Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning operations”

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 91 records · Page 5

Enhancing the Operational Resilience of Advanced Reactors with Digital Twins by Recurrent Neural Networks

Because of a lack of operation data during abnormal and accident scenarios, along with the existence of uncertainty in the evaluation model for transient and accident analysis, the established abnormal and emergency operating procedures can be biased in characterizing the reactor states and ensuring operational resilience. To improve state awareness and ensure operational flexibility for minimizing effects on the system due to anomaly, digital twin (DT) technology is suggested to support operator's decision-making by effectively extracting and using knowledge of the current and future plant states from the knowledge base. To demonstrate DT's capability for recovering the complete states of reactors and for predicting the future reactor behaviors, this paper develops and assesses both the diagnosis and prognosis DTs in a nearly autonomous management and control system for an Experimental Breeder Reactor-II simulator during different loss-of-flow scenarios.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Improving the prediction of daily reservoir releases over the CONUS using conditioned LSTM

Reservoirs play a vital role in regulating streamflow timing and variability for hydroelectricity, flood control, water supply, irrigation, and recreation. Despite their importance, many reservoirs lack comprehensive operational guidelines, making their management complex due to conflicting operational objectives. Hence traditional policy-based reservoir models often fail to capture real-world conditions accurately and they depend on perfect streamflow predictions, which are not always available. In contrast, data-driven models like Long Short-Term Memory (LSTM) networks offer a robust alternative. This study introduces an approach that integrates reservoir characteristics—such as main use, climate, and maximum capacity—into the LSTM model to enhance reservoir release predictions. Using data from nearly 200 reservoirs in the contiguous United States (CONUS), our conditioned LSTM model (LSTM_cond) was compared with both the vanila LSTM and a traditional policy-based approach. Furthermore, our results show that while both LSTM_cond and LSTM perfoms better than the policy-based approach, LSTM_cond consistently outperforms LSTM for hydroelectric, water supply, irrigation, and recreation reservoirs. The KGE median values for LSTM_cond for out-sample reservoirs are 0.764, 0.565, 0.821, and 0.779, respectively, for the aforementioned reservoir types, which are consistently higher that the corresponding KGE values of 0.737, 0.413, 0.775, and 0.713 of LSTM, demonstrating its advantages in improving generalizability.

CONUS↗

Optimizing inference of segmentation on high-resolution images in MLExchange

MLExchange is a machine learning (ML) operations platform providing web user-interfaces (UIs) for data visualization and analysis pipelines at synchrotron facilities. Among these UIs is the segmentation app which helps synchrotron users utilize ML algorithms to automatically segment high-resolution scientific images with minimal manual annotation effort. In this work, we share code optimizations that significantly speed up the segmentation inference workflow of large data in short time. By optimizing the sequence of CPU-GPU data transfers and introducing CPU parallelization to key operations, we improve the per-device, per-image frame computational efficiency and observe close to 3×$$\times$$ speedup over the original segmentation inference workflow run time when utilizing a single GPU. Further adaptations enabling multi-GPU inference yield more than 40×$$\times$$ speedup with 100 GPUs compared to the optimized single GPU inference workflow. This acceleration of the segmentation inference workflow will provide MLExchange users with easy access to segmentation results with little wait time.

Lu, Shizhao↗

Online Electron Reconstruction at CLAS12

Online reconstruction plays a crucial role in monitoring and in real-time analysis of high energy and nuclear physics experiments. A vital aspect of reconstruction algorithms is particle identification, which combines information from various detector components to determine the type of particle. Electron identification is particularly significant in electro-production nuclear physics experiments like the CLAS12 spectrometer at Jefferson Laboratory as it is essential in data recording. A machine learning approach has been developed for CLAS12 experiments to reconstruct and identify electrons by combining raw signals from multiple detector components at the data acquisition level. This method achieves high electron identification purity while maintaining nearly 100% efficiency. Furthermore, the machine learning tools operate at rates exceeding data acquisition speed, enabling the real-time electron reconstruction. This advancement significantly improves online analyses and monitoring capabilities for CLAS12 experiments.

Tyson,, Richard [Thomas Jefferson National Acceler↗

Exact constraints and appropriate norms in machine-learned exchange-correlation functionals

Machine learning techniques have received growing attention as an alternative strategy for developing general-purpose density functional approximations, augmenting the historically successful approach of human-designed functionals derived to obey mathematical constraints known for the exact exchange-correlation functional. More recently, efforts have been made to reconcile the two techniques, integrating machine learning and exact-constraint satisfaction. We continue this integrated approach, designing a deep neural network that exploits the exact constraint and appropriate norm philosophy to de-orbitalize the strongly constrained and appropriately normed (SCAN) functional. The deep neural network is trained to replicate the SCAN functional from only electron density and local derivative information, avoiding the use of the orbital-dependent kinetic energy density. The performance and transferability of the machine-learned functional are demonstrated for molecular and periodic systems.

Artificial neural networks↗

Machine Learning for Daily Forecasts of Arctic Sea Ice Motion: An Attribution Assessment of Model Predictive Skill

Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.

54 ENVIRONMENTAL SCIENCES↗

Non-Intrusive Parallel-in-Time Solvers for Partial Differential Equations (Final Report)

Many time-dependent problems and simulations are often modeled using Partial Differential Equations. Traditional modeling approaches that use sequential time-stepping are reaching a bottleneck in optimizing efficiency. The Center of Applied Science and Computing at Lawrence Livermore National Laboratory extensively works on parallelizing these algorithms to leverage the increasing computational power from the growing number of processors in computer hardware. In particular, they aim to design non-intrusive algorithms that can generalize to a variety of problems and sizes without requiring additional information from or modifications on the original problems. Multigrid Reduction in Time (MGRIT) is a parallel-in-time algorithm that is designed to be non-intrusive. This project focuses on increasing the efficiency of MGRIT by approximating the coarse-grid operator using machine learning approaches as a means to find the most non-intrusive, or general, solution.

97 MATHEMATICS AND COMPUTING↗

Cyber Resilience and Social Equity: Twin Pillars of a Sustainable Energy Future

This paper examines the intersection of security and accessibility within energy systems amidst the rise of grid modernization and digitization, especially considering the regulatory changes and the imperatives of inclusive energy strategies. It addresses the dual need for secure, resilient infrastructure and a commitment to mitigate energy poverty while maintaining equitable access to energy. Amid escalating cybersecurity and physical threats, the paper advocates for sustainable energy delivery systems that ensure robust defenses without compromising the goals of reducing energy poverty and ensuring energy security. This paper identifies the pressing need for Cyber-Informed Engineering (CIE) and Secure-by-Design (SbD) principles, highlighting how these strategies can protect critical infrastructure and democratize access to secure energy, particularly for disadvantaged communities. The analysis underscores the challenges presented by the expansion of attack surfaces, interoperability requirements, and grid-edge analytics, offering innovative solutions that leverage advanced technologies and data-driven insights. Furthermore, this paper addresses the workforce development gap, emphasizing the necessity for public-private partnerships and vendor engagement in creating a skilled cybersecurity workforce. This paper has a dual focus on both the technological aspect of cybersecurity and the social dimension of equity within the context of sustainable energy development. It suggests a comprehensive examination of how these two critical elements interact and support the overarching goal of a sustainable energy future.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Real-time avoidance of the L-mode and H-mode density limit via machine-learned stability metrics

Reliable operation of burning plasma tokamaks will require robust control strategies to avoid macroscopic instability limits such as the L-mode and H-mode density limits (LDL, HDL). In this work, we explore closed-loop avoidance of these phenomena at DIII-D using machine-learned risk metrics. Feedback control is implemented via the ‘DL Supervisor’ scheme, which regulates the chosen risk metric by reducing the density target or increasing NBI heating in real-time. Using the LDL 25 risk metric, the LDL is reproducibly suppressed. We also introduce an HDL risk metric in this study, HDL 25 , which reduces the False Positive Rate by 2x compared to the Greenwald fraction. Applying this scaling to a plasma current ramp-down, we successfully avoid an HDL-driven H/L back-transition. These experiments constitute the first demonstration of real-time DL avoidance using machine-learned risk metrics. These instability metrics outline a path to safer high-density operation, more reliable ramp-down scenarios, and improved off-normal control for next-step devices such as ITER and SPARC.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Automatic log analysis with NLP for the CMS workflow handling

The central Monte-Carlo production of the CMS experiment utilizes the WLCG infrastructure and manages daily thousands of tasks, each up to thousands of jobs. The distributed computing system is bound to sustain a certain rate of failures of various types, which are currently handled by computing operators a posteriori. Within the context of computing operations, and operation intelligence, we propose a Machine Learning technique to learn from the operators with a view to reduce the operational workload and delays. This work is in continuation of CMS work on operation intelligence to try and reach accurate predictions with Machine Learning. We present an approach to consider the log files of the workflows as regular text to leverage modern techniques from Natural Language Processing (NLP). In general, log files contain a substantial amount of text that is not human language. Therefore, different log parsing approaches are studied in order to map the log files’ words to high dimensional vectors. These vectors are then exploited as feature space to train a model that predicts the action that the operator has to take. This approach has the advantage that the information of the log files is extracted automatically and the format of the logs can be arbitrary. In this work the performance of the log file analysis with NLP is presented and compared to previous approaches.

Layer, Lukas↗

GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files

This submission includes example files associated with the Geothermal Operational Optimization using Machine Learning (GOOML) Big Kahuna fictional power plant, which uses synthetic data to model a fictional power plant. A forecast was produced using the GOOML data model framework and fictional input data, and a genetic optimization is included which determines optimal flash plant parameters. The inputs and outputs associated with the forecast and genetic optimization are included. The input and output files consist of data, configuration files, and plots. A link to the Physics-Guided Neural Networks (phygnn) GitHub repository is also included, which augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints. phygnn is used by the GOOML framework to help integrate its machine learning models into the relevant physics and engineering applications. Note that the data included in this submission are intended to provide a demonstration of GOOML's capabilities. Additional files that have not been released to the public are needed for users to run these models and reproduce these results. Units can be found in the readme data resource.

15 GEOTHERMAL ENERGY↗

Application of a machine learning algorithm (XGBoost) to offline RHIC luminosity optimization

The operation parameter optimization in 2020 RHIC low energy run is difficult. First, the RHIC luminosity is affected by many RHIC operation parameters, as well as affected by many Low Energy RHIC electron Cooling (LEReC) operation parameters. Second, the luminosity signal in this run is noisy and not sensitive to these parameter changes, especially when these parameters are very close to their optimized values. It is not easy to distinguish the effects of one parameter from all other operation parameters separately. Therefore, it is difficult to optimize the luminosity by varying these parameters one by one. To find a way for luminosity optimization, we analyze some operation parameters via a machine learning algorithm - XGBoost. After constructing a black-box surrogate model from XGBoost and plotting their partial dependency plots (PDF) and SHAP value plots for different operation parameters, we can find the effects of an individual parameter on the RHIC luminosity and optimize it accordingly.

43 PARTICLE ACCELERATORS↗

Applying AI/ML Techniques to U.S. Nuclear Operating Experience Program

Idaho National Laboratory (INL) has provided technical assistance to the U.S. Nuclear Regulatory Commission (NRC) in reliability and risk analysis including the operating experience (OpE) program since the 1980s. The U.S. nuclear OpE program provides input parameters to the NRC Standardized Plant Analysis Risk models and the industry probabilistic risk assessment (PRA) models. While earlier PRA focuses were on at-power, internal event analysis, the risks from external hazards and during low power shutdown (LPSD) operation could be significant and the needs to develop LPSD PRA and external hazards PRA are on the rise. One issue in developing LPSD PRA is the reasonable estimation of shutdown initiative event (SDIE) frequencies. INL has developed and is maintaining an SDIE database for the NRC. However, this database is based on the reviewing of Licensee Event Reports (LERs), which is believed to be only a subset of “actual” shutdown initiating events occurred in the industry. This paper investigates a new approach to identify and characterize shutdown initiating events from the Institute of Nuclear Power Operations (INPO) industry database using machine learning techniques. The main process in this approach is to find out the relationship between key words in event descriptions and the SDIE categories as in the NRC SDIE database. The relationship can then be applied to the INPO database and search for SDIEs.

99 GENERAL AND MISCELLANEOUS↗