Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “transfer learning.”

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

Neural-network quantum states for ultra-cold Fermi gases

Abstract Ultra-cold Fermi gases exhibit a rich array of quantum mechanical properties, including the transition from a fermionic superfluid Bardeen-Cooper-Schrieffer (BCS) state to a bosonic superfluid Bose-Einstein condensate (BEC). While these properties can be precisely probed experimentally, accurately describing them poses significant theoretical challenges due to strong pairing correlations and the non-perturbative nature of particle interactions. In this work, we introduce a Pfaffian-Jastrow neural-network quantum state featuring a message-passing architecture to efficiently capture pairing and backflow correlations. We benchmark our approach on existing Slater-Jastrow frameworks and state-of-the-art diffusion Monte Carlo methods, demonstrating a performance advantage and the scalability of our scheme. We show that transfer learning stabilizes the training process in the presence of strong, short-ranged interactions, and allows for an effective exploration of the BCS-BEC crossover region. Our findings highlight the potential of neural-network quantum states as a promising strategy for investigating ultra-cold Fermi gases.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Enhancing high-fidelity neural network potentials through low-fidelity sampling

The efficacy of neural network potentials (NNPs) critically depends on the quality of the configurational datasets used for training. Prior research using empirical potentials has shown that well-selected liquid–solid transitional configurations of a metallic system can be translated to other metallic systems. This study demonstrates that such validated configurations can be relabeled using density functional theory (DFT) calculations, thereby enhancing the development of high-fidelity NNPs. Training strategies and sampling approaches are efficiently assessed using empirical potentials and subsequently relabeled via DFT in a highly parallelized fashion for high-fidelity NNP training. Our results reveal that relying solely on energy and force for NNP training is inadequate to prevent overfitting, highlighting the necessity of incorporating stress terms into the loss functions. To optimize training involving force and stress terms, we propose employing transfer learning to fine-tune the weights, ensuring that the potential surface is smooth for these quantities composed of energy derivatives. This approach markedly improves the accuracy of elastic constants derived from simulations in both empirical potential-based NNPs and relabeled DFT-based NNPs. Overall, this study offers significant insights into leveraging empirical potentials to expedite the development of reliable and robust NNPs at the DFT level.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Sound propagation in realistic interactive 3D scenes with parameterized sources using deep neural operators

We address the challenge of acoustic simulations in three-dimensional (3D) virtual rooms with parametric source positions, which have applications in virtual/augmented reality, game audio, and spatial computing. The wave equation can fully describe wave phenomena such as diffraction and interference. However, conventional numerical discretization methods are computationally expensive when simulating hundreds of source and receiver positions, making simulations with parametric source positions impractical. To overcome this limitation, we propose using deep operator networks to approximate linear wave-equation operators. This enables the rapid prediction of sound propagation in realistic 3D acoustic scenes with parametric source positions, achieving millisecond-scale computations. By learning a compact surrogate model, we avoid the offline calculation and storage of impulse responses for all relevant source/listener pairs. Our experiments, including various complex scene geometries, show good agreement with reference solutions, with root mean squared errors ranging from 0.02 to 0.10 Pa. Notably, our method signifies a paradigm shift as—to our knowledge—no prior machine learning approach has achieved precise predictions of complete wave fields within realistic domains.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function

Abstract Motivation Millions of protein sequences have been generated by numerous genome and transcriptome sequencing projects. However, experimentally determining the function of the proteins is still a time consuming, low-throughput, and expensive process, leading to a large protein sequence-function gap. Therefore, it is important to develop computational methods to accurately predict protein function to fill the gap. Even though many methods have been developed to use protein sequences as input to predict function, much fewer methods leverage protein structures in protein function prediction because there was lack of accurate protein structures for most proteins until recently. Results We developed TransFun—a method using a transformer-based protein language model and 3D-equivariant graph neural networks to distill information from both protein sequences and structures to predict protein function. It extracts feature embeddings from protein sequences using a pre-trained protein language model (ESM) via transfer learning and combines them with 3D structures of proteins predicted by AlphaFold2 through equivariant graph neural networks. Benchmarked on the CAFA3 test dataset and a new test dataset, TransFun outperforms several state-of-the-art methods, indicating that the language model and 3D-equivariant graph neural networks are effective methods to leverage protein sequences and structures to improve protein function prediction. Combining TransFun predictions and sequence similarity-based predictions can further increase prediction accuracy. Availability and implementation The source code of TransFun is available at https://github.com/jianlin-cheng/TransFun.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

LSBGnet: an improved detection model for low-surface brightness galaxies

ABSTRACT The Chinese Space Station Telescope (CSST) is scheduled to launch soon, which is expected to provide a vast amount of image potentially containing low-surface brightness galaxies (LSBGs). However, detecting and characterizing LSBGs is known to be challenging due to their faint surface brightness, posing a significant hurdle for traditional detection methods. In this paper, we propose LSBGnet, a deep neural network specifically designed for automatic detection of LSBGs. We established LSBGnet-SDSS model using data set from the Sloan Digital Sky Survey (SDSS). The results demonstrate a significant improvement compared to our previous work, achieving a recall of 97.22 per cent and a precision of 97.27 per cent on the SDSS test set. Furthermore, we use the LSBGnet-SDSS model as a pre-training model, employing transfer learning to retrain the model with LSBGs from Dark Energy Survey (DES), and establish the LSBGnet-DES model. Remarkably, after retraining the model on a small DES sample, it achieves over 90 per cent precision and recall. To validate the model’s capabilities, we utilize the trained LSBGnet-DES model to detect LSBG candidates within a selected 5 sq. deg area in the DES footprint. Our analysis reveals the detection of 204 LSBG candidates, characterized by a mean surface brightness range of $23.5\ \mathrm{ mag}\ \mathrm{ arcsec}^{-2}\le \bar{\mu }_{\text{eff}}(g)\le 26.8\ \mathrm{ mag}\ \mathrm{ arcsec}^{-2}$ and a half-light radius range of 1.4 arcsec ≤ r1/2 ≤ 8.3 arcsec. Notably, 116 LSBG candidates exhibit a half-light radius ≥2.5 arcsec. These results affirm the remarkable performance of our model in detecting LSBGs, making it a promising tool for the upcoming CSST.

Su, Hao (ORCID:0009000778888301)↗
DOE OSTI2023

1-D Convolutional Graph Convolutional Networks for Fault Detection in Distributed Energy Systems

This paper presents a 1-D convolutional and graph convolutional networks for fault detection in microgrids. The combination of 1-D convolutional neural networks (1D-CNN) and graph convolutional networks (GCN) helps extract both spatial-temporal correlations from the voltage measurements in microgrids. The fault detection scheme includes fault event detection, fault type and phase classification, and fault location. There are five neural network model training to handle these tasks. Transfer learning and fine-tuning are applied to reduce training efforts. The combined 1-D convolutional and graph convolutional networks (1D-CGCN) is compared with the traditional ANN structure on the Potsdam 13-bus microgrid dataset. The accuracy of 99.5%, 98.4%, 99.2%, and 95.5% are achieved in fault event detection, fault type classification, fault phase identification, and fault location respectively. The detailed confusion matrices of fault type and fault phase classification are provided for validation.

deep neural network↗
DOE OSTI2022

pnnl/TransMED

Transfer Learning From Existing Diseases Via Hierarchical Multi-Modal BERT Models

Ham, Colby↗
DOE OSTI2025

Hiperclust

This software leverages transfer learning to analyze atom probe tomography (APT) data. It is trained on synthetic data and then applies this knowledge to predict the optimal number of clusters for a given APT dataset. Initially, the software used preliminary clustering to estimate the general structure of the data. Based on this, it provides suggestions for key parameters like minimum cluster size and minimum number of points. These parameters are critical for algorithms like HDBSCAN, ensuring accurate cluster formation without the need for trial-and-error testing. The software runs on High-Performance computing (HPC) systems, enabling fast, scalable analysis of large APT datasets, ultimately saving time and improving the reliability of clustering outcomes.

Tang, Yalei [Idaho National Laboratory (INL), Idah↗
DOE OSTI2022

Scalable Predictive And Risk Technologies

The research involves developing scalable technologies for risk-informed predictive analytics to achieve condition-based monitoring and maintenance strategies to reduce overall maintenance costs. The research utilizes data (real-time data, periodic data, and institutional knowledge) related to a particular plant asset from a specific nuclear plant site to develop technologies to scale risk-informed predictive analytic algorithms across different plant assets at the plant site and across the nuclear fleet. The developed algorithms and codes are used to optimize the maintenance strategy and estimate/forecast generation costs based on the state of health of the plant asset. Developed codes specifically include 1. Parameter estimation using plant operation data 2. Federated and Transfer learning model 3. Feature group based Multi-kernel SVM 4. Three state markov model

Manjunatha, KoushikAraseethota↗
DOE OSTI2026

HydraGNN_GFM_FineTuning4Materials v1.0

This repository enables fine-tuning of the HydraGNN Predictive GFM 2026 — an open-source ensemble of pre-trained graph foundation models for atomistic materials modeling, developed at Oak Ridge National Laboratory. The GFM 2026 is freely available and downloadable via Globus from the OLCF Data Constellation (DOI: 10.13139/OLCF/2562660). Starting from these pre-trained weights, this repository provides a complete transfer learning pipeline for adapting the GFM ensemble to domain-specific molecular and materials property prediction tasks. It includes: 1) Utilities for ensemble fine-tuning with task-specific output heads 2) Example pipelines for eight widely-used materials and molecular datasets 3) Tools for model adaptation and head configuration 4) Data preprocessing utilities for each supported dataset 5) Benchmarking and evaluation scripts

Ungerboeck, Linda↗
DOE OSTI2023

Assessing Tropical Pacific-induced Predictability of Southern California Precipitation Using a Novel Multi-input Multi-output Autoencoder

We construct a novel Multi-Input Multi-Output Autoencoder-decoder (MIMO-AE) to capture the non-linear relationship of Southern California precipitation and tropical Pacific Ocean sea surface temperature. The MIMO-AE is trained on both monthly TP-SST and SC-PRECIP anomalies simultaneously. The co-variability of the two fields in the MIMO-AE shared nonlinear latent space can be condensed into an index, termed the MIMO-AE index. We use a transfer learning approach to train a MIMO-AE on the combined dataset of 100 years of output from a historical simulation with the Energy Exascale Earth Systems Model version 1 and a segment of observational data. We further use Long Short-Term Memory networks to assess sub-seasonal predictability of SC-PRECIP using the MIMO-AE index. We find that the MIMO-AE index provides enhanced predictability of SC-PRECIP for a lead-time of up-to four months as compared to Niño 3.4 index and the El Niño Southern Oscillation Longitudinal Index.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Classification of Cloud Particle Imagery from Aircraft Platforms Using Convolutional Neural Networks

Abstract A vast amount of ice crystal imagery exists from a variety of field campaign initiatives that can be utilized for cloud microphysical research. Here, nine convolutional neural networks are used to classify particles into nine regimes on over 10 million images from the Cloud Particle Imager probe, including liquid and frozen states and particles with evidence of riming. A transfer learning approach proves that the Visual Geometry Group (VGG-16) network best classifies imagery with respect to multiple performance metrics. Classification accuracies on a validation dataset reach 97% and surpass traditional automated classification. Furthermore, after initial model training and preprocessing, 10 000 images can be classified in approximately 35 s using 20 central processing unit cores and two graphics processing units, which reaches real-time classification capabilities. Statistical analysis of the classified images indicates that a large portion (57%) of the dataset is unusable, meaning the images are too blurry or represent indistinguishable small fragments. In addition, 19% of the dataset is classified as liquid drops. After removal of fragments, blurry images, and cloud drops, 38% of the remaining ice particles are largely intersecting the image border (≥10% cutoff) and therefore are considered unusable because of the inability to properly classify and dimensionalize. After this filtering, an unprecedented database of 1 560 364 images across all campaigns is available for parameter extraction and bulk statistics on specific particle types in a wide variety of storm systems, which can act to improve the current state of microphysical parameterizations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

AutoFocus: AI/ML-driven real-time wavefront diagnostics to autonomously align and optimize X-ray optics

We present an integrated system that combines advanced wavefront diagnostics with artificial intelligence (AI) to automate and optimize X-ray optics at synchrotron beamlines. This system couples real-time wavefront sensing with AI-driven control algorithms to achieve precise beam alignment, stabilization, and performance optimization. A key feature is the use of multi-fidelity transfer learning, which enables knowledge gained from both real-world beamline optimizations and ultra-realistic digital twin simulations to be effectively applied to in situ optimization. By leveraging multi-objective bayesian optimization, the system continuously refines its performance, reducing optimization time and minimizing the need for manual adjustments. Designed for seamless deployment, it operates with existing beamline hardware and provides an intuitive graphical interface. Initial deployments at the advanced photon source beamlines have demonstrated its ability to enhance beam stability, improve reproducibility, and significantly streamline alignment procedures. This AI-enhanced control framework represents a significant step toward fully autonomous beamline operation in next-generation synchrotron facilities.

Rebuffi, Luca [Argonne National Laboratory (ANL), ↗
DOE OSTI2020

Analysis and Planning Framework for Nuclear Plant Transformation

Commercial nuclear power in the United States has been an unqualified success by any measure, providing low cost, carbon-free, and safe baseload electricity for decades. The industry today is at the peak of its historical performance in terms of generation output, reliable operations, and demonstrated nuclear safety. However, it is no longer among the lowest-cost electric generation sources with the emergence of subsidized renewables and shale gas generation. The business model that has served the operating nuclear fleet so well over its life is now a drag on cost performance due to its reliance on a large highly skilled labor force. In contrast, digital technology and innovation are enabling dramatic efficiencies in energy production, resulting in fierce competition for a commodity such as electricity. The nuclear power industry has responded to this challenge with many initiatives to improve efficiency and modernize plant equipment, especially where reliability and obsolescence issues are pressing. However, it would be a missed opportunity to merely modernize the plant components and the work processes of an outdated business model that was formulated to manage the technology of the 1960s. Rather, the greater opportunity is to transform that business model to one that fully exploits the capabilities of modern digital technology, resulting in substantially lower production costs and sustainable market viability. One successful example of such transformation is the concept of Integrated Operations, which was introduced into the North Sea oil and gas industry a couple of decades ago when the profitability of operating these fields was severely threatened by low world petroleum prices and the high overhead of operating the offshore oil and gas platforms. This effort resulted in significant changes to how these oil fields were operated and allowed the industry to continue profitable operation of these platforms. This example has some remarkable parallels to the U.S. commercial nuclear industry as described in the next section. This report provides an analysis and planning framework for such a nuclear plant operating model transformation based on the transferable learnings from the North Sea transformation. This framework is termed Integrated Operations for Nuclear or ION. This report describes the key principles and methods of Integrated Operations and how they are being applied in a collaboration between the DOE Light Water Reactor Sustainability Program and Xcel Energy in an initiative to transform its operating model for performance improvement and long-term sustainability. It describes a method to bring the operating costs of a nuclear fleet in line with market-based pricing, transforming work functions to reduce cost with technology innovations. This initiative will continue over the next several years in the detailed development of transformative concepts for nuclear plants, which will be published as follow-up to this initial report on Integrated Operations for Nuclear.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2021

Bridging Power System Protection Gaps with Data-driven Approaches

Protection is a critical function in power systems to avoid equipment damage, maintain personnel safety, and support system reliability. However, current protective relay technology cannot adequately protect equipment and personnel from effects of some events; these deficiencies are termed protection gaps. In this research, a data-driven approach is proposed to complement traditional protection technology and distinguish fault conditions from transients caused by normal operations. A convolutional neural network (CNN) based fault detection approach is implemented to achieve data translation invariance of the time-series input data. As a result, the data-driven method can accurately detect system faults despite variation and noise in the input data. In addition, using the CNN–based method avoids the complicated manual feature extraction procedure required by many traditional data-driven methods. The effectiveness of the proposed approach is tested on four kinds of protection gaps: high impedance faults, transformer/generator inter-turn faults, distribution system PV circuit faults, and the mis-operation situations of Zone 3 line protection relays operating under system stress. Finally, a transfer learning method is also proposed to address the common issue of data-driven methods for which real-world training data are scarce. Extensive study results demonstrate that the proposed approach can accurately bridge power system protection gaps.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Report on the Use and Function of the Integrated Operations Capability Analysis Platform (ICAP) and the LWRS Innovation Portal (IP)

The commercial nuclear power industry has achieved excellent safety and reliability performance but is struggling to survive in an electricity market that is increasingly dominated by subsidized renewables and cheap natural gas. These challenges have forced utilities to explore previously uncharted avenues to drastically reduce the operations and maintenance costs of their plants which are the primary drivers of the total cost to produce electricity. The petrochemical industry faced similar challenges some years ago as the costs of extraction and processing were rising while their reservoirs were being depleted along with a drop-in commodity prices that resulted in unsustainable operations. In this challenging climate, they developed a business model called Integrated Operations (IO) that sought to utilize technology to enable news ways of working through the integration of people, technology, process and governance changes. The Light Water Reactor Sustainability (LWRS) program, working with IFE have developed an operating model via transferable learnings from the North Sea O&G industry. This framework is termed “Integrated Operations for Nuclear” (ION). ION is a transformation model that integrates the benefits and features of four principal factors: People, Technology, Process and Governance. The purpose of this report is to describe how to generate an ION business process analysis and utilize this information to reduce O&M costs. In order to make this job easier, DOE LWRS has created a suite of tools that will allow a person who is involved in a transformation effort at their company to build a solid documented business case for embarking on a major transformation effort. These tools, the Integrated Operations Capability Analysis Model (ICAP) and the LWRS Innovation Portal (IP) are described herein with instructions on their use. Instructions on how the interface with the EPRI Business Case Analysis Method (BCAM) are also provided.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

Feasibility of Using Fourier Neural Operators for 3D Elastic Seismic Simulations

Seismic simulations in three-dimensional (3D) Earth models are important in many of the seismological applications related to our lab’s mission, however, accurate high-fidelity simulations are computationally costly. We investigated the capabilities of the newly developed Fourier Neural Operator (FNO) to solve the 3D elastic wave equations for seismic simulations. We generated simulation data for training the FNO model, and analyzed its performance on various test cases, such as the performance with different number of training data, different resolutions, and on more canonical structures. We found the FNO model can reproduce 3D seismic simulations with high accuracy and ~169 times faster on a small spatial grid size of 16 x 16 x16. When applied on higher resolution data, we found that transfer learning with fine-tuning on a small amount of data achieves reasonable results. This feasibility study showed promising results for using FNO’s for 3D seismic simulations and represents the foundation of further research to develop this into a more mature approach for different seismological applications. The potential impact of this project will provide techniques for large-scale or real-time applications of solving PEDs in support of national lab’s programs.

58 GEOSCIENCES↗