Engineering Papers⌕ Search

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.

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

At least 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Exploring the Intersection of AI and Visualization in the Nuclear Industry

This presentation explores the impact of AI and visualization in advancing the nuclear industry by improving safety, operational efficiency, and decision-making processes. It highlights key applications such as real-time monitoring, predictive maintenance, and immersive training, while addressing challenges like data quality, regulatory hurdles, and the need for explainable AI. Additionally, the presentation outlines future directions, emphasizing the potential of AI-driven reactor design, advanced simulation tools, and ethical considerations to drive innovation and sustainability in nuclear operations.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Online evolutionary neural architecture search for multivariate non-stationary time series forecasting

Time series forecasting (TSF) is one of the most important tasks in data science. TSF models are usually pre-trained with historical data and then applied on future unseen datapoints. However, real-world time series data is usually non-stationary and models trained offline usually face problems from data drift. Models trained and designed in an offline fashion can not quickly adapt to changes quickly or be deployed in real-time. To address these issues, this work presents the Online NeuroEvolution-based Neural Architecture Search (ONE-NAS) algorithm, which is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Without any pre-training, ONE-NAS utilizes populations of RNNs that are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world, large-scale multivariate wind turbine data as well as the univariate Dow Jones Industrial Average (DJIA) dataset. These results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies. Additionally, results show that utilizing multiple populations of RNNs which are periodically repopulated provide significant performance improvements, allowing this online neural network architecture design and training to be successful.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Modeling MTS pyrolysis and SiC deposition kinetics using principal component analysis and neural networks

Accurate chemical kinetics modeling is crucial for improving the efficiency of chemical processing and synthesis of ceramic matrix composites. Detailed kinetic models are computationally expensive due to the large number of transported chemical species, while the simplified physics-based models, such as single-step global mechanisms, are efficient but often overlook key chemical intermediates and pathways. Recent deep learning approaches promise accurate and cost-effective models. Yet, they require additional closures for the transported nonlinear latent variables, complicating integration with existing solvers. In this work, we develop a hybrid linear—nonlinear reduced model for silicon carbide deposition from methyltrichlorosilane precursor by combining principal component analysis (PCA) and autoencoder (AE) neural network (NN) approaches. PCA is used to identify a smaller set of linear transport variables, enabling direct reuse of conventional transport solvers. NNs then reconstruct the full chemical state from these reduced variables. We demonstrate the method on a chemical vapor deposition reactor—comprising a gas-phase pyrolysis plug flow reactor and a heterogeneous surface reactor—over a wide range of temperatures, pressures, and residence times. Our PCA–AE model achieves high accuracy with only five transported scalars, achieving an eightfold cost reduction compared to detailed mechanisms, in both a priori (using data from the test set only) and a posteriori (coupled with a differential equation solver). In conclusion, notable errors arise primarily near training domain boundaries and for long residence times, indicating the need for domain shift indicators and better long-horizon predictions in future reduced chemistry model development.

autoencoder neural networks↗
DOE OSTI2022

Time-series forecasting using manifold learning, radial basis function interpolation, and geometric harmonics

We address a three-tier numerical framework based on nonlinear manifold learning for the forecasting of high-dimensional time series, relaxing the “curse of dimensionality” related to the training phase of surrogate/machine learning models. At the first step, we embed the high-dimensional time series into a reduced low-dimensional space using nonlinear manifold learning (local linear embedding and parsimonious diffusion maps). Then, we construct reduced-order surrogate models on the manifold (here, for our illustrations, we used multivariate autoregressive and Gaussian process regression models) to forecast the embedded dynamics. Finally, we solve the pre-image problem, thus lifting the embedded time series back to the original high-dimensional space using radial basis function interpolation and geometric harmonics. The proposed numerical data-driven scheme can also be applied as a reduced-order model procedure for the numerical solution/propagation of the (transient) dynamics of partial differential equations (PDEs). In conclusion, we assess the performance of the proposed scheme via three different families of problems: (a) the forecasting of synthetic time series generated by three simplistic linear and weakly nonlinear stochastic models resembling electroencephalography signals, (b) the prediction/propagation of the solution profiles of a linear parabolic PDE and the Brusselator model (a set of two nonlinear parabolic PDEs), and (c) the forecasting of a real-world data set containing daily time series of ten key foreign exchange rates spanning the time period 3 September 2001–29 October 2020.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Optimization of Water-Alternating-CO2 Injection Field Operations Using a Machine-Learning-Assisted Workflow

Summary This paper will present a robust workflow to address multiobjective optimization (MOO) of carbon dioxide (CO2)-enhanced oil recovery (EOR)-sequestration projects with a large number of operational control parameters. Farnsworth unit (FWU) field, a mature oil reservoir undergoing CO2 alternating water injection (CO2-WAG) EOR, will be used as a field case to validate the proposed optimization protocol. The expected outcome of this work would be a repository of Pareto-optimal solutions of multiple objective functions, including oil recovery, carbon storage volume, and project economics. FWU’s numerical model is used to demonstrate the proposed optimization workflow. Because using MOO requires computationally intensive procedures, machine-learning-based proxies are introduced to substitute for the high-fidelity model, thus reducing the total computation overhead. The vector machine regression combined with the Gaussian kernel (Gaussian-SVR) is used to construct proxies. An iterative self-adjusting process prepares the training knowledge base to develop robust proxies and minimizes computational time. The proxies’ hyperparameters will be optimally designed using Bayesian optimization to achieve better generalization performance. Trained proxies will be coupled with multiobjective particle swarm Optimization (MOPSO) protocol to construct the Pareto-front solution repository. The outcomes of this workflow will be a repository containing Pareto-optimal solutions of multiple objectives considered in the CO2-WAG project. The proposed optimization workflow will be compared with another established methodology using a multilayer neural network (MLNN) to validate its feasibility in handling MOO with a large number of parameters to control. Optimization parameters used include operational variables that might be used to control the CO2-WAG process, such as the duration of the water/gas injection period, producer bottomhole pressure (BHP) control, and water injection rate of each well included in the numerical model. It is proved that the workflow coupling Gaussian-SVR proxies and the iterative self-adjusting protocol is more computationally efficient. The MOO process is made more rapid by squeezing the size of the required training knowledge base while maintaining the high accuracy of the optimized results. The outcomes of the optimization study show promising results in successfully establishing the solution repository considering multiple objective functions. Results are also verified by validating the Pareto fronts with simulation results using obtained optimized control parameters. The outcome from this work could provide field operators an opportunity to design a CO2-WAG project using as many inputs as possible from the reservoir models. The proposed work introduces a novel concept that couples Gaussian-SVR proxies with a self-adjusting protocol to increase the computational efficiency of the proposed workflow and to guarantee the high accuracy of the obtained optimized results. More importantly, the workflow can optimize a large number of control parameters used in a complex CO2-WAG process, which greatly extends its utility in solving large-scale MOO problems in various projects with similar desired outcomes.

Energy & Fuels↗
DOE OSTI2023

Machine-Learning-Based Rotating Detonation Engine Diagnostics: Evaluation for Application in Experimental Facilities

Real-time monitoring of combustion behavior is a crucial step toward actively controlled rotating detonation engine (RDE) operation in laboratory and industrial environments. Various machine learning methods have been developed to advance diagnostic efficiencies from conventional postprocessing efforts to real-time methods. Here this work evaluates and compares conventional techniques alongside convolutional neural network (CNN) architectures trained in previous studies, including image classification, object detection, and time series classification, according to metrics affecting diagnostic feasibility, external applicability, and performance. Real-time, capable diagnostics are deployed and evaluated using an altered experimental setup. Image-based CNNs are applied to externally provided images to approximate dataset restrictions. Image classification using high-speed chemiluminescence images and time series classification using high-speed flame ionization and pressure measurements achieve classification speeds enabling real-time diagnostic capabilities, averaging laboratory-deployed diagnostic feedback rates of 4–5 Hz. Object detection achieves the most refined resolution of 20 μs in postprocessing. Image and time series classification require the additional correlation of sensor data, extending their time-step resolutions to 80 ms. Comparisons show that no single diagnostic approach outperforms its competitors across all metrics. This finding justifies the need for a machine learning portfolio containing a host of networks to address specific needs throughout the RDE research community.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

ML Classifier Fusion for Three Data Streams with Quality Inversely Proportional to Time Resolution

We consider a monitoring scenario of phenomenon using three different streams of measurements whose quality is proportional to their constant inter-arrival times. Each measurement of a stream needs to be binary-classified to reflect the state of interest of the phenomenon. A set of classifiers is separately trained and fused for each stream at its time resolution using measurements collected under known states. We present a machine learning method to fuse the outputs of these fusers to provide a final classification at the finest time resolution. We show that this fused-fusers method provides decisions with likely superior classification probability compared to the best individual classifiers and fused-classifiers. We derive generalization equations that guarantee a superior classification probability of fused-fusers with a confidence probability specified by the classifiers’ generalization equations. We apply these results to study a practical problem of classifying Pu/Np target dissolution events at a radiochemical processing facility using gamma spectral measurements of effluent flows.

Rao, Nageswara↗
DOE OSTI2024

Scalable learning of potentials to predict time-dependent Hartree–Fock dynamics

We propose a framework to learn the time-dependent Hartree–Fock (TDHF) inter-electronic potential of a molecule from its electron density dynamics. Although the entire TDHF Hamiltonian, including the inter-electronic potential, can be computed from first principles, we use this problem as a testbed to develop strategies that can be applied to learn a priori unknown terms that arise in other methods/approaches to quantum dynamics, e.g., emerging problems such as learning exchange–correlation potentials for time-dependent density functional theory. We develop, train, and test three models of the TDHF inter-electronic potential, each parameterized by a four-index tensor of size up to 60 × 60 × 60 × 60. Two of the models preserve Hermitian symmetry, while one model preserves an eight-fold permutation symmetry that implies Hermitian symmetry. Across seven different molecular systems, we find that accounting for the deeper eight-fold symmetry leads to the best-performing model across three metrics: training efficiency, test set predictive power, and direct comparison of true and learned inter-electronic potentials. All three models, when trained on ensembles of field-free trajectories, generate accurate electron dynamics predictions even in a field-on regime that lies outside the training set. To enable our models to scale to large molecular systems, we derive expressions for Jacobian-vector products that enable iterative, matrix-free training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Chemometrics and Experimental Design for the Quantification of Nitrate Salts in Nitric Acid: Near-Infrared Spectroscopy Absorption Analysis

Implementing remote, real-time spectroscopic monitoring of radiochemical processing streams in hot cell environments requires efficiency and simplicity. The success of optical spectroscopy for the quantification of species in chemical systems highly depends on representative training sets and suitable validation sets. Selecting a training set (i.e., calibration standards) to build multivariate regression models is both time- and resource-consuming using standard one-factor-at-a-time approaches. This study describes the use of experimental design to generate spectral training sets and a validation set for the quantification of sodium nitrate (0–1 M) and nitric acid (0.1–10 M) using the near-infrared water band centered at 1440 nm. Partial least squares regression models were built from training sets generated by both D- and I-optimal experimental designs and a one-factor-at-a-time approach. The prediction performance of each model was evaluated by comparing the bias and standard error of prediction for statistical significance. D- and I-optimal designs reduced the number of samples required to build regression models compared with one-factor-at-a-time while also improving performance. Models must be confirmed against a validation sample set when minimizing the number of samples in the training set. The D-optimal design performed the best when considering both performance and efficiency by improving predictive capability and reducing number of samples in the training set by 64% compared with the one-factor-at-a-time approach. The experimental design approach objectively selects calibration and validation spectral data sets based on statistical criterion to optimize performance and minimize resources.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2022

AI Data Quality Monitoring with Hydra

Hydra is an extensible framework for training and managing AI for near real time monitoring that aims to replace the tedious and repetitive data quality monitoring activities the shift crew and online monitoring coordinator typically perform. It continuously scans incoming data in the form of monitoring plots for signs of problems, flagging them for human review. A web app was developed such that experts can efficiently label images for training. Labels are stored in a database for use in training and model validation. Backed up by a comprehensive database, it utilizes an additional web based front-end for viewing the current monitoring status from anywhere in the world. The system has been in production use for the GlueX experiment at Jefferson Lab for more than 2 years with new features still under active development.

Britton, Thomas↗
DOE OSTI2021

Predicting fault slip via transfer learning

Abstract Data-driven machine-learning for predicting instantaneous and future fault-slip in laboratory experiments has recently progressed markedly, primarily due to large training data sets. In Earth however, earthquake interevent times range from 10’s-100’s of years and geophysical data typically exist for only a portion of an earthquake cycle. Sparse data presents a serious challenge to training machine learning models for predicting fault slip in Earth. Here we describe a transfer learning approach using numerical simulations to train a convolutional encoder-decoder that predicts fault-slip behavior in laboratory experiments. The model learns a mapping between acoustic emission and fault friction histories from numerical simulations, and generalizes to produce accurate predictions of laboratory fault friction. Notably, the predictions improve by further training the model latent space using only a portion of data from a single laboratory earthquake-cycle. The transfer learning results elucidate the potential of using models trained on numerical simulations and fine-tuned with small geophysical data sets for potential applications to faults in Earth.

58 GEOSCIENCES↗
DOE OSTI2022

Combining biomarker and virus phylogenetic models improves HIV-1 epidemiological source identification

To identify and stop active HIV transmission chains new epidemiological techniques are needed. Here, we describe the development of a multi-biomarker augmentation to phylogenetic inference of the underlying transmission history in a local population. HIV biomarkers are measurable biological quantities that have some relationship to the amount of time someone has been infected with HIV. To train our model, we used five biomarkers based on real data from serological assays, HIV sequence data, and target cell counts in longitudinally followed, untreated patients with known infection times. The biomarkers were modeled with a mixed effects framework to allow for patient specific variation and general trends, and fit to patient data using Markov Chain Monte Carlo (MCMC) methods. Subsequently, the density of the unobserved infection time conditional on observed biomarkers were obtained by integrating out the random effects from the model fit. This probabilistic information about infection times was incorporated into the likelihood function for the transmission history and phylogenetic tree reconstruction, informed by the HIV sequence data. To critically test our methodology, we developed a coalescent-based simulation framework that generates phylogenies and biomarkers given a specific or general transmission history. Testing on many epidemiological scenarios showed that biomarker augmented phylogenetics can reach 90% accuracy under idealized situations. Under realistic within-host HIV-1 evolution, involving substantial within-host diversification and frequent transmission of multiple lineages, the average accuracy was at about 50% in transmission clusters involving 5–50 hosts. Realistic biomarker data added on average 16 percentage points over using the phylogeny alone. Using more biomarkers improved the performance. Shorter temporal spacing between transmission events and increased transmission heterogeneity reduced reconstruction accuracy, but larger clusters were not harder to get right. More sequence data per infected host also improved accuracy. We show that the method is robust to incomplete sampling and that adding biomarkers improves reconstructions of real HIV-1 transmission histories. The technology presented here could allow for better prevention programs by providing data for locally informed and tailored strategies.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Evaluation of pre-training large language models on leadership-class supercomputers

Large language models (LLMs) have arisen rapidly to the center stage of artificial intelligence as the foundation models applicable to many downstream learning tasks. However, how to effectively build, train, and serve such models for many high-stake and first-principle-based scientific use cases are both of great interests and of great challenges. Moreover, pre-training LLMs with billions or even trillions of parameters can be prohibitively expensive not just for academic institutions, but also for well-funded industrial and government labs. Furthermore, the energy cost and the environmental impact of developing LLMs must be kept in mind. Here, in this work, we conduct a first-of-its-kind performance analysis to understand the time and energy cost of pre-training LLMs on the Department of Energy (DOE)’s leadership-class supercomputers. Employing state-of-the-art distributed training techniques, we evaluate the computational performance of various parallelization approaches at scale for a range of model sizes, and establish a projection model for the cost of full training. Our findings provide baseline results, best practices, and heuristics for pre-training such large models that should be valuable to HPC community at large. We also offer insights and optimization strategies for using the first exascale computing system, Frontier, to train models of the size of GPT-3 and beyond.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Dynamic three-dimensional maps of solute concentration and solute arrival times in synthetic and geologic porous media

Experimental and training data associated with the publication entitled ‘Three-Dimensional Permeability Inversion Using Convolutional Neural Networks and Positron Emission Tomography’ (published in WRR, DOI: 10.1029/2021WR031554). The dataset contain three-dimensional maps of various properties on four geologic rock cores obtained from X-ray Computed Tomography and Positron Emission Tomography imaging measurements. The synthetic training dataset used in the publication is also attached.

58 GEOSCIENCES↗
DOE OSTI2021

Mitigating Catastrophic Forgetting in Deep Learning in a Streaming Setting Using Historical Summary

Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.

Dash, Sajal↗
DOE OSTI2025

Forecasting Multi-Step-Ahead Street-Scale Nuisance Flooding using a seq2seq LSTM Surrogate Model for Real-Time Application in a Coastal-Urban City

In coastal-urban cities facing an elevated risk of nuisance flooding (by rain and tide) due to increased heavy rainfall, sea level rise, urbanization, and aging drainage systems, real-time flood forecasting at the street-scale can provide useful information to transportation decision-makers. Physics-Based Models (PBMs) that offer high accuracy come with high computational runtimes and costs that limit their application for real-time flood forecasting. To address this challenge, Machine Learning (ML) surrogate models trained from PBMs have been proposed to provide street-scale flood forecasts. Previous related studies have focused on using Long Short-Term Memory (LSTM) architectures to model hourly flood depth on streets. While LSTM models can capture input sequences effectively, they fall short in accurately preserving output sequences, limiting their suitability for multi-step-ahead forecasts. The seq2seq LSTM architecture offers a key advantage here by capturing the full sequence of input–output, making it potentially more suitable for multi-step-ahead flood forecasts compared to traditional LSTM models. However, seq2seq LSTM has not been tested for street-scale flood forecasting, particularly for rapidly fluctuating nuisance flooding events which require special attention to its temporal sequences. Hence, in this study, we applied the seq2seq LSTM model to explore multi-step-ahead street-scale nuisance flooding and compared its results to the traditional LSTM model as a benchmark model. LSTM and seq2seq LSTM surrogate models were applied to 22 flood-prone streets in Norfolk, Virginia, as a case study with a 4-hr (short-term) and 8-hr (long-term) lead time. The models were trained with environmental (rainfall and tide) and topographic (elevation, Topographic Wetness Index, and Depth-To-Water) features along with PBM-derived water depths for different storm events. The results demonstrated satisfactory performance of both LSTM and seq2seq LSTM surrogate models throughout the forecast period compared to the PBM. However, the seq2seq LSTM showed lower Mean Absolute Error (MAE)/ Root Mean Square Error (RMSE) and higher Nash–Sutcliffe Efficiency (NSE)/ correlation than the LSTM across most lead times, particularly for long-term forecasting due to its supremacy in handling both input–output sequences together, which is missing in the traditional LSTM. For example, in the long-term, the average RMSE ranges were 0.0268–0.0373 m for LSTM and 0.0226–0.0319 m for seq2seq LSTM, while in the short-term, they were 0.0263–0.0293 m and 0.0261–0.0283 m, respectively. Additionally, while both models exhibited similar performance in distinguishing flooded and non-flooded streets for flood depth ≥ 0.1 m, the seq2seq LSTM model demonstrated superior performance for higher flood depths (such as ≥ 0.2 m and ≥ 0.3 m). Once trained, inference took only 0.09 to 0.11 s (short-term) and 0.30 to 0.35 s (long-term) per storm event for the 22 streets, making the application highly suitable for real-time decision-making during nuisance flood events.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Detector pixel calibration of time-of-flight neutron diffractometers accelerated by machine learning

Modern time-of-flight neutron diffractometers at spallation neutron source are equipped with two dimensional detectors with fine pixelations. The flight path of neutrons from the moderator to the sample and to the detector needs to be precisely calibrated at detector pixel level using standard powders so the diffraction data from all the detector pixels can be correctly time-focused to produce high resolution diffraction peaks. The number of pixels can reach to millions which makes a single-pixel calibration process time-consuming, or even impossible, with conventional fitting routine. Here we presented a machine learning aided calibration process via a “training and predict” process by training machine learning models with the relations between the individual pixel time-of-flight diffraction pattern and fitted diffraction constant. The training models take a portion of the available pixels to predict the diffraction constants precisely and rapidly for massive pixel diffraction patterns.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Multiobjective Hyperparameter Optimization for Deep Learning Interatomic Potential Training Using NSGA-II

Deep neural network (DNN) potentials are an emerging tool for simulation of dynamical atomistic systems, with the promise of quantum mechanical accuracy at speedups of 10000$\times$. As with other DNN methods, hyperparameters used during training can make a substantial difference in model accuracy, and optimal settings vary with dataset. To enable rapid tuning of hyperparameters for DNN potential training, we developed a scalable multiobjective optimization evolutionary algorithm for supercomputers and tested it on the Summit system at the Oak Ridge Leadership Computing Facility (OLCF). The multiobjective approach is required due to the coupling of two learned values defining the potential: the energy and force. Using a large-scale implementation of the NSGA-II algorithm adapted for training DNN potentials, we discovered several optimal multiobjective combinations, including best choices of activation functions, learning rate scaling scheme, and pairing of the two radial cutoffs used in the three dimensional descriptor function.

Coletti, Mark↗