Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “train”

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 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

A perfect amalgam - the combination of company in-house training with an academic online certificate program

A well-trained and qualified workforce is an essential element in the modern day work place of the nuclear industry. For generations, from the guilds of the Middle Age through to the early Industrial Age, people learned their crafts through hands-on training provided at the hands of masters. Today, though there is an ever-pressing need for mentoring in the workplace, the fast-paced environment and lack of time to develop specific in-house training programs can create hindrances to both formal and informal learning in the work place. One way to overcome this gap is through private company and academic collaboration. In 2012, the University of Nevada, Las Vegas (UNLV) developed a Nuclear Regulatory Commission sponsored Nuclear Criticality Safety Certificate Program. In collaboration with URENCO USA, an online version of the program was also developed to assist the URENCO criticality workforce in the nuclear criticality safety (NCS) qualification process to further their education. This paper looks into the differences between formal and informal learning and how factors, which shape informal learning, are used to compliment formal learning in the work environment. It further discusses how a collaborative relationship between private and academic partners can assist a company in maintaining a high level of expertise, while assisting with a company's goals of fostering, sustaining and strengthening the nuclear safety culture. (authors)

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2020

Training for Decommissioning and Waste Management - Competence in the Field of Nuclear Engineering - 20137

Due to the phase-out of nuclear power and the reorganization of the participating organizations in Germany, the demand for qualified personnel has increased. But the number of nuclear study programs has rapidly decreased in Germany, although qualified employees are needed for the upcoming tasks in nuclear decommissioning. The solution for those challenging tasks can only be achieved through a strategic approach, involving all stakeholders. AiNT supports this process by offering a tailor-made Education and Training (E and T) program in cooperation with a wide range of partners and initiating the project BEAST (Building competence - Expert knowledge - Applied techniques - Safe decommissioning - Train fellows) as part of the OECD NEA framework Nuclear Education, Skills and Technology (NEST) program. This paper describes the current situation in Germany, provides insight into the education and training program of AiNT, and presents the project BEAST. We are currently looking for international partner institutions that would like to cooperate with us within the framework of the BEAST project and expand the range of topics. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

3D Virtual Simulation for Radiation Safety and Hazards Identification Training

This presentation will be presented at CAES codebreaker session on May 4th. The slides include two projects that demonstrate how virtual training can benefit from visualization technology. One is a collaboration project between the Applied Visualization Laboratory and College of Eastern Idaho for radiation safety and survey training. The other one is Idaho National Laboratory's hazards identification online training that utilized LiDAR technology.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Iterative sampling of expensive simulations for faster deep surrogate training

Deep neural network (DNN) surrogates of expensive physics simulations are enabling a rapid change in the way that common experimental design and analysis tasks are approached. Surrogate models allow simulations to be performed in parallel and separately from downstream tasks, thereby enabling analyses that would be impossible with the simulation in-the-loop; surrogates based on DNNs can effectively emulate diverse non-scalar data of the types collected in fusion and laboratory-astrophysics experiments. The challenge is in training the surrogate model, for which large ensembles of physics simulations must be run, preferably without wasting computational effort on uninteresting simulations. Here, in this paper, we present an iterative sampling scheme that can preferentially propose simulations in interesting regions of parameter space without neglecting unexplored regions, allowing high-quality and wide-ranging surrogate models to be trained using 2–3 times fewer simulations compare to space-filling designs. Our approach uses an explicit importance function defined on the simulation output space, balanced against a measure of simulation density which serves as a proxy for surrogate accuracy. It is easy to implement and can be tuned to find interesting simulations early in the study, allowing surrogates to be trained quickly and refined as new simulations become available; this represents an important step towards the routine generation of deep surrogate models quickly enough to be truly relevant to experimental work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Multi-task Parallelism for Robust Pre-training of Graph Foundation Models on Multi-source, Multi-fidelity Atomistic Modeling Data

Graph foundation models using graph neural networks promise sustainable, efficient atomistic modeling. To tackle challenges of processing multi-source, multi-fidelity data during pre-training, recent studies employ multi-task learning, in which shared message passing layers initially process input atomistic structures regardless of source, then route them to multiple decoding heads that predict data-specific outputs. This approach stabilizes pre-training and enhances a model’s transferability to unexplored chemical regions. Preliminary results on approximately four million structures are encouraging, yet questions remain about generalizability to larger, more diverse datasets and scalability on supercomputers. We propose a multi-task parallelism method that distributes each head across computing resources with GPU acceleration. Implemented in the open-source HydraGNN architecture, our method was trained on over 24 million structures from five datasets and tested on the Perlmutter, Aurora, and Frontier supercomputers, demonstrating efficient scaling on all three highly heterogeneous super-computing architectures.

Lupo Pasini, Massimiliano [ORNL] (ORCID:0000000249↗
DOE OSTI2018

Aerobic exercise training decreases cereblon and increases AMPK signaling in the skeletal muscle of STZ-induced diabetic rats

Highlights: • STZ-induced diabetes increased levels of CRBN protein in the skeletal muscle. • Aerobic exercise training attenuates level of CRBN protein and increases AMPK signaling in skeletal muscle. • CRBN is a regulator of exercise-mediated anti-diabetic effect. Cereblon (CRBN) has been reported as a negative regulator of adenosine monophosphate-activated protein kinase (AMPK). Aerobic exercise training has been shown to increase AMPK, which resulted in glucose regulation in skeletal muscle. However, the expression level of CRBN and its association with the physiological modulation of glucose are still unclear. Male Sprague-Dawley rats (5-week-old, n = 18) were assigned to control, streptozotocin (STZ, 65 mg/kg)-induced diabetic group, and STZ + exercise (STZ + EXE) group with six rats in each group. Rats in the STZ + EXE group exercised by treadmill running (20 m/min, 60 min, 4 times/week) for 8 weeks. Compared with the STZ group, blood glucose was significantly decreased in the STZ + EXE group. The skeletal muscle of rats in the STZ + EXE group showed a significant decrease in CRBN levels and an increase in AMPK, protein kinase B, peroxisome proliferator-activated receptor gamma coactivator 1-alpha, fibronectin type III domain-containing protein 5, glucose transporter type 4, superoxide dismutase 1, and uncoupling protein 3 levels. These results suggest that CRBN is a potential regulator of glucose homeostasis in the skeletal muscle. Moreover, our results suggest that aerobic exercise training may provide an important physiological treatment for type 1 diabetes by decreasing CRBN and increasing AMPK signaling in skeletal muscle.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications

In this work we introduce a novel two-level overlapping additive Schwarz preconditioner for accelerating the training of scientific machine learning applications. The design of the proposed preconditioner is motivated by the nonlinear two-level overlapping additive Schwarz preconditioner. The neural network parameters are decomposed into groups (subdomains) with overlapping regions. In addition, the network’s feed-forward structure is indirectly imposed through a novel subdomain-wise synchronization strategy and a coarse-level training step. Through a series of numerical experiments, which consider physicsinformed neural networks and operator learning approaches, we demonstrate that the proposed two-level preconditioner significantly speeds up the convergence of the standard (LBFGS) optimizer while also yielding more accurate machine learning models. Moreover, the devised preconditioner is designed to take advantage of model-parallel computations, which can further reduce the training time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Forest aboveground biomass estimation through integration of sentinel-2 and PALSAR-2 time series: assessing models trained on GEDI and field inventory benchmarks

Accurate and spatially explicit forest Aboveground Biomass (AGB) mapping through remote sensing is critical for quantifying terrestrial carbon stocks and informing effective forest management strategies. However, AGB estimation in dense forests with complex terrain remains challenging due to satellite sensor signal saturation problem (saturation issue occurs in high biomass forests), structural complexity, and limited ground truth for calibration. This study presents a novel framework that integrates multi-temporal Sentinel-2 optical imagery, ALOS PALSAR-2 Synthetic Aperture Radar (SAR) data, and topographic variables with explainable Machine Learning to map AGB across mountainous forests within subtropical and temperate oceanic climate zones of Mexico. We evaluate the effects of temporal granularity and sensor synergy by comparing multiple temporal inputs and sensor configurations (Sentinel-2, PALSAR-2, and their fusion), and assess model performance using two reference datasets: NASA GEDI LiDAR-derived biomass and Mexico’s National Forest and Soil Inventory (INFyS). Our results showed that models trained on INFyS consistently outperformed those trained on GEDI, highlighting limitations in GEDI’s reliability in biomass estimates within this study region. Furthermore, the integration of Sentinel-2 and PALSAR-2 provided improved predictions compared to single-sensor models, particularly when combined with temporally explicit yearly statistics. The best-performing model, which was trained on INFyS data, and considered both Sentinel-2 and PALSAR-2 yearly statistics, as well as topographic variables, achieved an R2 of 0.64, RMSE of 51.10 Mg/ha, and relative RMSE (rRMSE) of 58.69%. Explainable ML analysis identified Sentinel-2 spectral indices and topographic features as key predictors, while PALSAR-2 metrics provided complementary information, partially mitigating saturation effects in high-biomass areas. Specifically, integrating both sensors substantially improved AGB estimation in high biomass forest (≥200 Mg/ha), yielding 98% gains over optical-only model, with resulting estimates exceeding GEDI L4B by 29% and ESA-CCI-BIOMASS by 174%. Terrain-stratified analysis indicated close agreement with GEDI in low-slope areas, with increasing divergence as slope steepness increased, while estimates remained consistently higher than ESA-CCI-BIOMASS across all slope classes. The proposed approach advances multi-sensor fusion and temporal feature engineering for AGB mapping using open-access satellite datasets, providing a scalable and reproducible framework for annual biomass monitoring in topographically complex mountainous forests. The resulting 25 m resolution biomass product has the potential to provide spatially detailed information for forest monitoring and may support applications in carbon accounting and forest management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Convergence of variational Monte Carlo simulation and scale-invariant pre-training

We provide theoretical convergence bounds for the variational Monte Carlo (VMC) method as applied to optimize neural network wave functions for the electronic structure problem. Here, we study both the energy minimization phase and the supervised pre-training phase that is commonly used prior to energy minimization. For the energy minimization phase, the standard algorithm is scale-invariant by design, and we provide a proof of convergence for this algorithm without modifications. The pre-training stage typically does not feature such scale-invariance. We propose using a scale-invariant loss for the pretraining phase and demonstrate empirically that it leads to faster pre-training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Divergent effects of sex and calcium/vitamin D supplementation on serum magnesium and markers of bone structure and function during initial military training

Maintaining Mg status may be important for military recruits, a population that experiences high rates of stress fracture during initial military training (IMT). The objectives of this secondary analysis were to (1) compare dietary Mg intake and serum Mg in female and male recruits pre- and post-IMT, (2) determine whether serum Mg was related to parameters of bone health pre-IMT, and (3) whether Ca and vitamin D supplementation (Ca/vitamin D) during IMT modified serum Mg. Females (n 62) and males (n 51) consumed 2000 mg of Ca and 25 μg of vitamin D/d or placebo during IMT (12 weeks). Dietary Mg intakes were estimated using FFQ, serum Mg was assessed and peripheral quantitative computed tomography was performed on the tibia. Dietary Mg intakes for females and males pre-IMT were below the estimated average requirement and did not change with training. Serum Mg increased during IMT in females (0·06 ± 0·08 mmol/l) compared with males (–0·02 ± 0·10 mmol/l; P < 0·001) and in those consuming Ca/vitamin D (0·05 ± 0·09 mmol/l) compared with placebo (0·001 ± 0·11 mmol/l; P = 0·015). In females, serum Mg was associated with total bone mineral content (BMC, β = 0·367, P = 0·004) and robustness (β = 0·393, P = 0·006) at the distal 4 % site, stress–strain index of the polaris axis (β = 0·334, P = 0·009) and robustness (β = 0·420, P = 0·004) at the 14 % diaphyseal site, and BMC (β = 0·309, P = 0·009) and stress–strain index of the polaris axis (β = 0·314, P = 0·006) at the 66 % diaphyseal site pre-IMT. No significant relationships between serum Mg and bone measures were observed in males. Findings suggest that serum Mg may be modulated by Ca/vitamin D intake and may impact tibial bone health during training in female military recruits.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2017

Tensor-Train Split-Operator Fourier Transform (TT-SOFT) Method: Multidimensional Nonadiabatic Quantum Dynamics

We introduce the “tensor-train split-operator Fourier transform” (TT-SOFT) method for simulations of multidimensional nonadiabatic quantum dynamics. TT-SOFT is essentially the grid-based SOFT method implemented in dynamically adaptive tensor-train representations. In the same spirit of all matrix product states, the tensor-train format enables the representation, propagation, and computation of observables of multidimensional wave functions in terms of the grid-based wavepacket tensor components, bypassing the need of actually computing the wave function in its full-rank tensor product grid space. We demonstrate the accuracy and efficiency of the TT-SOFT method as applied to propagation of 24-dimensional wave packets, describing the S 1 / S 2 interconversion dynamics of pyrazine after UV photoexcitation to the S 2 state. Furthermore, our results show that the TT-SOFT method is a powerful computational approach for simulations of quantum dynamics of polyatomic systems since it avoids the exponential scaling problem of full-rank grid-based representations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Event‐Based Training in Label‐Limited Regimes

Abstract The distribution of attributes assigned using data on independent sensors for a specific source, for example, magnitude, can be richly descriptive for final event characterization and associated uncertainty. Attribute distributions can also provide powerful context for event characterization in the absence of comprehensive annotation. This work develops a way to leverage distributional information across a set of sensors in the absence of comprehensive annotation as a domain‐informed regularization term applied during gradient‐based learning. The regularization term is the basis of event‐based training which I show can be a powerful semi‐supervised learning (SSL) approach. I first use a simple feed forward neural network and a toy data set to outline how data set structure interacts with the assumptions inherent to many semi‐supervised learning approaches. I then demonstrate the effectiveness of event‐based training using a deep convolutional neural network for seismic event classification in Utah, which increases SSL accuracy from 92% to 97% on event classification with a limited number of training labels.

Linville, Lisa M.↗
DOE OSTI2024

Robust training of machine learning interatomic potentials with dimensionality reduction and stratified sampling

Abstract Machine learning interatomic potentials (MLIPs) enable accurate simulations of materials at scales beyond that accessible by ab initio methods and play an increasingly important role in the study and design of materials. However, MLIPs are only as accurate and robust as the data on which they are trained. Here, we present DImensionality-Reduced Encoded Clusters with sTratified (DIRECT) sampling as an approach to select a robust training set of structures from a large and complex configuration space. By applying DIRECT sampling on the Materials Project relaxation trajectories dataset with over one million structures and 89 elements, we develop an improved materials 3-body graph network (M3GNet) universal potential that extrapolates more reliably to unseen structures. We further show that molecular dynamics (MD) simulations with the M3GNet universal potential can be used instead of expensive ab initio MD to rapidly create a large configuration space for target systems. We combined this scheme with DIRECT sampling to develop a reliable moment tensor potential for titanium hydrides without the need for iterative augmentation of training structures. This work paves the way for robust high-throughput development of MLIPs across any compositional complexity.

Qi, Ji (ORCID:0000000158089931)↗
DOE OSTI2025

ORBITaL-Net: A labeled training library for large-scale building feature extraction

Over the course of several years, nearly 1.5 million building outlines have been created from approximately 128,000 training tiles covering roughly 7,000 km 2 of very high-resolution multispectral overhead imagery, primarily dated between 2010 and 2020. This dataset, dubbed the Oak Ridge Building Image and TrAining Label Net (ORBITaL-Net), is designed for machine learning applications and is global in scope, with samples drawn from 72 countries across North America, South America, Africa, Europe, and Asia. ORBITaL-Net captures a great diversity in geographic setting, structural characteristics, land use (urban and rural), terrain, and imagery conditions. While the labeled building outlines are themselves valuable, the dataset’s true strength lies in the pairing of these labels with corresponding reference imagery, which is being released for open source use. Similar to SpaceNet and Replicable AI For Microplanning (ramp), this building outline dataset will allow the larger computer vision community from academia, government, and industry the opportunity to develop robust, scalable, and generalizable geospatial machine learning techniques. Unlike SpaceNet and ramp, which offer high resolution labels and imagery primarily for large urban cities, ORBITaL-Net is not focused on training samples from heavily populated areas but instead aims to capture the innate variability of conditions present in both the physical environment and imagery collections.

Geography↗
DOE OSTI2019

Stable, predictable and training-free operation of superconducting Bi-2212 Rutherford cable racetrack coils at the wire current density of 1000 A/mm 2

High-temperature superconductors (HTS) could enable high-field magnets stronger than is possible with Nb-Ti and Nb 3 Sn, but two challenges have so far been the low engineering critical current density J E , especially in high-current cables, and the danger of quenches. Most HTS magnets made so far have been made out of REBCO coated conductor. Here we demonstrate stable, reliable and training-quench-free performance of Bi-2212 racetrack coils wound with a Rutherford cable fabricated from wires made with a new precursor powder. These round multifilamentary wires exhibited a record J E up to 950 A/mm 2 at 30 T at 4.2 K. These coils carried up to 8.6 kA while generating 3.5 T at 4.2 K at a J E of 1020 A/mm 2 . Different from the unpredictable training performance of Nb-Ti and Nb 3 Sn magnets, these Bi-2212 magnets showed no training quenches and entered the flux flow state in a stable manner before thermal runaway and quench occurred. Also different from Nb-Ti, Nb 3 Sn, and REBCO magnets for which localized thermal runaways occur at unpredictable locations, the quenches of Bi-2212 magnets consistently occurred in the high field regions over a long conductor length. These characteristics make quench detection simple, enabling safe protection, and suggest a new paradigm of constructing quench-predictable superconducting magnets from Bi-2212.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

TEMImageNet training library and AtomSegNet deep-learning models for high-precision atom segmentation, localization, denoising, and deblurring of atomic-resolution images

Abstract Atom segmentation and localization, noise reduction and deblurring of atomic-resolution scanning transmission electron microscopy (STEM) images with high precision and robustness is a challenging task. Although several conventional algorithms, such has thresholding, edge detection and clustering, can achieve reasonable performance in some predefined sceneries, they tend to fail when interferences from the background are strong and unpredictable. Particularly, for atomic-resolution STEM images, so far there is no well-established algorithm that is robust enough to segment or detect all atomic columns when there is large thickness variation in a recorded image. Herein, we report the development of a training library and a deep learning method that can perform robust and precise atom segmentation, localization, denoising, and super-resolution processing of experimental images. Despite using simulated images as training datasets, the deep-learning model can self-adapt to experimental STEM images and shows outstanding performance in atom detection and localization in challenging contrast conditions and the precision consistently outperforms the state-of-the-art two-dimensional Gaussian fit method. Taking a step further, we have deployed our deep-learning models to a desktop app with a graphical user interface and the app is free and open-source. We have also built a TEM ImageNet project website for easy browsing and downloading of the training data.

25 ENERGY STORAGE↗
DOE OSTI2025

Efficient and assured reinforcement learning-based building HVAC control with heterogeneous expert-guided training

Abstract Building heating, ventilation, and air conditioning (HVAC) systems account for nearly half of building energy consumption and $$20\%$$ of total energy consumption in the US. Their operation is also crucial for ensuring the physical and mental health of building occupants. Compared with traditional model-based HVAC control methods, the recent model-free deep reinforcement learning (DRL) based methods have shown good performance while do not require the development of detailed and costly physical models. However, these model-free DRL approaches often suffer from long training time to reach a good performance, which is a major obstacle for their practical deployment. In this work, we present a systematic approach to accelerate online reinforcement learning for HVAC control by taking full advantage of the knowledge from domain experts in various forms . Specifically, the algorithm stages include learning expert functions from existing abstract physical models and from historical data via offline reinforcement learning, integrating the expert functions with rule-based guidelines, conducting training guided by the integrated expert function and performing policy initialization from distilled expert function. Moreover, to ensure that the learned DRL-based HVAC controller can effectively keep room temperature within the comfortable range for occupants, we design a runtime shielding framework to reduce the temperature violation rate and incorporate the learned controller into it. Experimental results demonstrate up to 8.8 X speedup in DRL training from our approach over previous methods, with low temperature violation rate.

Xu, Shichao↗