Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Predicting nonequilibrium Green’s function dynamics and photoemission spectra via nonlinear integral operator learning

Understanding the dynamics of nonequilibrium quantum many-body systems is an important research topic in a wide range of fields across condensed matter physics, quantum optics, and high-energy physics. However, numerical studies of large-scale nonequilibrium phenomena in realistic materials face serious challenges due to intrinsic high-dimensionality of quantum many-body problems and the absence of time-invariance. The nonequilibrium properties of many-body systems can be described by the dynamics of the correlator, or the Green's function of the system, whose time evolution is given by a high-dimensional system of integro-differential equations, known as the Kadanoff–Baym equations (KBEs). The time-convolution term in KBEs, which needs to be recalculated at each time step, makes it difficult to perform long-time numerical simulation. In this paper, we develop an operator-learning framework based on recurrent neural networks (RNNs) to address this challenge. We utilize RNNs to learn the nonlinear mapping between Green's functions and convolution integrals in KBEs. By using the learned operators as a surrogate model in the KBE solver, we obtain a general machine-learning scheme for predicting the dynamics of nonequilibrium Green's functions. Besides significant savings per each time step, the new methodology reduces the temporal computational complexity from $O(N_t^3)$ to $O(N_t)$ where N t is the number of steps taken in a simulation, thereby making it possible to study large many-body problems which are currently infeasible with conventional KBE solvers. Through various numerical examples, we demonstrate the effectiveness of the operator-learning based approach in providing accurate predictions of physical observables such as the reduced density matrix and time-resolved photoemission spectra. Moreover, our framework exhibits clear numerical convergence and can be easily parallelized, thereby facilitating many possible further developments and applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Learning nuclear cross sections across the chart of nuclides with graph neural networks

We explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime. Our approach follows a two-stage learning framework. First, we apply representation learning to encode cross section data into a latent space using either variational autoencoders (VAEs) or implicit neural representations (INRs). Then, we train graph neural networks (GNNs) on the resulting embeddings to predict missing values across the nuclear chart by leveraging the topological structure of neighboring isotopes. We demonstrate accurate cross section predictions within a 9 × 9 block of missing nuclei. We also find that the optimal GNN training strategy depends on the type of latent representation used, with VAE embeddings performing best under end-to-end optimization in the original space, while INR embeddings achieve better results when the GNN is trained only in the latent space. Furthermore, using clustering algorithms, we map groups of latent vectors into regions of the nuclear chart and show that VAEs and INRs can discover some of the neutron magic numbers. These findings suggest that deep-learning models based on the representation encoding of cross sections combined with graph neural networks hold significant potential in augmenting nuclear theory models, e.g., by providing reliable estimates of covariances of cross sections, including cross-material covariances.

Machine learning↗
DOE OSTI2023

Explainable machine learning for hydrogen diffusion in metals and random binary alloys

Hydrogen diffusion in metals and alloys plays an important role in the discovery of new materials for fuel cell and energy storage technology. While analytic models use hand-selected features that have clear physical ties to hydrogen diffusion, they often lack accuracy when making quantitative predictions. Machine learning models are capable of making accurate predictions, but their inner workings are obscured, rendering it unclear which physical features are truly important. To develop interpretable machine learning models to predict the activation energies of hydrogen diffusion in metals and random binary alloys, we create a database for physical and chemical properties of the species and use it to fit six machine learning models. Our models achieve root-mean-squared errors between 98–119 meV on the testing data and accurately predict that elemental Ru has a large activation energy, while elemental Cr and Fe have small activation energies. By analyzing the feature importances of these fitted models, we identify relevant physical properties for predicting hydrogen diffusivity. While metrics for measuring the individual feature importances for machine learning models exist, correlations between the features lead to disagreement between models and limit the conclusions that can be drawn. Instead grouped feature importance, formed by combining the features via their correlations, agree across the six models and reveal that the two groups containing the packing factor and electronic specific heat are particularly significant for predicting hydrogen diffusion in metals and random binary alloys. In conclusion, this framework allows us to interpret machine learning models and enables rapid screening of new materials with the desired rates of hydrogen diffusion.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Experimental quantum learning of a spectral decomposition

Currently available quantum hardware allows for small-scale implementations of quantum machine learning algorithms. Such experiments aid the search for applications of quantum computers by benchmarking the near-term feasibility of candidate algorithms. Here we demonstrate the quantum learning of a two-qubit unitary by a sequence of three parameterized quantum circuits containing a total of 21 variational parameters. Moreover, we variationally diagonalize the unitary to learn its spectral decomposition, i.e., its eigenvalues and eigenvectors. We illustrate how this can be used as a subroutine to compress the depth of dynamical quantum simulations. One can view our implementation as a demonstration of entanglement-enhanced machine learning, as only a single (entangled) training data pair is required to learn a 4 × 4 unitary matrix.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Universal Compiling and (No-)Free-Lunch Theorems for Continuous-Variable Quantum Learning

Quantum compiling, where a parameterized quantum circuit is trained to learn a target unitary, is an important primitive for quantum computing that can be used as a subroutine to obtain optimal circuits or as a tomographic tool to study the dynamics of an experimental system. While much attention has been paid to quantum compiling on discrete-variable hardware, less has been paid to compiling in the continuous-variable paradigm. Here we motivate several, closely related, short-depth continuous-variable algorithms for quantum compilation. We analyze the trainability of our proposed cost functions and numerically demonstrate our algorithms by learning arbitrary Gaussian operations and Kerr nonlinearities. We further make connections between this framework and quantum learning theory in the continuous-variable setting by deriving no-free-lunch theorems. These generalization bounds demonstrate a linear resource reduction for learning Gaussian unitaries using entangled coherent-Fock states and an exponential resource reduction for learning arbitrary unitaries using two-mode-squeezed states.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Representation Learning via Quantum Neural Tangent Kernels

Variational quantum circuits are used in quantum machine learning and variational quantum simulation tasks. Designing good variational circuits or predicting how well they perform for given learning or optimization tasks is still unclear. Here we discuss these problems, analyzing variational quantum circuits using the theory of neural tangent kernels. We define quantum neural tangent kernels, and derive dynamical equations for their associated loss function in optimization and learning tasks. We analytically solve the dynamics in the frozen limit, or lazy training regime, where variational angles change slowly and a linear perturbation is good enough. We extend the analysis to a dynamical setting, including quadratic corrections in the variational angles. We then consider a hybrid quantum classical architecture and define a large-width limit for hybrid kernels, showing that a hybrid quantum classical neural network can be approximately Gaussian. The results presented here show limits for which analytical understandings of the training dynamics for variational quantum circuits, used for quantum machine learning and optimization problems, are possible. These analytical results are supported by numerical simulations of quantum machine-learning experiments.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Reinforcement Learning via Gaussian Processes with Neural Network Dual Kernels

While deep neural networks (DNNs) and Gaussian Processes (GPs) are both popularly utilized to solve problems in reinforcement learning, both approaches feature undesirable drawbacks for challenging problems. DNNs learn complex non-linear embeddings, but do not naturally quantify uncertainty and are often data-inefficient to train. GPs infer posterior distributions over functions, but popular kernels exhibit limited expressivity on complex and high-dimensional data. Fortunately, recently discovered conjugate and neural tangent kernel functions encode the behavior of overparameterized neural networks in the kernel domain. We demonstrate that these kernels can be efficiently applied to regression and reinforcement learning problems by analyzing a baseline case study.We apply GPs with neural network dual kernels to solve reinforcement learning tasks for the first time. We demonstrate, using the well understood mountain-car problem, that GPs empowered with dual kernels perform at least as well as those using the conventional radial basis function kernel. Finally, we conjecture that by inheriting the probabilistic rigor of GPs and the powerful embedding properties of DNNs, GPs using NN dual kernels will empower future reinforcement learning models on difficult domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

An Analysis of Post Attack Impacts and Effects of Learning Parameters on Vulnerability Assessment of Power Grid

Due to the increasing number of heterogeneous devices connected to electric power grid, the attack surface increases the threat actors. Game theory and machine learning are being used to study the power system failures caused by external manipulation. Most of existing works in the literature focus on one-shot process of attacks and fail to show the dynamic evolution of the defense strategy. In this paper, we focus on an adversarial multistage sequential game between the adversaries of the smart electric power transmission and distribution system. We study the impact of exploration rate and convergence of the attack strategies (sequences of action that creates large scale blackout based on the system capacity) based on the reinforcement learning approach. We also illustrate how the learned attack actions disrupt the normal operation of the grid by creating transmission line outages, bus voltage violations, and generation loss. This simulation studies are conducted on IEEE 9 and 39 bus systems. The results show the improvement of the defense strategy through the learning process. The results also prove the feasibility of the learned attack actions by replicating the disturbances created in simulated power system.

attack impacts↗
DOE OSTI2020

Power Grid Contingency Analysis with Machine Learning: A Brief Survey and Prospects

We briefly review previous applications of machine learning (ML) in power grid analyses and introduce our ongoing effort toward developing a generative-adversarial (GA) model for fast and reliable grid contingency analyses. According to our review, the persisting limitation of traditional ML techniques in grid analyses is the need for an exhaustive amount of training data for model generalization and accurate predictions. GA models overcome this limitation by first learning true data distribution from a small training set, from which new samples assimilating true data are generated with some variations. Subsequently, GA models can transfer learn or super-generalize with increased accuracy, that is, accurately predict n - (k + 2) contingencies from a small n - k training set and generated n - (k + 1) data. The joint effort between Idaho National Lab and Florida State University strives to develop a zero-shot and deep learning-based contingency analysis tool, named Smart Contingency Analysis Neural Network (SCANN), by leveraging the aforementioned advantages of GA models. The basic architecture of SCANN stems from the Latent Encoding of Atypical Perturbations network combined with an adversarial network, and it is designed to generate imbalanced power flow data from learned true data distributions for prediction purposes. Here we also introduce the abstract concept of resilience-chaos plots, a new resilience characterization tool proposed to complement SCANN by aiding in the assessment of large amounts of high-order contingency predictions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2018

Integrated Multi-Scale Data Analytics and Machine Learning for the Distribution Grid

We consider the field of machine learning and where it is both useful, and not useful, for the distribution grid and buildings interface. While analytics, in general, is a growing field of interest, and often seen as the golden goose in the burgeoning distribution grid industry, its application is often limited by communications infrastructure, or lack of a focused technical application. Overall, the linkage of analytics to purposeful application in the grid space has been limited. In this paper we consider the field of machine learning as a subset of analytical techniques, and discuss its ability and limitations to enable the future distribution grid. To that end, we also consider the potential for mixing distributed and centralized analytics and the pros and cons of these approaches. There is an exponentially expanding volume of measured data being generated on the distribution grid, which, with appropriate application of analytics, may be transformed into intelligible, actionable information that can be provided to the right actors - such as grid and building operators, at the appropriate time to enhance grid or building resilience, efficiency, and operations against various metrics or goals - such as total carbon reduction or other economic benefit to customers. While some basic analysis into these data streams can provide a wealth of information, computational and human boundaries on performing the analysis are becoming significant, with more data and multi-objective concerns. Efficient applications of analysis and the machine learning field are being considered in the loop. This paper describes benefits and limits of present machine-learning applications for use on the grid and presents a series of case studies that illustrate the potential benefits of developing advanced local multi-variate analytics machine-learning-based applications.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Fair Concurrent Training of Multiple Models in Federated Learning

Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL applications may increasingly require multiple FL tasks to be trained simultaneously, sharing clients’ computing resources, which we call Multiple-Model Federated Learning (MMFL). Current MMFL algorithms use naïve average-based client-task allocation schemes that often lead to unfair performance when FL tasks have heterogeneous difficulty levels, as the more difficult tasks may need more client participation to train effectively. Furthermore, in the MMFL setting, we face a further challenge that some clients may prefer training specific tasks to others, and may not even be willing to train other tasks, e.g., due to high computational costs, which may exacerbate unfairness in training outcomes across tasks. We address both challenges by firstly designing FedFairMMFL, a difficulty-aware algorithm that dynamically allocates clients to tasks in each training round, based on the tasks’ current performance levels. We provide guarantees on the resulting task fairness and FedFairMMFL’s convergence rate. We then propose novel auction designs that incentivizes clients to train multiple tasks, so as to fairly distribute clients’ training efforts across the tasks, and extend our convergence guarantees to this setting. Here, we finally evaluate our algorithm with multiple sets of learning tasks on real world datasets, showing that our algorithm improves fairness by improving the final model accuracy and convergence speed of the worst performing tasks, while maintaining the average accuracy across tasks.

Federated learning↗
DOE OSTI2019

A Supervised Machine Learning Approach to Control Energy Storage Devices

This paper introduces a supervised machine learning approach to predict and schedule the real-time operation mode of the next operation interval for residential PV/Battery systems controlled by mode-based controllers. The performance of the mode-based economic model-predictive control (EMPC) approach is used as the benchmark. The residential load and PV data used in the paper are 1-minute data downloaded from the the Pecan Street Project website. The optimal operation mode for each control interval is first derived from the historical data used as the training set. Then, four machine learning algorithms (i.e. neural network, support vector machine, logistic regression, and random forest algorithms) are applied. We compared the performance of the four algorithms when using different number of features and length of the training sets extracted from different months of the year. Simulation results show that using the machine learning approach can effectively improve the performance of the mode-based control system and reduce the computation effort of local controllers because the training can be completed on a cloud-based Machine Learning engine. Furthermore, the work presented in this paper paves the way for using a shared-learning platform to design controllers of residential PV/storage systems. This may significantly reduce the cost for implementing such systems.

25 ENERGY STORAGE↗
DOE OSTI2020

An Edge-Cloud Integrated Solution for Buildings Demand Response Using Reinforcement Learning

Buildings, as major energy consumers, can provide great untapped demand response (DR) resources for grid services. However, their participation remains low in real-life. One major impediment for popularizing DR in buildings is the lack of cost-effective automation systems that can be widely adopted. Existing optimization-based smart building control algorithms suffer from high costs on both building-specific modeling and on-demand computing resources. To tackle these issues, this paper proposes a cost-effective edge-cloud integrated solution using reinforcement learning (RL). Beside RL’s ability to solve sequential optimal decision-making problems, its adaptability to easy-to-obtain building models and the off-line learning feature are likely to reduce the controller’s implementation cost. Using a surrogate building model learned automatically from building operation data, an RL agent learns an optimal control policy on cloud infrastructure, and the policy is then distributed to edge devices for execution. Simulation results demonstrate the control efficacy and the learning efficiency in buildings of different sizes. A preliminary cost analysis on a 4-zone commercial building shows the annual cost for optimal policy training is only 2.25% of the DR incentive received. Results of this study show a possible approach with higher return on investment for buildings to participate in DR programs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control

This paper develops an intelligent grid-interactive building controller, which optimizes building operation during both normal hours and demand response (DR) events. To avoid costly on-demand computation and to adapt to non-linear building models, the controller utilizes reinforcement learning (RL) and makes real-time decisions based on a near-optimal control policy. Learning such a policy typically amounts to solving a hard non-convex optimization problem. We propose to address this problem with a novel global-local policy search method. In the first stage, an RL algorithm based on zero-order gradient estimation is leveraged to search for the optimal policy globally, due to its scalability and the potential to escape some poor performing local optima. The obtained policy is then fine-tuned locally to bring the first-stage solution closer to that of the original unsmoothed problem. Experiments on a simulated five-zone commercial building demonstrate the advantages of the proposed method over existing learning approaches. They also show that the learned control policy outperforms a pragmatic linear model predictive controller (MPC) and approaches the performance of an oracle MPC in testing scenarios. Using a state-of-the-art advanced computing system, we demonstrate that the controller can be learned and deployed within hours of training.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2014

MO-G-BRE-09: Validating FMEA Against Incident Learning Data: A Study in Stereotactic Body Radiation Therapy

Purpose: Though FMEA (Failure Mode and Effects Analysis) is becoming more widely adopted for risk assessment in radiation therapy, to our knowledge it has never been validated against actual incident learning data. The objective of this study was to perform an FMEA analysis of an SBRT (Stereotactic Body Radiation Therapy) treatment planning process and validate this against data recorded within an incident learning system. Methods: FMEA on the SBRT treatment planning process was carried out by a multidisciplinary group including radiation oncologists, medical physicists, and dosimetrists. Potential failure modes were identified through a systematic review of the workflow process. Failure modes were rated for severity, occurrence, and detectability on a scale of 1 to 10 and RPN (Risk Priority Number) was computed. Failure modes were then compared with historical reports identified as relevant to SBRT planning within a departmental incident learning system that had been active for two years. Differences were identified. Results: FMEA identified 63 failure modes. RPN values for the top 25% of failure modes ranged from 60 to 336. Analysis of the incident learning database identified 33 reported near-miss events related to SBRT planning. FMEA failed to anticipate 13 of these events, among which 3 were registered with severity ratings of severe or critical in the incident learning system. Combining both methods yielded a total of 76 failure modes, and when scored for RPN the 13 events missed by FMEA ranked within the middle half of all failure modes. Conclusion: FMEA, though valuable, is subject to certain limitations, among them the limited ability to anticipate all potential errors for a given process. This FMEA exercise failed to identify a significant number of possible errors (17%). Integration of FMEA with retrospective incident data may be able to render an improved overview of risks within a process.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2014

SU-C-BRD-05: Implementation of Incident Learning in the Safety and Quality Management of Radiotherapy: The Primary Experience in a New Established Program with Advanced Techniques

Purpose: To explore the implementation and effectiveness of incident learning for the safety and quality of radiotherapy in a new established radiotherapy program with advanced technology. Methods: Reference to the consensus recommendations by American Association of Physicist in Medicine, an incident learning system was specifically designed for reporting, investigating, and learning of individual radiotherapy incidents in a new established radiotherapy program, with 4D CBCT, Ultrasound guided radiotherapy, VMAT, gated treatment delivered on two new installed linacs. The incidents occurring in external beam radiotherapy from February, 2012 to January, 2014 were reported. Results: A total of 33 reports were analyzed, including 28 near misses and 5 incidents. Among them, 5 originated in imaging for planning, 25 in planning, 1 in plan transfer, 1 in commissioning and 1 in treatment delivery. Among them, three near misses originated in the safety barrier of the radiotherapy process. In terms of error type, 1 incident was classified as wrong patient, 7 near misses/incidents as wrong site, 6 as wrong laterality, 5 as wrong dose, 7 as wrong prescription, and 7 as suboptimal plan quality. 5 incidents were all classified as grade 1/2 of dosimetric severity, 1 as grade 0, and the other 4 as grade 1 of medical severity. For the causes/contributory factors, negligence, policy not followed, inadequate training, failure to develop an effective plan, and communication contributed to 19, 15, 12, 5 and 3 near misses/incidents, respectively. The average incident rate per 100 patients treated was 0.4; this rate fell to 0.28% in the second year from 0.56% in the first year. The rate of near miss fell to 1.24% from 2.22%. Conclusion: Effective incident learning can reduce the occurrence of near miss/incidents, enhance the culture of safety. Incident learning is an effective proactive method for improving the quality and safety of radiotherapy.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2016

SU-D-BRB-05: Quantum Learning for Knowledge-Based Response-Adaptive Radiotherapy

Purpose: There is tremendous excitement in radiotherapy about applying data-driven methods to develop personalized clinical decisions for real-time response-based adaptation. However, classical statistical learning methods lack in terms of efficiency and ability to predict outcomes under conditions of uncertainty and incomplete information. Therefore, we are investigating physics-inspired machine learning approaches by utilizing quantum principles for developing a robust framework to dynamically adapt treatments to individual patient’s characteristics and optimize outcomes. Methods: We studied 88 liver SBRT patients with 35 on non-adaptive and 53 on adaptive protocols. Adaptation was based on liver function using a split-course of 3+2 fractions with a month break. The radiotherapy environment was modeled as a Markov decision process (MDP) of baseline and one month into treatment states. The patient environment was modeled by a 5-variable state represented by patient’s clinical and dosimetric covariates. For comparison of classical and quantum learning methods, decision-making to adapt at one month was considered. The MDP objective was defined by the complication-free tumor control (P{sup +}=TCPx(1-NTCP)). A simple regression model represented state-action mapping. Single bit in classical MDP and a qubit of 2-superimposed states in quantum MDP represented the decision actions. Classical decision selection was done using reinforcement Q-learning and quantum searching was performed using Grover’s algorithm, which applies uniform superposition over possible states and yields quadratic speed-up. Results: Classical/quantum MDPs suggested adaptation (probability amplitude ≥0.5) 79% of the time for splitcourses and 100% for continuous-courses. However, the classical MDP had an average adaptation probability of 0.5±0.22 while the quantum algorithm reached 0.76±0.28. In cases where adaptation failed, classical MDP yielded 0.31±0.26 average amplitude while the quantum approach averaged a more optimistic 0.57±0.4, but with high phase fluctuations. Conclusion: Our results demonstrate that quantum machine learning approaches provide a feasible and promising framework for real-time and sequential clinical decision-making in adaptive radiotherapy.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

MO-DE-BRA-05: EUTEMPE-RX: Combining E-Learning and Face-To-Face Training to Build Expert Knowledge, Skills and Competences for Medical Physicists in Diagnostic and Interventional Radiology

Purpose: In 2013, the EURATOM authorities of the European Commission decided to support the Horizon2020 project submission ‘EUTEMPE-RX’ that aimed for a new set of course modules to train medical physicists in diagnostic and interventional radiology to expert level with small group deep learning. Each module would consist of 2 phases: an e-learning and a face-to-face phase, each phase requiring typically 40h of participant time. Methods: The European Federation (EFOMP) and 13 European partners, all of them selected for their excellent scientific and/or educational skills, led the 12 course modules. A quality manual ensured the quality of course content and organization. Educational workshops familiarized the teachers with e-learning techniques and methods for assessment. Content was set in accordance with the EC document RP174 that lists learning outcomes in terms of knowledge, skills and competences (KSCs) for different specialties and levels of medical physics. Surveys for stake holder satisfaction were prepared. Results: Today the course modules are being realized. The modules cover most of the KSCs in RP174 document. Teachers have challenged the participants with unique tasks: case studies in medical physics leadership, Monte Carlo simulation of a complete x-ray imaging chain, development of a task specific QA protocol, compilation of optimization plans, simulation tasks with anthropomorphic breast models, etc. Participants undertook practical sessions in modern hospitals and visited a synchrotron facility, a calibration lab, screening organizations, etc. Feedback form quality surveys was very positive and constructive. A sustainability plan has been worked out. Conclusion: The modules have enabled the participants to develop their KSCs and cope with challenges in medical physics. The sustainability plan will be implemented to continue the unique combined e-learning and face to face training at high level training in diagnostic and interventional radiology also beyond Europe. The EUTEMPE-RX project is funded by the Horizon2020 - EURATOM program of the European Commission.

60 APPLIED LIFE SCIENCES↗