SEARCH · Engineering Papers
Results for “Transfer Learning Model”
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.
TRANSFER LEARNING FOR FIELD EMISSION MITIGATION IN CEBAF SRF CAVITIES
The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab operates hundreds of super-conducting radio frequency (SRF) cavities in its two linear accelerators (linacs). Field emission (FE) is an ongoing operational challenge in higher gradient SRF cavities. FE generates high levels of neutron and gamma radiation leading to damaged accelerator hardware and a radiation hazard environment. During machine development periods, we performed gradient scans to record data capturing the relationship between cavity gradients and radiation levels measured throughout the linacs. However, the field emission environment at CEBAF varies considerably over time as the configuration of the radio frequency (RF) gradients changes and due to the changing behaviour of field emitters. An artificial intelligence/machine learning (AI/ML) approach with transfer learning could be a valuable tool to mitigate FE and lower the radiation levels. In this work, we mainly focus on leveraging the RF trip data gathered during CEBAF operations. We develop a transfer learning-based surrogate model for radiation detector readings given RF cavity gradients to track the CEBAF?s changing configuration and environment. Then, we could use the developed model as an optimization process for redistributing the RF gradients within a linac to minimize radiation levels.
TRANSFER LEARNING FOR FIELD EMISSION MITIGATION IN CEBAF SRF CAVITIES
The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab operates hundreds of super-conducting radio frequency (SRF) cavities in its two linear accelerators (linacs). Field emission (FE) is an ongoing operational challenge in higher gradient SRF cavities. FE generates high levels of neutron and gamma radiation leading to damaged accelerator hardware and a radiation hazard environment. During machine development periods, we performed gradient scans to record data capturing the relationship between cavity gradients and radiation levels measured throughout the linacs. However, the field emission environment at CEBAF varies considerably over time as the configuration of the radio frequency (RF) gradients changes and due to the changing behaviour of field emitters. An artificial intelligence/machine learning (AI/ML) approach with transfer learning could be a valuable tool to mitigate FE and lower the radiation levels. In this work, we mainly focus on leveraging the RF trip data gathered during CEBAF operations. We develop a transfer learning-based surrogate model for radiation detector readings given RF cavity gradients to track the CEBAF?s changing configuration and environment. Then, we could use the developed model as an optimization process for redistributing the RF gradients within a linac to minimize radiation levels.
First Impressions: Early-time Classification of Supernovae Using Host-galaxy Information and Shallow Learning
Substantial effort has been devoted to the characterization of transient phenomena from photometric information. Automated approaches to this problem have taken advantage of complete phase coverage of an event, limiting their use for triggering rapid follow-up of ongoing phenomena. In this work, we introduce a neural network with a single recurrent layer designed explicitly for early photometric classification of supernovae (SNe). Our algorithm leverages transfer learning to account for model misspecification, host-galaxy photometry to solve the data-scarcity problem soon after discovery, and a custom weighted loss to prioritize accurate early classification. We first train our algorithm using state-of-the-art transient and host-galaxy simulations, then adapt its weights and validate it on the spectroscopically confirmed SNe Ia, SNe II, and SNe Ib/c from the Zwicky Transient Facility Bright Transient Survey. On observed data, our method achieves an overall accuracy of 82% ± 2% within 3 days of an event’s discovery, and an accuracy of 87% ± 5% within 30 days of discovery. At both early and late phases, our method achieves comparable or superior results to the leading classification algorithms with a simpler network architecture. These results help pave the way for rapid photometric and spectroscopic follow-up of scientifically valuable transients discovered in massive synoptic surveys.
VRN3P: Variational Recurrent Neural Network Based Net-Load Prediction under High Solar Penetration
This is the final technical report for the SETO-funded VRN3P project (PNNL# 76914). The goal of this project, led by Pacific Northwest National Laboratory (PNNL), in collaboration with Lawrence Livermore National Laboratory (LLNL) and Portland General Electric (PGE), was to develop and validate a deep variational recurrent neural network-based net-load prediction (VRN3P) framework for probabilistic time-series forecasting of day-ahead net-load under high solar penetration scenarios. The project team reports successful design of a novel probabilistic net-load forecasting architecture, comprising of a variational autoencoder and a recurrent neural network, which demonstrates 30% improvement in forecast performance, 60% improvement in training time, and consumes 44% less memory, when compared with conventional baseline models. The team tested the VRN3P model performance on GridLAB-D test-cases representing varying BTM solar penetration levels of 20%, 30%, and 50%, with integrated time-series net-load profiles provided by the utility partner (PGE). The VRN3P model demonstrate <2% hourly MAPE (averaged over the year) for day- ahead net-load forecast on the test scenario with 20% BTM solar. Transfer learning extension of the VRN3P model has demonstrated 8.33× speed-up in training, while still achieving acceptable forecast performance of 2.24% hourly MAPE on the 30% BTM solar penetration test-scenario. A preliminary version of the VRN3P GridAPPS-D™has been developed, along with a web-based interactive user-interface (named ‘Forte’) which has made available on GitHub for public use.
Deep learning-based predictive models for laser direct drive at the Omega Laser Facility
The rich and complex physics of inertial confinement fusion provides a unique and challenging space for high-fidelity first-principles modeling. Consequently, simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this article, we present two deep-learning-based predictive models intended to address these difficulties. The first model (TL DNN) acts as a fast emulator of simulations as well as experiments at the Omega Laser Facility. This model is trained on a simulation database and subsequently calibrated on experimental data using transfer learning. To facilitate the development of this model, an autoencoder is developed to reduce the dimensionality of the input space by compressing the laser pulse input. The model predicts key experimental scalar observables of Omega experiments with high accuracy and minimal computational cost. This deep neural net enables rapid exploration of a high-dimensional input parameter space for an optimal implosion design. The second model (DNN SM+) aims to extend the statistical modeling work of Lees et al. [Phys. Rev. Lett. 127, 105001 (2021)], by increasing the complexity of the model space and allowing for coupling between degradation terms. Since the model capacity of DNN SM+ is higher than the model of Lees et al., DNN SM+ can potentially provide an improvement in predictive capability, and we use this model to provide insight into complicated degradation dependencies.
A consensus mathematical model of vaccine-induced antibody dynamics for multiple vaccine platforms and pathogens
Introduction: Vaccine platforms used in successful, licensed vaccines have varied among pathogens. However, antibody level is still the main clinical correlate of protection in most approved vaccines. Decisions as to the best vaccine platform to pursue for a given pathogen may be informed through improved understanding of the process of antibody generation and its temporal dynamics, as well as the relationship between these processes and the type of vaccine. Methods: We have analyzed the dynamics of antibody generation for different vaccine platforms against diverse pathogens, and developed a consensus mathematical model that captures antibody dynamics across these diverse systems. Initially, the model was fitted to a rich dataset of antibody and immune cell concentrations in a SARS-CoV-2 vaccine experiment. We then used concepts from machine learning, such as transfer learning, to apply the same model to a variety of systems, involving different pathogens, vaccine platforms, and booster dose use/timing, fixing most parameter values relating to the dynamics of the immune system. Results: The model includes B cell proliferation and differentiation, as well as the generation of plasma cells, which secrete large amounts of antibody, and memory B cells. Overall, the model describes antibody generation in all systems tested well and shows that the main differences across platforms are related to the dynamics of antigen presentation. Discussion: This model can be used to predict antibody generation in pairs of vaccine platform/pathogen, allowing for the use of in silico results to narrow down experimental burden in vaccine development.
SNM Radiation Signature Classification Using Different Semi-Supervised Machine Learning Models
The timely detection of special nuclear material (SNM) transfers between nuclear facilities is an important monitoring objective in nuclear nonproliferation. Persistent monitoring enabled by successful detection and characterization of radiological material movements could greatly enhance the nuclear nonproliferation mission in a range of applications. Supervised machine learning can be used to signal detections when material is present if a model is trained on sufficient volumes of labeled measurements. However, the nuclear monitoring data needed to train robust machine learning models can be costly to label since radiation spectra may require strict scrutiny for characterization. Therefore, this work investigates the application of semi-supervised learning to utilize both labeled and unlabeled data. As a demonstration experiment, radiation measurements from sodium iodide (NaI) detectors are provided by the Multi-Informatics for Nuclear Operating Scenarios (MINOS) venture at Oak Ridge National Laboratory (ORNL) as sample data. Anomalous measurements are identified using a method of statistical hypothesis testing. After background estimation, an energy-dependent spectroscopic analysis is used to characterize an anomaly based on its radiation signatures. In the absence of ground-truth information, a labeling heuristic provides data necessary for training and testing machine learning models. Supervised logistic regression serves as a baseline to compare three semi-supervised machine learning models: co-training, label propagation, and a convolutional neural network (CNN). In each case, the semi-supervised models outperform logistic regression, suggesting that unlabeled data can be valuable when training and demonstrating value in semi-supervised nonproliferation implementations.
Transitioning from Simulation to Reality: Applying Chatter Detection Models to Real-World Machining Data
Chatter, a self-excited vibration phenomenon, is a critical challenge in high-speed machining operations, affecting tool life, product surface quality, and overall process efficiency. While machine learning models trained on simulated data have shown promise in detecting chatter, their real-world applicability remains uncertain due to discrepancies between simulated and actual machining environments. The primary goal of this study is to bridge the gap between simulation-based machine learning models and real-world applications by developing and validating a Random Forest-based chatter detection system. This research focuses on improving manufacturing efficiency through reliable chatter detection by integrating Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL). The study applies a Random Forest classification model trained on over 140,000 simulated machining datasets, incorporating techniques like Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL) to adapt the model for real-world operational data. The model is validated against 1600 real-world machining datasets, achieving an accuracy of 86.1%, with strong precision and recall scores. The results demonstrate the model’s robustness and potential for practical implementation in industrial settings, highlighting challenges such as sensor noise and variability in machining conditions. This work advances the use of predictive analytics in machining processes, offering a data-driven solution to improve manufacturing efficiency through more reliable chatter detection.
Structure-aware graph neural network based deep transfer learning framework for enhanced predictive analytics on diverse materials datasets
Abstract Modern data mining methods have demonstrated effectiveness in comprehending and predicting materials properties. An essential component in the process of materials discovery is to know which material(s) will possess desirable properties. For many materials properties, performing experiments and density functional theory computations are costly and time-consuming. Hence, it is challenging to build accurate predictive models for such properties using conventional data mining methods due to the small amount of available data. Here we present a framework for materials property prediction tasks using structure information that leverages graph neural network-based architecture along with deep-transfer-learning techniques to drastically improve the model’s predictive ability on diverse materials (3D/2D, inorganic/organic, computational/experimental) data. We evaluated the proposed framework in cross-property and cross-materials class scenarios using 115 datasets to find that transfer learning models outperform the models trained from scratch in 104 cases, i.e., ≈90%, with additional benefits in performance for extrapolation problems. We believe the proposed framework can be widely useful in accelerating materials discovery in materials science.
Short-term solar radiation forecast using total sky imager via transfer learning
Ground-based sky cameras, which capture hemispherical images, have been extensively used for localized monitoring of clouds. This paper proposes a short-term forecasting approach based on transfer learning using Total Sky-Imager (TSI) images of the Southern Great Plains (SGP) site obtained from the Atmospheric Radiation Measurement (ARM) dataset. An accurate estimation of solar irradiance using TSI is key for short-term solar energy generation forecasting and optimal energy consumption planning. We make use of deep neural network architectures such as AlexNet and ResNet-101 to extract the underlying deep convolution features from TSI images and then train using an ensemble learning approach to model and forecast solar radiation. We demonstrate the performance of the proposed approach by showcasing the best and worst cases. Thus, the transfer learning approach significantly reduces the time and resources required for modeling solar radiation. We outperform with reference to another state-of-art technique for solar modeling using TSI images at different forecast lead times.
Deep Learning for Fish Identification from Sonar Data (CRADA 481 Final Report)
In eastern regions of the United States, the American eel is a species of management and regulatory concern because of significant population declines, despite the species’ previous abundance in all tributaries of rivers flowing into the Atlantic Ocean. The American eel is also a candidate for listing under the U.S. Endangered Species Act. While hydropower construction and operation are only one of several factors contributing to this population decline, such a listing could impose additional regulatory challenges for a large number of hydropower projects. In this CRADA project, we improved technologies for identifying migrating eels with the goal of reducing the cost and time required for future American eel hydropower impact assessment and mitigation studies, while maintaining accuracy. We built on results from a previous FOA project (FOA# DE-FOA-0001662), led by the Electric Power Research Institute (EPRI), which developed a highly accurate, deep-learning method for identifying migrating eels from imaging sonar data. The current study aimed to further optimize this deep-learning model, originally designed for image classification, and to develop an object detection software capable of identifying fish from sonar videos in real time, enabling the detection of events like fish migrations and specific species, such as the American eel, at hydropower dams. The data conversion algorithms were packaged as software with a graphical user interface, and the software is evaluated by external collaborators. We focused on the American eel in this project and explored the transferability of the developed deep learning models to the sea lamprey, given the similar body shape and swimming behavior between the two species.
Recent Progress on Surface Water Quality Models Utilizing Machine Learning Techniques
Surface waterbodies are heavily exposed to pollutants caused by natural disasters and human activities. Empowering sensor technologies in water quality monitoring, sufficient measurements have become available to develop machine learning (ML) models. Numerous ML models have quickly been adopted to predict water quality indicators in various surface waterbodies. This paper reviews 78 recent articles from 2022 to October 2024, categorizing water quality models utilizing ML into three groups: Point-to-Point (P2P), which estimates the current target value based on other measurements at the same time point; Sequence-to-Point (S2P), which utilizes previous time series data to predict the target value at one time point ahead; and Sequence-to-Sequence (S2S), which uses previous time series data to forecast sequential target values in the future. The ML models used in each group are classified and compared according to water quality indicators, data availability, and model performance. Widely used strategies for improving performance, including feature engineering, hyperparameter tuning, and transfer learning, are recognized and described to enhance model effectiveness. The interpretability limitations of ML applications are discussed. This review provides a perspective on emerging ML for surface water quality models.
Intra-hour Solar Irradiance Forecast in Multiple Locations using Deep Transfer Learning
In recent years, solar power system installation imposes several challenges on the operations of local and regional power grids due to the inherent variability of ground-level solar irradiance. This work proposes a novel real-time solar forecast methodology for intra-hour solar irradiance based on deep transfer learning from ground-based sky imager for time horizons ranging from 5-15 min. There are three unique aspects of the proposed methodology: (1) a Deep Learning based algorithm development which is modeled as a classification approach rather than a traditional regression approach; (2) the use of the Transfer Learning technique to show generalization capability, robustness, and portability of baseline model in the newly deployed location where availability of enough data for training is typically scarce, and (3) redefinition of point-based irradiation forecast error estimation technique with a window-based one that is more intuitive and user-friendly. The system is developed using multiple years of irradiance and sky image recording in New Jersey and one-year data from Colorado, USA. The method is validated against ground telemetry from these two locations of diverse geographic and climatic conditions. Results show that the forecasting method proposed in this work is robust and highly accurate (8% MAPE error) for multiple locations deployment.
Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations
Accurate frequency modelling of inverter‐based resource (IBR)‐dominated power systems is crucial for ensuring stable, reliable and resilient operations, particularly given their inherent low‐inertia characteristics and fast dynamics that traditional swing equation‐based models inadequately capture. This paper explores neural ordinary differential equations (Neural ODEs) as a computationally efficient, data‐driven framework for modelling power system frequency dynamics, specifically within microgrids integrating high penetrations of distributed energy resources (DERs). The developed neural ODEs framework incorporates a neural network architecture designed to capture input dynamics. By actively perturbing the system with a known signal, the Python‐based neural ODEs framework was trained using measured system states and inputs, without the need for detailed system information. The framework, tested on a model of the Cordova, AK, microgrid, achieved a goodness of fit ranging from 60% to 99% across different state variables and maintained a mean square error in the 10 -6 p.u. range under square and step excitation signals. The proposed approach demonstrated robustness to measurement noise and initial condition variations while maintaining low computational complexity suitable for real‐time power system control applications. Furthermore, transfer learning enabled the neural ODEs model to adapt to the following changes in system topology or generator dispatch, highlighting its effectiveness for dynamic microgrids with frequently evolving configurations and diverse DERs.
A transfer learning approach to energy-efficient control of small and medium-sized commercial buildings
Model-free reinforcement learning (RL) provides a data-driven and adaptive approach to optimize building energy use while satisfying occupant comfort. This powerful tool does not need any prior knowledge about the environment and system it is optimizing and can adapt its policy based on the changes in captures. Like any other data-driven tool, it faces high training costs due to the extensive agent-environment interactions required to capture long-term building dynamics and user comfort. Transfer learning, particularly policy distillation, offers a promising way to accelerate training by leveraging pretrained RL agents in different building and system types. Here, this study investigates online student distillation, in which the student model updates its neural network weights using outputs from teacher models. The work introduces a student distillation strategy designed for efficient knowledge transfer, along with a teacher selection method that ensures high-quality guidance. The approach is validated using a highly calibrated whole building energy model for a small/medium commercial building test facility. Results show substantial reductions in training time and data requirements while surpassing the performance of ASHRAE Guideline 36, an advanced rule-based control strategy. The distilled RL model required 45% less data and achieved 20% higher cumulative rewards than a state-of-the-art RL model, with faster convergence and lower energy consumption. These outcomes demonstrate that effective transfer learning enables a scalable and data-efficient energy management solution for commercial buildings.
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.
Improving net ecosystem CO2 flux prediction using memory-based interpretable machine learning
Terrestrial ecosystems play a central role in the global carbon cycle and affect climate change. However, our predictive understanding of these systems is still limited due to their complexity and uncertainty about how key drivers and their legacy effects influence carbon fluxes. Here, we propose an interpretable Long Short-Term Memory (iLSTM) network for predicting net ecosystem CO 2 exchange (NEE) and interpreting the influence on the NEE prediction from environmental drivers and their memory effects. We consider five drivers and apply the method to three forest sites in the United States. Besides performing the prediction in each site, we also conduct transfer learning by using the iLSTM model trained in one site to predict at other sites. Results show that the iLSTM model produces good NEE predictions for all three sites and, more importantly, it provides reasonable interpretations on the input driver's importance as well as their temporal importance on the NEE prediction. Additionally, the iLSTM model demonstrates good across-site transferability in terms of both prediction accuracy and interpretability. The transferability can improve the NEE prediction in unobserved forest sites, and the interpretability advances our predictive understanding and guides process-based model development.