Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep 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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Hybrid deep learning architecture for general disruption prediction across tokamaks

In this paper, we present a new deep learning disruption prediction algorithm based on important findings from explorative data analysis which effectively allows knowledge transfer from existing devices to new ones, thereby predicting disruptions using very limited disruptive data from the new devices. The explorative data analysis conducted via unsupervised clustering techniques confirms that time-sequence data are much better separators of disruptive and non-disruptive behavior than the instantaneous plasma state data with further advantageous implications for a sequence-based predictor. Based on such important findings, we have designed a new algorithm for multi-machine disruption prediction that achieves high predictive accuracy on the C-Mod (AUC=0.801), DIII-D (AUC=0.947) and EAST (AUC=0.973). tokamaks with limited hyperparameter tuning. Through numerical experiments, we show that boosted accuracy (AUC=0.959) is achieved on EAST predictions by including in the training only 20 disruptive discharges, thousands of non-disruptive discharges from EAST, and combining this with more than a thousand discharges from DIII-D and C-Mod. The improvement of predictive ability obtained by combining disruptive data from other devices is found to be true for all permutations of the three devices. Furthermore, by comparing the predictive performance of each individual numerical experiment, we find that non-disruptive data are machine-specific while disruptive data from multiple devices contain device-independent knowledge that can be used to inform predictions for disruptions occurring on a new device.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2020

Shedding Light on Microbial Dark Matter with A Universal Language of Life

The majority of microbial genomes have yet to be cultured, and most proteins predicted from microbial genomes or sequenced from the environment cannot be functionally annotated. As a result, current computational approaches to describe microbial systems rely on incomplete reference databases that cannot adequately capture the full functional diversity of the microbial tree of life, limiting our ability to model high-level features of biological sequences. The scientific community needs a means to capture the functionally and evolutionarily relevant features underlying biology, independent of our incomplete reference databases. Such a model can form the basis for transfer learning tasks, enabling downstream applications in environmental microbiology, medicine, and bioengineering. Here we present LookingGlass, a deep learning model capturing a “universal language of life”. LookingGlass encodes contextually-aware, functionally and evolutionarily relevant representations of short DNA reads, distinguishing reads of disparate function, homology, and environmental origin. We demonstrate the ability of LookingGlass to be fine-tuned to perform a range of diverse tasks: to identify novel oxidoreductases, to predict enzyme optimal temperature, and to recognize the reading frames of DNA sequence fragments. LookingGlass is the first contextually-aware, general purpose pre-trained “biological language” representation model for short-read DNA sequences. LookingGlass enables functionally relevant representations of otherwise unknown and unannotated sequences, shedding light on the microbial dark matter that dominates life on Earth.

A Hoarfrost↗
DOE OSTI2025

Deep Learning Approaches for Predicting the Surface Tension of Ionic Liquids

Ionic liquids (ILs) are a novel class of solvents that have attracted significant attention due to their unique and tunable properties. Among their physiochemical characteristics, surface tension plays a critical role in various industrial applications including electrolytes, heat transfer fluids, and separation processes. However, because of the exploratory nature of IL design and the vast combinatorial space of possible anion–cation pairs, the experimental determination of these properties is often impractical, being both time-consuming and costly. To overcome these challenges, computational approaches are increasingly employed to develop accurate predictive models that can accelerate IL discovery and design. In this study, we present two deep learning (DL) models for predicting the surface tension of ILs across a broad temperature range at a constant pressure. The models use simplified molecular input line entry system, SMILES, representations of ILs to extract molecular features as inputs. Both DL models demonstrate excellent agreement with experimental data, achieving an R 2 value of 0.990 and a root-mean-square error of 0.792 mN/m. In conclusion, these results offer valuable insights for the rapid screening and rational design of ILs with tailored surface tension values.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients

Nuclear reactor safety and efficiency can be enhanced through the development of accurate and fast methods for prediction of reactor transient (RT) states. Physics informed neural networks (PINNs) leverage deep learning methods to provide an alternative approach to RT modeling. Applications of PINNs in monitoring of RTs for operator support requires near real-time model performance. However, as with all machine learning models, development of a PINN involves time-consuming model training. Here, we show that a transfer learning (TL-PINN) approach achieves significant performance gain, as measured by reduction of the number of iterations for model training. Using point kinetic equations (PKEs) model with six neutron precursor groups, constructed with experimental parameters of the Purdue University Reactor One (PUR-1) research reactor, we generated different RTs with experimentally relevant range of variables. The RTs were characterized using Hausdorff and Fréchet distance. We have demonstrated that pre-training TL-PINN on one RT results in up to two orders of magnitude acceleration in prediction of a different RT. The mean error for conventional PINN and TL-PINN models prediction of neutron densities is smaller than 1%. We have developed a correlation between TL-PINN performance acceleration and similarity measure of RTs, which can be used as a guide for application of TL-PINNs.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Identifying common stored product insects using automated deep learning methods

Monitoring stored product insect pests is a common practice for post-harvest management of stored grain and grain-based commodities, which helps ensure product quality from harvest to final consumer. Current methods of sampling and monitoring can be time-consuming, labor-intensive, expensive and require expertise in insect identification. Therefore, this study aims to develop an image-based automated identification system for common stored product insect species using deep-learning methods. Top-down images of the common stored product adult insect species of Rhyzopertha dominica, Cryptolestes ferrugineus, Tribolium castaneum, Sitophilus oryzae, and Oryzaephilus surinamensis were acquired and analyzed. Deep learning-based, state-of-the-art Convolutional Neural Networks (CNN) models (ResNet-50, MobileNet-v2, DarkNet-53, and EfficientNet-b0) were fine-tuned with a transfer learning approach to classify the insect species. All models were able to correctly identify the insect species with at least 96% accuracy and with few misclassifications. One issue with trained CNNs is that they do not explain the reasoning for the classification and are often called a “black box”. Therefore, visualization methods called Gradient-weighted Class Activation Mapping (Grad-CAM) were implemented to explore the black box network. The Grad-CAM uses heat maps to highlight the major image features that the network focused on to make insect species predictions. The Grad-CAM verifies the network's prediction and also helps improve network performance. This study contributes to the overall goal of developing a camera-based system for monitoring stored grain insects. As a result, the developed system would empower warehouse, flour mills, and other food facilities with a tool to quickly and accurately identify insect species in stored product environments and could be implemented as part of a close to real-time monitoring system.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Super-resolution and segmentation deep learning for breast cancer histopathology image analysis

Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminator networks so-called super-resolution generative adversarial network-based on aggregated residual transformation (SRGAN-ResNeXt) to facilitate cancer diagnosis in low resource settings. The results provide high enhancement in image quality where the peak signal-to-noise ratio and structural similarity of our network results are over 30 dB and 0.93, respectively. The derived performance is superior to the results obtained from both the bicubic interpolation and the well-known SRGAN deep-learning methods. In addition, another custom CNN is used to perform image segmentation from the generated high-resolution breast cancer images derived with our model with an average Intersection over Union of 0.869 and an average dice similarity coefficient of 0.893 for the H&E image segmentation results. Finally, we propose the jointly trained SRGAN-ResNeXt and Inception U-net Models, which applied the weights from the individually trained SRGAN-ResNeXt and inception U-net models as the pre-trained weights for transfer learning. The jointly trained model’s results are progressively improved and promising. We anticipate these custom CNNs can help resolve the inaccessibility of advanced microscopes or whole slide imaging (WSI) systems to acquire high-resolution images from low-performance microscopes located in remote-constraint settings.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom Probe Tomography (APT) is a powerful technique for visualizing the atomic-scale distribution of solutes in materials, but quantitative cluster analysis of APT datasets remains a challenge due to the need for subjective parameter selection in clustering algorithms. While distance-based and density-based methods such as HDBSCAN are widely used, their performance is highly sensitive to user-defined parameters, which undermines reproducibility and accuracy. This study proposes an image-based, deep learning-aided workflow for automating parameter selection and cluster detection in APT data analysis. By projecting 3D APT point clouds onto 2D planes, we leverage pretrained convolutional neural networks (ConvNeXt-Tiny and ResNet-50) through transfer learning to predict the number of clusters present in synthetic datasets. The output is used to guide K-means clustering and estimate HDBSCAN parameters, specifically minimum cluster size and minimum sample points. This approach reduces reliance on manual parameter tuning, improving consistency and scalability. The methodology demonstrates the feasibility of using image-based deep learning for interpreting complex spatial patterns in APT data, enabling faster and more objective analysis. The complete workflow and code are made publicly available to support reproducibility and future research.

Density-based clustering↗
DOE OSTI2022

Deep structural clustering for single-cell RNA-seq data jointly through autoencoder and graph neural network

Abstract Single-cell RNA sequencing (scRNA-seq) permits researchers to study the complex mechanisms of cell heterogeneity and diversity. Unsupervised clustering is of central importance for the analysis of the scRNA-seq data, as it can be used to identify putative cell types. However, due to noise impacts, high dimensionality and pervasive dropout events, clustering analysis of scRNA-seq data remains a computational challenge. Here, we propose a new deep structural clustering method for scRNA-seq data, named scDSC, which integrate the structural information into deep clustering of single cells. The proposed scDSC consists of a Zero-Inflated Negative Binomial (ZINB) model-based autoencoder, a graph neural network (GNN) module and a mutual-supervised module. To learn the data representation from the sparse and zero-inflated scRNA-seq data, we add a ZINB model to the basic autoencoder. The GNN module is introduced to capture the structural information among cells. By joining the ZINB-based autoencoder with the GNN module, the model transfers the data representation learned by autoencoder to the corresponding GNN layer. Furthermore, we adopt a mutual supervised strategy to unify these two different deep neural architectures and to guide the clustering task. Extensive experimental results on six real scRNA-seq datasets demonstrate that scDSC outperforms state-of-the-art methods in terms of clustering accuracy and scalability. Our method scDSC is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/scDSC.

Gan, Yanglan↗
DOE OSTI2021

Detecting operons in bacterial genomes via visual representation learning

Contiguous genes in prokaryotes are often arranged into operons. Detecting operons plays a critical role in inferring gene functionality and regulatory networks. Human experts annotate operons by visually inspecting gene neighborhoods across pileups of related genomes. These visual representations capture the inter-genic distance, strand direction, gene size, functional relatedness, and gene neighborhood conservation, which are the most prominent operon features mentioned in the literature. By studying these features, an expert can then decide whether a genomic region is part of an operon. We propose a deep learning based method named Operon Hunter that uses visual representations of genomic fragments to make operon predictions. Using transfer learning and data augmentation techniques facilitates leveraging the powerful neural networks trained on image datasets by re-training them on a more limited dataset of extensively validated operons. Our method outperforms the previously reported state-of-the-art tools, especially when it comes to predicting full operons and their boundaries accurately. Furthermore, our approach makes it possible to visually identify the features influencing the network’s decisions to be subsequently cross-checked by human experts.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Flavor Classification in ICARUS Using Convolutional Visual Networks

In this work, we adapt the Convolutional Visual Network (CVN) approach [1] to the ICARUS detector by incorporating TPC stitching methods inspired by NuGraph[8]. The stitching technique used here is unique to ICARUS, designed specifically to handle its distinct detector segmentations. We then retrain the network using ICARUS-specific data. This study underscores the flexibility of deep learning models in high-energy physics and the importance of accounting for detector-specific features when transferring machine learning techniques between experiments. This poster presents the methods, classification performance, and insights gained from applying CVN to ICARUS data.

Wieler, Felipe [Tech. Fed. Parana U.]↗
NASA NTRS2000

Probing Below the Surface of Mars

In this activity, students will record and graph temperature data to learn about NASA's Mars Microprobe Mission, Deep Space 2, and how the properties of a material affect the transfer of heat.

Deep Space 2 Mars Microprobes classroom experiment↗
DOE OSTI2026

Neutrino Flavor Classification in ICARUS Experiment Using Convolutional Visual Networks

In this work, I adapt the Convolutional Visual Network (CVN) approach to the ICARUS detector by incorporating TPC stitching methods inspired by NuGraph. The stitching technique used here is unique to ICARUS, designed specifically to handle its distinct detector segmentation s. I then retrain the network using ICARUS-specific data. This study underscores the flexibility of deep learning models in high-energy physics and the importance of accounting for detector-specific features when transferring machine learning techniques between experiments. This dissertation presents the methods, classification performance, and insights gained from applying CVN to ICARUS data.

Wieler, Felipe Andre [Parana Tech. Fed. U., Toledo↗
DOE OSTI2022

Automated defect identification in electroluminescence images of solar modules

Solar photovoltaic (PV) modules are susceptible to manufacturing defects, mishandling problems or extreme weather events that can limit energy production or cause early device failure. Trained professionals use electroluminescence (EL) images to identify defects in modules, however, field surveys or inline image acquisition can generate millions of EL images, which are infeasible to analyze by rote inspection. Here, we develop a rapid automatic computer vision pipeline (~0.5 seconds/module) to analyze EL images and identify defects including cracks, intra-cell defects, oxygen-induced defects, and solder disconnections. Defect identification is achieved with a machine learning model (Random Forest, ResNet models and YOLO) trained on 762 manually-labeled EL images of PV modules. We compare model performance on an imbalanced real-world validation set containing 134 EL images and determine that ResNet18 and YOLO are the optimal models; we next evaluated these models on a dedicated testing set (129 module images) with resulting macro F1 scores of 0.83 (ResNet18) and 0.78 (YOLO). Using a field EL survey of a PV power plant damaged in a vegetation fire, we analyze 18,954 EL images (2.4 million cells) and inspect the spatial distribution of defects on the solar modules. The results find increased frequency of ‘crack’, ‘solder’ and ‘intra-cell’ defects on the edges of the solar module closest to the ground after fire. We also find an abnormal increase of striation rings on cells which were assumed to be caused mainly in fabrication process. Our methods are published as open-source software. It can also be used to identify other kinds of defects or process different types of solar cells with minor modification on models by transfer learning.

14 SOLAR ENERGY↗
DOE OSTI2023

Using a physics-informed neural network and fault zone acoustic monitoring to predict lab earthquakes

Abstract Predicting failure in solids has broad applications including earthquake prediction which remains an unattainable goal. However, recent machine learning work shows that laboratory earthquakes can be predicted using micro-failure events and temporal evolution of fault zone elastic properties. Remarkably, these results come from purely data-driven models trained with large datasets. Such data are equivalent to centuries of fault motion rendering application to tectonic faulting unclear. In addition, the underlying physics of such predictions is poorly understood. Here, we address scalability using a novel Physics-Informed Neural Network (PINN). Our model encodes fault physics in the deep learning loss function using time-lapse ultrasonic data. PINN models outperform data-driven models and significantly improve transfer learning for small training datasets and conditions outside those used in training. Our work suggests that PINN offers a promising path for machine learning-based failure prediction and, ultimately for improving our understanding of earthquake physics and prediction.

42 ENGINEERING↗
DOE OSTI2021

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗
DOE OSTI2025

Deep learning-based spatio-temporal fusion for high-fidelity ultra-high-speed X-ray radiography

Full-field ultra-high-speed (UHS) X-ray imaging experiments have been well established to characterize various processes and phenomena. However, the potential of UHS experiments through the joint acquisition of X-ray videos with distinct configurations has not been fully exploited. In this paper, we investigate the use of a deep learning-based spatio-temporal fusion (STF) framework to fuse two complementary sequences of X-ray images and reconstruct the target image sequence with high spatial resolution, high frame rate and high fidelity. We applied a transfer learning strategy to train the model and compared the peak signal-to-noise ratio (PSNR), average absolute difference (AAD) and structural similarity (SSIM) of the proposed framework on two independent X-ray data sets with those obtained from a baseline deep learning model, a Bayesian fusion framework and the bicubic interpolation method. The proposed framework outperformed the other methods with various configurations of the input frame separations and image noise levels. With three subsequent images from the low-resolution (LR) sequence of a four times lower spatial resolution and another two images from the high-resolution (HR) sequence of a 20 times lower frame rate, the proposed approach achieved average PSNRs of 37.57 dB and 35.15 dB, respectively. When coupled with the appropriate combination of high-speed cameras, the proposed approach will enhance the performance and therefore the scientific value of UHS X-ray imaging experiments.

deep learning↗
DOE OSTI2025

Explainable artificial intelligence relates perovskite luminescence images to current-voltage metrics

As the demand for low-cost, high-efficiency solar energy technologies grows, metal halide perovskite (MHP) solar cells have emerged as a promising candidate for next-generation photovoltaics due to their high power conversion efficiencies. However, their poor durability and issues with manufacturing consistency remain significant barriers to commercialization. In this work, we develop deep learning models to support materials characterization and provide insight into features and processes influencing performance. The models are trained using transfer learning of a pretrained model to predict relevant current-voltage (IV) metrics based on different combinations of input electroluminescence (EL) and photoluminescence (PL) images of MHP devices. We examine which image types are most informative in accurately predicting different IV metrics. Additionally, we use explainable artificial intelligence (XAI) techniques to provide insights into specific spatial features in the devices that drive differences in performance. We find that stabilized luminescence images (e.g. those collected after biasing the devices for at least 1 min) are better for predicting metrics of open-circuit voltage (by PL) and short-circuit current (by PL with EL), but that predicting fill factor and overall power output may use the time-evolution of EL images. Based on attribution masks generated by integrated gradients for each device performance metric, we further suggest different loss mechanisms associated with categories of large and small spatial defects. Overall, this case study highlights the potential applicability of XAI methodology for streamlining MHP device analysis and accelerating detailed understanding of the relationships between spatial defects and impacts on performance.

14 SOLAR ENERGY↗
DOE OSTI2022

SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.

97 MATHEMATICS AND COMPUTING↗