are attractive potential technologies for utilizing waste plastics and reducing overall waste generation. Efficient utilization of plastics requires a detailed understanding of the conversion process such as pyrolysis and gasification. However, a mechanistic understanding of these processes lead to large and complex kinetic schemes that are not suited for large-scale and long-time simulation methods. Currently, most modeling approaches for pyrolysis and gasification rely on globally lumped, simplified kinetic schemes that provide results that are classified by their product type and not individual species, which limit the level of fidelity achieved via modeling. A machine learning (ML) model has been developed for the primary reactions of high-density polyethylene (HDPE) in an attempt to increase computational efficiency while still maintaining a high level of detail and accuracy. The ML model is trained on a detailed reaction mechanism containing 42 total species and 737 chemical reactions. A DeepONet branch and trunk architecture was adopted to train the model using time-steps relevant to computational fluid dynamics simulations. The ML used physics-informed loss functions to ensure mass conservation. The surrogate model has been deployed in simple MFiX CFD simulations, single particle and an experimental drop tube reactor, and has shown promising performance compared to the original scheme.

Houston, Ross↗

DOE OSTI2020

Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations

Here we propose a generalized space-time domain decomposition approach for the physics-informed neural networks (PINNs) to solve nonlinear partial differential equations (PDEs) on arbitrary complex-geometry domains. The proposed framework, named eXtended PINNs ( X P I N N s ), further pushes the boundaries of both PINNs as well as conservative PINNs (cPINNs), which is a recently proposed domain decomposition approach in the PINN framework tailored to conservation laws. Compared to PINN, the XPINN method has large representation and parallelization capacity due to the inherent property of deployment of multiple neural networks in the smaller subdomains. Unlike cPINN, XPINN can be extended to any type of PDEs. Moreover, the domain can be decomposed in any arbitrary way (in space and time), which is not possible in cPINN. Thus, XPINN offers both space and time parallelization, thereby reducing the training cost more effectively. In each subdomain, a separate neural network is employed with optimally selected hyperparameters, e.g., depth/width of the network, number and location of residual points, activation function, optimization method, etc. A deep network can be employed in a subdomain with complex solution, whereas a shallow neural network can be used in a subdomain with relatively simple and smooth solutions. We demonstrate the versatility of XPINN by solving both forward and inverse PDE problems, ranging from one-dimensional to three-dimensional problems, from time-dependent to time-independent problems, and from continuous to discontinuous problems, which clearly shows that the XPINN method is promising in many practical problems. The proposed XPINN method is the generalization of PINN and cPINN methods, both in terms of applicability as well as domain decomposition approach, which efficiently lends itself to parallelized computation. The XPINN code is available on h t t p s : / / g i t h u b . c o m / A m e y a J a g t a p / X P I N N s .

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

MMMnet: A Neural Network Surrogate for Real-Time Transport Prediction Based on the Updated Multi-Mode Model

The Multi-Mode Model (MMM) is a physics-based anomalous transport model integrated into TRANSP for predicting electron and ion thermal transport, electron and impurity particle transport, and toroidal and poloidal momentum transport. While MMM provides valuable predictive capabilities, its computational cost, although manageable for standard simulations, is too high for real-time control applications. MMMnet, a neural network-based surrogate model, is developed to address this challenge by significantly reducing computation time while maintaining high accuracy. Trained on TRANSP simulations of DIII-D discharges, MMMnet incorporates an updated version of MMM (9.0.10) with enhanced physics, including isotopic effects, plasma shaping via effective magnetic shear, unified correlation lengths for ion-scale modes, and a new physics-based model for the electromagnetic electron temperature gradient mode. A key advancement is MMMnet’s ability to predict all six transport coefficients, providing a comprehensive representation of plasma transport dynamics. MMMnet achieves a two-order-of-magnitude speed improvement while maintaining strong correlation with MMM diffusivities, making it well-suited for real-time tokamak control and scenario optimization.

DIII-D↗

DOE OSTI2022

Network Models of Active Degradation Mechanisms and Pathways for Service Life Prediction of Indoor and Outdoor PV Modules

ct: PV service lifetime prediction (SLP) enables accurate calculation of levelized cost of energy (LCOE), which is crucial to rationalizing PV investment and installation. However, SLP is challeging since PV reliability in the field is affected by many combined factors, including various environmental stresses and module quality. In order to map out the active degradation mechanisms and pathways that best resemble real world conditions, we introduce the framework of a study protocol and use network models fitted to data, to enable analysis and SLP of complex PV systems with multiple active degradation mechanisms. The study protocol is the experimental design, including module variants and different exposure conditions, selection of evaluation methods, time-series data acquisition and training of network models to these data. We present SLP of minimodules in the lab and PV systems in the field. For lab SLP, minimodules with 8 variants based on manufacturer, architecture, and encapsulation were prepared and aged in modified damp heat with or without full spectrum light exposure. Stepwise I-V and Suns-Voc data acquisition tracks changes in electrical properties including Rs,IV, Isc,IV, Vmp,PIV providing insights into power loss of minimodules. Network structural equation modeling (netSEM) was utilized to construct degradation pathway models that identify active degradation mechanisms and predict power loss over time. For field SLP, datastreams of Pmp values and I-V curve datastreams of two types of modules installed in three distinctly different Köppen-Geiger climate zones for 9 years were acquired. With power loss modes corresponding to uniform current loss (ΔPIsc), recombination (ΔPVoc), series resistance (ΔPRs), and current mismatch (ΔPImis) determined, the performance loss rates (PLR) were determined using PVplr. We show how to establish a study protocol framework to ensure appropriate parametric variations and valid data collection from the variants of your complex systems. Then the data-driven netSEM model fitting provides a comprehensive mapping of multiple active degradation mechanisms, and accurate service life prediction.

network model, degradation, photovoltaic, solar↗

DOE OSTI2022

Timing measurement apparatus

Methods, devices and systems for providing accurate measurements of timing errors using optical techniques are described. An example timing measurement device includes an optical hybrid that receives two optical pulse trains and produces two or more phase shifted optical outputs. The timing measurement device further includes two or more optical filters that receive the outputs of the optical hybrid to produce multiple pulse signals with distinctive frequency bands. The device also includes one or more photodetectors and analog-to-digital converters to receive to produce electrical signals in the digital domain corresponding to the optical outputs of the hybrid. A timing error associated with the optical pulse trains can be determined using the electrical signals in digital domain based on a computed phase difference between a first frequency band signal and a second frequency band signal and a computed frequency difference between the first frequency band signal and the second frequency band.

DeVore, Peter Thomas Setsuda↗

DOE OSTI2024

Timing measurement apparatus

DeVore, Peter Thomas Setsuda↗

DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Probing the evolution of fault properties during the seismic cycle with deep learning

We use seismic waves that pass through the hypocentral region of the 2016 M6.5 Norcia earthquake together with Deep Learning (DL) to distinguish between foreshocks, aftershocks and time-to-failure (TTF). Binary and N-class models defined by TTF correctly identify seismograms in test with > 90% accuracy. We use raw seismic records as input to a 7 layer CNN model to perform the classification. Here we show that DL models successfully distinguish seismic waves pre/post mainshock in accord with lab and theoretical expectations of progressive changes in crack density prior to abrupt change at failure and gradual postseismic recovery. Performance is lower for band-pass filtered seismograms (below 10 Hz) suggesting that DL models learn from the evolution of subtle changes in elastic wave attenuation. Tests to verify that our results indeed provide a proxy for fault properties included DL models trained with the wrong mainshock time and those using seismic waves far from the Norcia mainshock; both show degraded performance. Our results demonstrate that DL models have the potential to track the evolution of fault zone properties during the seismic cycle. If this result is generalizable it could improve earthquake early warning and seismic hazard analysis.

58 GEOSCIENCES↗

DOE OSTI2023

Adaptive autoencoder latent space tuning for more robust machine learning beyond the training set for six-dimensional phase space diagnostics of a time-varying ultrafast electron-diffraction compact accelerator

In this work, we present a general adaptive latent space tuning approach for improving the robustness of machine learning tools with respect to time variation and distribution shift. We demonstrate our approach by developing an encoder-decoder convolutional neural network-based virtual 6D phase space diagnostic of charged particle beams in the HiRES ultrafast electron diffraction (UED) compact particle accelerator with uncertainty quantification. Our method utilizes model-independent adaptive feedback to tune a low dimensional 2D latent space representation of ~1 million dimensional objects which are the 15 unique 2D projections (x, y),...,(z, p z ) of the 6D phase space (x, y, z, p x , p y , p z ) of the charged particle beams. We demonstrate our method with numerical studies of short electron bunches utilizing experimentally measured UED input beam distributions.

43 PARTICLE ACCELERATORS↗

DOE OSTI2020

Newton versus the machine: solving the chaotic three-body problem using deep neural networks

ABSTRACT Since its formulation by Sir Isaac Newton, the problem of solving the equations of motion for three bodies under their own gravitational force has remained practically unsolved. Currently, the solution for a given initialization can only be found by performing laborious iterative calculations that have unpredictable and potentially infinite computational cost, due to the system’s chaotic nature. We show that an ensemble of converged solutions for the planar chaotic three-body problem obtained using an arbitrarily precise numerical integrator can be used to train a deep artificial neural network (ANN) that, over a bounded time interval, provides accurate solutions at a fixed computational cost and up to 100 million times faster than the numerical integrator. In addition, we demonstrate the importance of training an ANN using converged solutions from an arbitrary precise integrator, relative to solutions computed by a conventional fixed precision integrator, which can introduce errors in the training data, due to numerical round-off and time discretization, that are learned by the ANN. Our results provide evidence that, for computationally challenging regions of phase space, a trained ANN can replace existing numerical solvers, enabling fast and scalable simulations of many-body systems to shed light on outstanding phenomena such as the formation of black hole binary systems or the origin of the core collapse in dense star clusters.

Breen, Philip G.↗

DOE OSTI2024

Powering Data Centers with Clean Energy: A Techno-Economic Case Study of Nuclear and Renewable Energy Dependability

Rising data demands from artificial intelligence (AI) and large language models (LLMs) generating images, videos, and text have prompted increased need for larger and more robust data centers in the United States. Major companies interested in these larger data centers face the choice of linking them to existing regional grids, building stand-alone power supplies onsite, or a combination of both. The request, review, and approval process for new transmission lines to grids in the United States, however, has grown in recent years to times spans rivaling those of new construction for nuclear power plants. Building an islanded power supply for each data center is therefore becoming a prominent option. In this case study, several technologies are modeled in techno-economic simulations for long-term system costs subject to fixed electricity demand from a singular data center. A 250 MWe data center is assumed with additional 50 MWe for resiliency. Techno-economic simulations are conducted using the Holistic Energy Resource Optimization Network (HERON) software, which is a part of the Framework for Optimization of Resources and Economics (FORCE) tool suite. Technologies considered include solar, wind, lithium-ion batteries, and several types of nuclear reactors: large-scale reactors, small modular reactors, and microreactors. A low- and high-cost estimate for each technology is assumed to develop a range of expected economic performance. Low-cost estimates included several clean energy production tax credits. Different combinations of renewable energy generators with nuclear reactors are considered, ranging from a fully renewable-powered data center to a fully nuclear-powered data center. Historic time series of wind and solar availability from the Texas grid are used to train a reduced order model; this model then generates unique time series with similar characteristics of the training dataset. Multiple scenarios of weather and subsequent operations are simulated for each renewable-nuclear combination to determine total costs throughout the project lifetime. Fully renewable-powered configurations required large amounts of installed capacity (GW scale) in the simulations to meet the fixed demand of the data center. This is due to some scenarios in the historical dataset which captured low-wind and low-solar days, requiring over-building of these technologies as well as batteries to compensate for the low amounts of electricity generation. Fully nuclear-powered configurations outperformed the fully renewable and mixed renewable-nuclear configurations in terms of cost, with ranges between $1B and $10B in 2023 USDs compared to $40B+ for fully renewable configurations. Of the nuclear technologies, small modular reactors performed better economically than large-scale nuclear models due to lower projected capital costs, and both performed better than the microreactor models. These results demonstrate the applicability of firm, dispatchable electricity resources from baseload generators like nuclear power plants for operating facilities that run at constant power without daily variability.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Autoregressive long-horizon prediction of plasma edge dynamics *

Accurate modeling of scrape-off layer (SOL) and divertor-edge dynamics is vital for designing plasma-facing components in fusion devices. High-fidelity edge fluid/neutral codes such as SOLPS-ITER capture SOL physics with high accuracy, but their computational cost limits broad parameter scans and long transient studies. We present transformer-based, autoregressive surrogates for efficient prediction of 2D, time-dependent plasma edge state fields. Trained on SOLPS-ITER spatiotemporal data for the KSTAR tokamak, the surrogates forecast electron temperature, electron density, and radiated power over extended horizons. We evaluate model variants trained with increasing autoregressive horizons (1–100 steps) on short- and long-horizon prediction tasks. Longer-horizon training systematically improves rollout stability and mitigates error accumulation, enabling stable predictions over hundreds to thousands of steps and reproducing key dynamical features such as the motion of high-radiation regions. Measured end-to-end wall-clock times show the surrogate is orders of magnitude faster than SOLPS-ITER, enabling rapid parameter exploration. Prediction accuracy degrades when the surrogate enters physical regimes not represented in the training dataset, motivating future work on data enrichment and physics-informed constraints. Overall, this approach provides a fast, accurate surrogate for computationally intensive plasma edge simulations, supporting rapid scenario exploration, control-oriented studies, and progress toward real-time applications in fusion devices.

autoregressive deep learning↗

DOE OSTI2023

Data-driven predictions of the time remaining until critical global warming thresholds are reached

Leveraging artificial neural networks (ANNs) trained on climate model output, we use the spatial pattern of historical temperature observations to predict the time until critical global warming thresholds are reached. Although no observations are used during the training, validation, or testing, the ANNs accurately predict the timing of historical global warming from maps of historical annual temperature. The central estimate for the 1.5 °C global warming threshold is between 2033 and 2035, including a ±1σ range of 2028 to 2039 in the Intermediate (SSP2-4.5) climate forcing scenario, consistent with previous assessments. However, our data-driven approach also suggests a substantial probability of exceeding the 2 °C threshold even in the Low (SSP1-2.6) climate forcing scenario. While there are limitations to our approach, our results suggest a higher likelihood of reaching 2 °C in the Low scenario than indicated in some previous assessments—though the possibility that 2 °C could be avoided is not ruled out. Explainable AI methods reveal that the ANNs focus on particular geographic regions to predict the time until the global threshold is reached. Our framework provides a unique, data-driven approach for quantifying the signal of climate change in historical observations and for constraining the uncertainty in climate model projections. Given the substantial existing evidence of accelerating risks to natural and human systems at 1.5 °C and 2 °C, our results provide further evidence for high-impact climate change over the next three decades.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Learning to learn by using nonequilibrium training protocols for adaptable materials

Evolution in time-varying environments naturally leads to adaptable biological systems that can easily switch functionalities. Advances in the synthesis of environmentally responsive materials therefore open up the possibility of creating a wide range of synthetic materials which can also be trained for adaptability. We consider high-dimensional inverse problems for materials where any particular functionality can be realized by numerous equivalent choices of design parameters. By periodically switching targets in a given design algorithm, we can teach a material to perform incompatible functionalities with minimal changes in design parameters. We exhibit this learning strategy for adaptability in two simulated settings: elastic networks that are designed to switch deformation modes with minimal bond changes and heteropolymers whose folding pathway selections are controlled by a minimal set of monomer affinities. The resulting designs can reveal physical principles, such as nucleation-controlled folding, that enable such adaptability.

Science & Technology - Other Topics↗