Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning efficiency”

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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗
DOE OSTI2020

Neural-based time series forecasting of loss of coolant accidents in nuclear power plants

During the last few years, deep learning in neural networks has demonstrated impressive successes in the areas of computer vision, speech and image recognition, text generation, and many others. However, sensitive engineering areas such as nuclear engineering benefited less from these efficient techniques. In this work, deep learning expert systems are utilized to model and predict time series progression of a design-basis nuclear accident, featuring a loss of coolant accident. Two major findings are accomplished in this work. First, the ability to train expert systems with high accuracy, which could help nuclear power plant operators to figure out plant responses during the accident. Second, building fast, efficient, and accurate deep models to simulate nuclear phenomena, which could be valuable to nuclear computational science. In this work, large amount of time series data is obtained from simulation tools by simulating different conditions of the base-case/nominal accident scenario. Four critical outputs/responses are monitored during the accident (e.g. temperature, pressure, break flow rate, water level). Two approaches are adopted in this work. The first approach is to use feedforward deep neural networks (DNN) to fit all time steps and outputs in a single model. The second approach is to use long short-term memory (LSTM) to fit all time steps together for each reactor response separately. Both DNN and LSTM demonstrate very good performance in predicting the test and base-case scenarios, with accuracy as low as 92% and as high as 99%, where these test scenarios are unknown to the expert systems and are not included in the model training. In addition, both approaches demonstrate a significant reduction in computational costs, as the deep expert system is able to accurately predict the accident 100,000 times faster than the original simulation tool. Given sufficient data, the methodology adopted in this study demonstrates that DNN/LSTM expert systems can be used as a decision support system to model advanced time series phenomena within nuclear power plants with high accuracy and negligible computational costs.

42 ENGINEERING↗
DOE OSTI2025

Deep reinforcement learning control for co-optimizing energy consumption, thermal comfort, and indoor air quality in an office building

With the recent demand for decarbonization and energy efficiency, advanced HVAC control using Deep Reinforcement Learning (DRL) becomes a promising solution. Due to its flexible structures, DRL has been successful in energy reduction for many HVAC systems. However, only a few researches applied DRL agents to manage the entire central HVAC system and control multiple components in both the water loop and the air loop, owing to its complex system structures. Moreover, those researches have not extended their applications by incorporating the indoor air quality, especially both CO2 and PM2.5concentrations, on top of energy saving and thermal comfort, as achieving those objectives simultaneously can cause multiple control conflicts. What's more, DRL agents are usually trained on the simulation environment before deployment, so another challenge is to develop an accurate but relatively simple simulator. Therefore, we propose a DRL algorithm for a central HVAC system to co-optimize energy consumption, thermal comfort, indoor CO2 level, and indoor PM2.5 level in an office building. To train the controller, we also developed a hybrid simulator that decoupled the complex system into multiple simulation models, which are calibrated separately using laboratory test data. The hybrid simulator combined the dynamics of the HVAC system, the building envelope, as well as moisture, CO2, and particulate matter transfer. Three control algorithms (rule-based, MPC, and DRL) are developed, and their performances are evaluated on the hybrid simulator environment with a realistic scenario (i.e., with stochastic noises). The test results showed that, the DRL controller can save 21.4 % of energy compared to a rule-based controller, and has improved thermal comfort, reduced indoor CO2 concentration. The MPC controller showed an 18.6 % energy saving compared to the DRL controller, mainly due to savings from comfort and indoor air quality boundary violations caused by unmeasured disturbances, and it also highlights computational challenges in real-time control due to non-linear optimization. Finally, we provide the practical considerations for designing and implementing the DRL and MPC controllers based on their respective pros and cons.

Guo, Fangzhou↗
DOE OSTI2024

Multi-Level Structural Damage Characterization Using Sparse Acoustic Sensor Networks and Knowledge Transferred Deep Learning

Standard structural health monitoring techniques face well-known difficulties for comprehensive defect diagnosis in real-world structures that have structural, material, or geometric complexity. This motivates the exploration of machine-learning-based structural health monitoring methods in complex structures. However, creating sufficient training data sets with various defects is an ongoing challenge for data-driven machine (deep) learning algorithms. The ability to transfer the knowledge of a trained neural network from one component to another or to other sections of the same component would drastically reduce the required training data set. Also, it would facilitate computationally inexpensive machine learning based inspection systems. In this work, a machine-learning-based multi-level damage characterization is demonstrated with the ability to transfer trained knowledge within the sparse sensor network. A novel network spatial assistance and an adaptive convolution technique are proposed for efficient knowledge transfer within the deep learning algorithm. Proposed structural health monitoring method is experimentally evaluated on an aluminum plate with artificially induced defects. It was observed that the method improves the performance of knowledge transferred damage characterization by 50% during localization and 24% during severity assessment. Further, experiments using time windows with and without multiple edge reflections are studied. Results reveal that multiply scattered waves contain rich and deterministic defect signatures that can be mined using deep learning neural networks, improving the accuracy of both identification and quantification. In the case of a fixed sensor network, using multiply scattered waves shows 100% prediction accuracy at all levels of damage characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Emerging Technologies for Improved Plug Load Management Systems: Learning Behavior Algorithms and Automatic and Dynamic Load Detection

Plug loads are responsible for a significant portion of the energy consumed in commercial buildings, yet their distributed and ever-changing nature makes them one of the most challenging building end uses to manage. Plug load management systems exist today that utilize smart plugs to meter and control devices at the outlet level, however, their uptake has been relatively slow in part due to the significant labor required for installation and maintenance. Learning behavior algorithms and automatic and dynamic load detection have been identified as two technology areas that could accelerate the adoption of plug load management systems by reducing these labor demands and providing additional energy efficiency and non-energy benefits. Learning behavior algorithms learn occupant behavior and adjust plug load management systems accordingly, allowing for the automatic creation of optimized control schedules. Automatic and dynamic load detection allows a plug load management system to identify devices as they are plugged in to a building and keeps the system up to date as devices are moved throughout a building. In this paper, we present our findings with respect to the current state of these two technologies based on a review of existing research and patents, as well as a series of interviews with companies working in the plug load space. We have found that, as of now, no commercialized solutions exist for these plug load technologies and that more work is needed to bring them to market. In addition, we summarize our findings related to the technology challenges, market barriers, drivers, and opportunities for these technologies moving forward.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

Automating Bug Report Classification with Few Shot Learning

Orthogonal defect classification (ODC) is a method used to categorize software defects, providing valuable insights into the development process. This study focuses on automating the classification of software bug reports into different ODC defect types using few shot learning, a machine learning approach that requires minimal labeled data. Previous research has manually classified bug reports or used traditional machine learning algorithms like linear support vector machine, achieving limited success. Our approach uses few shot learning to improve classification accuracy and efficiency. The results show a harmonic mean of recall and precision (i.e., the F1 score) of around 0.6 which is a performance improvement over previous methods. The results highlight the potential benefit of few shot learning techniques and their application in enhancing the safety and reliability of nuclear digital instrumentation and control (DI&C) systems. Future work will explore incorporating advanced techniques to supplement the model's training data and achieve better results.

42 - ENGINEERING↗
DOE OSTI2020

Quantum Chemistry-Informed Active Learning to Accelerate the Design and Discovery of Sustainable Energy Storage Materials

Here we employed Density Functional Theory (DFT) to compute oxidation potentials of 1,400 homobenzylic ether molecules to search for the ideal sustainable redoxmer design. The generated data were used to construct an active learning model based on Bayesian optimization (BO) that targets candidates with desired oxidation potentials utilizing only a minimal number of DFT calculations. The active learning model demonstrated not only significant efficiency improvement over the random selection approach but also robust capability in identifying desired candidates in an untested set of 112,000 homobenzylic ether molecules. Our findings highlight the efficacy of quantum chemistry-informed active learning to accelerate the discovery of materials with desired properties from a vast chemical space.

25 ENERGY STORAGE↗
DOE OSTI2025

Machine Learning-Based Process Control for Injection Molding of Recycled Polypropylene

The increased interest in artificial intelligence in manufacturing has driven the adoption of machine learning to optimize processes and improve efficiency. A key challenge in injection molding is the variability of recycled materials, which affects part quality and processing stability. This study presents a novel closed-loop process control approach for injection molding, leveraging machine learning to adaptively predict processing inputs and quality outcomes. The methodology was tested on five blends of recycled polypropylene (rPP), using artificial neural networks (ANNs), linear regression, and polynomial regression to model the relationships between material properties and process parameters. The dataset was split 80/20 into training and testing sets. The ANN model was implemented using TensorFlow and Keras, with six hidden layers of 32 neurons per layer, ReLU activation, and an Adam optimizer. Empirical tuning and early stopping were used to optimize performance and prevent overfitting. Predictions were evaluated based on mean absolute error (MAE), mean squared error (MSE), and percentage error. The results showed that yield stress, ultimate elongation, and part weight were accurately predicted within a 5% error for linear and polynomial regression models and within a 10% error for the ANN. However, modulus predictions were less reliable, with errors of ~11% for ANN and linear regression and ~40% for polynomial regression, reflecting the inherent variability of this property in rPP blends. Predictions of processing inputs had errors ranging from 3% to 25%, depending on the model and response variable. No single modeling approach was consistently superior across all responses, highlighting the complexity of the relationship between material properties, process parameters, and quality metrics. Overall, the work demonstrates that closed-loop process control, powered by machine learning, can effectively predict key quality parameters in injection molding of recycled materials. The proposed approach can improve process stability and material utilization, facilitating increased adoption of sustainable materials.

Krantz, Joshua↗
DOE OSTI2026

A machine learning based approach to online electron reconstruction at CLAS12

Online reconstruction is key for monitoring purposes and real time analysis in High Energy and Nuclear Physics experiments. A necessary component of reconstruction algorithms is particle identification that combines information left by a particle passing through several detector components to identify the particle’s type. Of particular interest to electro-production Nuclear Physics experiments such as CLAS12 is electron identification which is used to trigger data recording. A machine learning approach was developed for CLAS12 to reconstruct and identify electrons by combining raw signals at the data acquisition level from several detector components. Here, this approach achieves an electron identification purity above 75% whilst retaining an efficiency close to 100%. The machine learning tools are capable of running at high rates exceeding the data acquisition rates and will allow electron reconstruction in real-time. This work enhances online analyses and monitoring and can contribute to improved triggering at CLAS12. This machine learning driven approach will also be crucial for experiments aiming to transition to streaming readout operations where online reconstruction will be a key component of the data taking paradigm.

Artificial intelligence↗
DOE OSTI2024

Efficient six-dimensional phase space reconstructions from experimental measurements using generative machine learning

Next-generation accelerator concepts, which hinge on the precise shaping of beam distributions, demand equally precise diagnostic methods capable of reconstructing beam distributions within six-dimensional position-momentum spaces. However, the characterization of intricate features within six-dimensional beam distributions using current diagnostic techniques necessitates a substantial number of measurements, using many hours of valuable beam time. Novel phase space reconstruction techniques are needed to reduce the number of measurements required to reconstruct detailed, high-dimensional beam features in order to resolve complex beam phenomena and as a feedback in precision beam shaping applications. In this study, we present a novel approach to reconstructing detailed six-dimensional phase space distributions from experimental measurements using generative machine learning and differentiable beam dynamics simulations. We demonstrate that this approach can be used to resolve six-dimensional phase space distributions from scratch, using basic beam manipulations and as few as 20 two-dimensional measurements of the beam profile. We also demonstrate an application of the reconstruction method in an experimental setting at the Argonne Wakefield Accelerator, where it is able to reconstruct the beam distribution and accurately predict previously unseen measurements 75× faster than previous methods.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

A critical examination of compound stability predictions from machine-learned formation energies

Machine learning has emerged as a novel tool for the efficient prediction of material properties, and claims have been made that machine-learned models for the formation energy of compounds can approach the accuracy of Density Functional Theory (DFT). The models tested in this work include five recently published compositional models, a baseline model using stoichiometry alone, and a structural model. By testing seven machine learning models for formation energy on stability predictions using the Materials Project database of DFT calculations for 85,014 unique chemical compositions, we show that while formation energies can indeed be predicted well, all compositional models perform poorly on predicting the stability of compounds, making them considerably less useful than DFT for the discovery and design of new solids. Most critically, in sparse chemical spaces where few stoichiometries have stable compounds, only the structural model is capable of efficiently detecting which materials are stable. The nonincremental improvement of structural models compared with compositional models is noteworthy and encourages the use of structural models for materials discovery, with the constraint that for any new composition, the ground-state structure is not known a priori. This work demonstrates that accurate predictions of formation energy do not imply accurate predictions of stability, emphasizing the importance of assessing model performance on stability predictions, for which we provide a set of publicly available tests.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗
DOE OSTI2020

Accelerating geostatistical modeling using geostatistics-informed machine Learning

Ordinary Kriging (OK) is a popular geostatistical algorithm for spatial interpolation and estimation. The computational complexity of OK changes quadratically and cubically for memory and speed, respectively, given the number of data. Therefore, it is computationally intensive and also challenging to process a large set of data, especially in three-dimensional (3D) cases. This paper develops a geostatistics-informed machine learning (GIML) model to improve the efficiency of OK by reducing the number of points required to be estimated using OK. Specifically, only a very few of the unknown points are estimated by OK to get the weights and estimations, which are used as the training dataset. Moreover, the governing equations of OK are used to guide our proposed machine learning to better reproduce the spatial distributions. Our results show that the proposed GIML can reduce the computational time of OK by at least one order of magnitude. The effectiveness of the GIML is evaluated and compared using a 2D case. Furthermore, we demonstrate its efficiency and robustness by considering a different number of training samples on various 3D simulation grids.

58 GEOSCIENCES↗
DOE OSTI2020

Conditional Karhunen-Loève expansion for uncertainty quantification and active learning in partial differential equation models

We use a conditional Karhunen-Lo` eve (KL) model to quantify and reduce uncertainty in a stochastic partial differential equation (SPDE) problem with partially-known space-dependent coefficient, Y (x). We assume that a small number of Y (x) measurements are available and model Y (x) with a KL expansion. We achieve reduction in uncertainty by conditioning the KL expansion coefficients on measurements. We consider two approaches for conditioning the KL expansion: In Approach 1, we condition the KL model first and then truncate it. In Approach 2, we first truncate the KL expansion and then condition it. We employ the conditional KL expansion together with Monte Carlo and sparse grid collocation methods to compute the moments of the solution of the SPDE problem. Uncertainty of the problem is further reduced by adaptively selecting additional observation locations using two active learning methods. Method 1 minimizes the variance of the PDE coefficient, while Method 2 minimizes the variance of the solution of the PDE. We demonstrate that conditioning leads to dimension reduction of the KL representation of Y (x). For a linear diffusion SPDE with uncertain log-normal coefficient, we show that Approach 1 provides a more accurate approximation of the conditional log-normal coefficient and solution of the SPDE than Approach 2 for the same number of random dimensions in a conditional KL expansion. Furthermore, Approach 2 provides a good estimate for the number of terms of the truncated KL expansion of the conditional field of Approach 1. Finally, we demonstrate that active learning based on Method 2 is more efficient for uncertainty reduction in the SPDE’s states (i.e., it leads to a larger reduction of the variance) than active learning using Method 2.

Conditioned Karhunen-Lo` eve expanion, machine lea↗
DOE OSTI2022

Accelerating the discovery of novel magnetic materials using machine learning–guided adaptive feedback

Magnetic materials are essential for energy generation and information devices, and they play an important role in advanced technologies and green energy economies. Currently, the most widely used magnets contain rare earth (RE) elements. An outstanding challenge of notable scientific interest is the discovery and synthesis of novel magnetic materials without RE elements that meet the performance and cost goals for advanced electromagnetic devices. Here, we report our discovery and synthesis of an RE-free magnetic compound, Fe 3 CoB 2 , through an efficient feedback framework by integrating machine learning (ML), an adaptive genetic algorithm, first-principles calculations, and experimental synthesis. Magnetic measurements show that Fe 3 CoB 2 exhibits a high magnetic anisotropy ( K 1 = 1.2 MJ/m 3 ) and saturation magnetic polarization ( J s = 1.39 T), which is suitable for RE-free permanent-magnet applications. Our ML-guided approach presents a promising paradigm for efficient materials design and discovery and can also be applied to the search for other functional materials.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Accelerating charge estimation in molecular dynamics simulations using physics-informed neural networks: corrosion applications

Molecular Dynamics (MD) simulations are used to understand the effects of corrosion on metallic materials in salt brine. Reactive force fields in classical MD enable accurate modeling of bond formation and breakage in the aqueous medium and at the metal-electrolyte interface, while also facilitating dynamic partial charge equilibration. However, MD simulations are computationally intensive and unsuitable for modeling the long time scales characteristic of corrosive phenomena. To address this, we develop reduced-order machine learning models that provide accurate and efficient predictions of charge density in corrosive environments. Specifically, we use Long Short-Term Memory (LSTM) networks to forecast charge density evolution based on atomic environments represented by Smooth Overlap of Atomic Positions (SOAP) descriptors. A physics-informed loss function enforces charge neutrality and electronegativity equivalence. The atomic charges predicted by the deep learning model trained on this work were obtained two orders of magnitude faster than those from molecular dynamics (MD) simulations, with an error of less than 3% compared to the MD-obtained charges, even in extrapolative scenarios, while adhering to physical constraints. This demonstrates the excellent accuracy, computational efficiency, and validity of the developed model. Lastly, even though developed for corrosion, these protocols are formulated in a phenomenon-agnostic manner, allowing application to various variable-charge interatomic potentials and related fields.

Atomistic models↗