Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning systems”

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 955 records · Page 53

Combined Force-Frequency Sampling for Simulation of Systems Having Rugged Free Energy Landscapes.

An adaptive, machine learning-based sampling method is presented for simulation of systems having rugged, multidimensional free energy landscapes. The method's main strength resides in its ability to learn both from the frequency of visits to distinct states and the generalized force estimates that arise in a system as it evolves in phase space. This is accomplished by introducing a self-integrating artificial neural network, which generates an estimate of the free energy directly from its derivatives. The usefulness of the proposed combined approach is examined in the context of two concrete examples, namely, an alanine dipeptide molecule in water and a polymer diffusing through a narrow pore. This new method is found to be robust, faster, and more accurate than approaches that rely only on frequency-based or generalized force-based estimations. After combining the proposed approach with overfill protection and support for sparse data storage and training, the method is shown to be more effective than comparable, previously available techniques and capable of scaling efficiently to larger numbers of collective variables.

Sevgen, Emre↗

System and method for structural characterization of materials by supervised machine learning-based analysis of their spectra

A method of supervised machine learning-based spectrum analysis information, using a neural network trained with spectrum information, to identify a specified feature of a given material, a system for supervised machine learning-based spectrum analysis, and a method of training a neural network to analyze spectrum data. The method of supervised machine learning-base spectrum analysis comprises inputting into the neural network spectrum data obtained from a sample of the given material; and the neural network processing the spectrum data, in accordance with the training of the neural network, and outputting one or more values for the specified feature of the sample of the material. In an embodiment, the training set of data includes x-ray absorption spectroscopy data for the given material. In an embodiment, the training set of data includes electron energy loss spectra (EELS) data.

Frenkel, Anatoly↗

HPC formulations of optimization algorithms for tensor completion

Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often accomplished via low-rank sparse tensor factorization, a computationally expensive non-convex optimization problem which has only recently been studied in the context of parallel computing. In this work, we study three optimization algorithms that have been successfully applied to tensor completion: alternating least squares (ALS), stochastic gradient descent (SGD), and coordinate descent (CCD++). We explore opportunities for parallelism on shared- and distributed-memory systems and address challenges such as memory- and operation-efficiency, load balance, cache locality, and communication. Among our advancements are a communication-efficient CCD++ algorithm, an ALS algorithm rich in level-3 BLAS routines, and an SGD algorithm which combines stratification with asynchronous communication. Furthermore, we show that introducing randomization during ALS and CCD++ can accelerate convergence. We evaluate our parallel formulations on a variety of real datasets on a modern supercomputer and demonstrate speedups through 16384 cores. Further, these improvements reduce time-to-solution from hours to seconds on real-world datasets. We show that after our optimizations, ALS is advantageous on parallel systems of small-to-moderate scale, while both ALS and CCD++ provide the lowest time-to-solution on large-scale distributed systems.

97 MATHEMATICS AND COMPUTING↗

Components of the Bond Energy in Polar Diatomic Molecules, Radicals, and Ions Formed by Group-1 and Group-2 Metal Atoms

While many transition metal complexes are known to have high multireference character, the multireference character of main-group closed-shell singlet diatomic molecules like BeF, CaO, and MgO has been less studied. Yet, many group-1 and group-2 diatomic molecules do have multireference character, and they provide informative systems for studying multireference character because they are simpler than transition metal compounds. The goal of the present work is to understand these multireference systems better so that, ultimately, we can apply what we learn to more complicated multireference systems and to the design of new exchange-correlation functionals for treating multireference systems more adequately. Fourteen main-group diatomic molecules and one triatomic molecule (including radicals, cations, and anions, as well as neutral closed-shell species) have been studied for this article. Eight of these molecules contain a group-1 element, and six contain a group-2 element. Seven of these molecules are multireference systems, and eight of them are single-reference systems. Fifty-three exchange-correlation functionals of 11 types [local spin-density approximation (LSDA), generalized gradient approximation (GGA), nonseparable gradient approximation (NGA), global-hybrid GGA, meta-GGA, meta-NGA, global-hybrid meta GGA, range-separated hybrid GGA, range-separated hybrid meta-GGA, range-separated hybrid meta-NGA, and DFT augmented with molecular mechanics damped dispersion (DFT-D)] and the Hartree–Fock method have been applied to calculate the bond distance, bond dissociation energy (BDE), and dipole moment of these molecules. All of the calculations are converged to a stable solution by allowing the symmetry of the Slater determinant to be broken. A reliable functional should not only predict an accurate BDE but also predict accurate components of the BDE, so each bond dissociation energy has been decomposed into ionization potential (IP) of the electropositive element, electron affinity of the electronegative bonding partner (EA), atomic excitation energy (EE) to prepare the valence states of the interacting partners, and interaction energy (IE) of the valence-prepared states. Adding Hartree–Fock exchange helps to obtain better results for atomic excitation energy, and this leads to improvements in getting the right answer for the right reason. The following functionals are singled out for reasonably good performance on all three of bond distance, BDE, and dipole moment: B97-1, B97-3, MPW1B95, M05, M06, M06-2X, M08-SO, N12-SX, O3LYP, TPSS, τ-HCTHhyb, and GAM; all but two (TPSS and GAM) of these functionals are hybrid functionals.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

EdREC: Design and Development of Adaptive Platform for Scaling-up Flipped Mastery Learning

EdREC is an adaptive learning and management platform designed to enhance the adoption of differential classroom and mastery flipped learning in K-12 school system. The platform is an innovative approach to teaching and learning that addresses education needs of each student separately by providing customized education plans and adaptive learning methodologies that tunes to the students abilities as well as giving students freedom to learn in their own way. On one side, EdREC provides innovative ways to help students learn; on the other side, it reduces educators' workload and empowers them to understand their students better. EdREC comes with a state-of-the-art computer algorithm package that enables educators to store and retrieve their students' information and augment their abilities to individualize student attention, get real-time feedback about student education progress, and provide corrective actions. The platform provides approaches to design and develop a differential classroom concept that frees much needed time by the teachers to focus more on the students at the individual level and to increase communication and collaboration opportunities among them.

Gautam, Thakur↗

Integrated and Advanced Lighting Controls: The Next Frontier in Energy Savings?

Lighting energy use has significantly declined as a portion of overall building energy usage due largely to the uptake of more efficient light-emitting diode technology. Although the per unit cost of lighting controls has declined, the installation and use of lighting controls are low and the installation and use of advanced controls are abysmally low. Increased use of advanced and connected lighting controls, and the ability to integrate lighting with other building systems (e.g., heat and air, plug loads, miscellaneous loads) that make the building “smarter,” offer the potential for additional energy savings. Studies into the performance of new, advanced lighting control technologies in commercial buildings have generated new findings. Although each field evaluation has interesting results individually, an analysis of their collective findings across a spectrum of commercial building types will help establish the current state of the technology and implications related to market readiness. This paper will analyze results from available field evaluation studies (recently completed as well as ongoing) of retrofit sites and share findings and insights including: • The amount of energy savings that may be expected from these systems. • Cost effectiveness, monetization, and cost points of these systems. • Ideal characteristics of these systems the most viable. • Lessons learned from the installation, commissioning, and occupant response of these systems. The results will support Department of Energy research investments and help inform efficiency programs of the potential of these emerging technologies and how they may fit within the clean energy future.

Myer, Michael↗

Learning Optimal Power Flow Solutions using Linearized Models in Power Distribution Systems

Solving nonlinear optimal power flow (OPF) problem is computationally expensive, and poses scalability challenges for power distribution networks. An alternative to solving the original nonlinear OPF is the linear approximated OPF models. Although, these linear approximated OPF models are fast, the resulting solutions may result in significant optimality gap. Lately, the application of machine learning (ML) methods in successfully solving the nonlinear OPF has been reported. These methods learn and estimate the nonlinear control policies using a purely data-driven approach. In this paper, we propose an approach to complements the ML based approach to solving OPF using solutions from known linearized OPF model. Specifically, we use supervised learning to map the solutions of linear OPF to nonlinear control variables. Unlike, the traditional ML based methods for OPF that approximate the full distribution feeder model using function approximation, our approach uses a two-node approximation of radial networks. The proposed approach is validated using IEEE 123 bus test system for OPF solutions obtained using the nonlinear OPF models.

optimal power flow, power distribution systems, su↗

Flood Susceptibility Mapping Using Machine Learning and Geospatial-Sentinel-1 SAR Integration for Enhanced Early Warning Systems

This study presents a comprehensive framework for flood susceptibility mapping by integrating geospatial factors with both statistical and machine learning models. Thirteen Flood-related factors, including DEM, slope, TWI, NDVI, etc., are extracted as features of models, and historical flood data derived from Sentinel-1 SAR from 2018 to 2023 are used as the target variables of the models. These datasets are analyzed using a frequency-based statistical model and three machine learning models, including Random Forest, XGBoost, and CNN, to generate flood susceptibility maps. The performance of each model is evaluated through AUC; and SHAP scores are separately generated for Machine learning (ML) models to explain each feature contribution in the ML model. The generated susceptibility maps are validated by high-flood-risk locations monitored by flood sensors, BLE inundation models, and flood-prone areas suggested by the Local Community Task Force. The results indicate that the XGBoost model outperforms all other models, with an AUC of 0.92 and demonstrates the highest alignment with recommended high-flood-risk locations, while the frequency-based statistical model showed the weakest performance with an AUC of 0.65. SHAP value graphs highlight the elevation, slope, and TWI as the most influential features across all models. The susceptibility maps generated by the machine learning model show strong agreement with the BLE map and high-flood-risk areas identified by the local Community Task Force.

Google Engine↗

Mesh Failure Prediction Using Deep Learning Techniques

The goal of this joint effort between SRI and LLNL has been to investigate the use of state-of-the-art deep learning architectures to effectively explore the correlations between a set of mesh zone attributes and manifestations of failure in a given mesh simulation and draw useful conclusions towards a practical failure detection system. Each zone attribute is a scalar feature that is recorded separately for each zone during simulation, resulting in a multivariate time series signal for each zone. Currently, these features are used to manually decide where to apply manual relaxations so that simulations run without any failures. Our long-term vision is to build a machine learning system that is capable of reliably detecting upcoming failures and is able to apply finer-grained targeted relaxations automatically to relevant zones to avoid an expected failure.

97 MATHEMATICS AND COMPUTING↗

Demonstration of Decentralized Physics-Driven Learning

In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain, neurons and synapses self-adjust based on local information. Contrastive learning algorithms have recently been proposed to train physical systems, such as fluidic, mechanical, or electrical networks, to perform machine-learning tasks from local evolution rules. However, to date, such systems have only been implemented in silico due to the engineering challenge of creating elements that autonomously evolve based on their own response to two sets of global boundary conditions. Here, we introduce and implement a physics-driven contrastive learning scheme for a network of variable resistors, using circuitry to locally compare the response of two identical networks subjected to the two different sets of boundary conditions. Using this method, our system effectively trains itself, optimizing its resistance values without the use of a central processor or external information storage. Once the system is trained for a specified allostery, regression, or classification task, the task is subsequently performed rapidly and automatically by the physical imperative to minimize power dissipation in response to the given voltage inputs. Here, we demonstrate that, unlike typical computers, such learning systems are robust to extreme damage (and thus manufacturing defects) due to their decentralized learning. Our twin-network approach is therefore readily scalable to extremely large or nonlinear networks, where its distributed nature will be an enormous advantage; a laboratory network of only 500 edges will already outpace its in silico counterpart.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Joint Chance Constraints in AC Optimal Power Flow: Improving Bounds through Learning

This paper considers distribution systems with a high penetration of distributed, renewable generation and addresses the problem of incorporating the associated uncertainty into the optimal operation of these networks. Joint chance constraints, which satisfy multiple constraints simultaneously with a prescribed probability, are one way to incorporate uncertainty across sets of constraints, leading to a chance-constrained optimal power flow problem. Departing from the computationally-heavy scenario-based approaches or approximations that transform the joint constraint into conservative deterministic constraints, this paper develops a scalable, data-driven approach which learns operational trends in a power network, eliminates zero-probability events (e.g., inactive constraints), and accurately and efficiently approximates bounds on the joint chance constraint iteratively. In particular, the proposed framework improves upon the classic methods based on the union bound (or Boole's inequality) by generating a much less conservative set of single chance constraints that also guarantees the satisfaction of the original joint constraint. The proposed framework is evaluated numerically using the IEEE 37-node test feeder, focusing on the problem of voltage regulation in distribution grids.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Artificial Intelligence/Deep Learning FRNN Software for Prediction & Real-Time Control of DIII-D Plasma Control System (PCS)

This collaborative project integrated an improved version of the Artificial Intelligence/Deep Learning FRNN prediction and control software into the real-time DIII-D PCS (plasma control system). A key AI/DL software challenge is to build a modern high-performance computing (HPC) enabled “synthetic plasma simulator” capable of carrying out HPC-driven real-time plasma control applications. This involves development of a deep learning framework to train the surrogate model for a first-principles-based instability analysis simulator (“SGTC”) derived from the global gyrokinetic code GTC. The role of SGTC is to provide accurate and detailed plasma instability information from a real-time AI-based simulator capability to complement the deep learning prediction and control from experimentally-measured signals, such as ECE Imaging, supplemented by synthetic SGTC-ECEI.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Probabilistic learning and updating of a digital twin for composite material systems

This paper presents an approach for characterizing and estimating statistical dependence between a large number of observables in a composite material system. Conditional regression is carried out using the estimated joint density function, permitting a systematic exploration of interdependence between fine scale and coarse observables that can be used for both prognosis and design of complex material systems. An example demonstrates the integration of experimental data with a computational database. The statistical approach is based on the probabilistic learning on manifolds recently developed by the authors. This approach leverages intrinsic structure detected through diffusion on graphs with projected stochastic differential equations to generate samples constrained to that structure.

42 ENGINEERING↗

Power System Frequency Dynamics Modeling, State Estimation, and Control using Neural Ordinary Differential Equations (NODEs) and Soft Actor-Critic (SAC) Machine Learning Approaches

With the global energy transition of the electric power system, grid control, supervision, and protection is becoming more challenging. With the increasing integration of renewable energy sources (RES), the system dynamics are changing, causing traditional power system dynamic modeling with swing equation-based modeling approaches to fail. Additionally, the converter-dominated power grid is decreasing the system inertia, making the power system more fragile to the frequency swings. This paper first investigates and compares the application of a model-based Kalman filter state estimation approach with (i) a model-free machine learning approach --- neural ordinary differential equations (NODEs) --- and (ii) a data-driven system identification (SysId) approach to model and infer critical state values of the power system frequency dynamics. Then a model predictive control (MPC) framework is compared to a model-free Soft Actor-Critic (SAC) reinforcement learning (RL) control algorithm in providing efficient fast frequency response (FFR) to the power system frequency dynamics. The approaches are compared in terms of their performance goals as well as their per-timestep computational efficiency. Furthermore, the comparative study for state estimation shows that for the model-free requirement, both NODEs and SysId can provide accurate state estimates; however, with increasing model complexity, NODEs can be a better choice for model identification. Similarly, the results from the FFR comparative study show that the SAC RL-based FFR, once trained, outperforms MPC with better control signals and faster computation time, making the SAC RL-based FFR better option for providing FFR to the power system.

97 MATHEMATICS AND COMPUTING↗

A Cyber-Physical System for Freeway Ramp Meter Signal Control Using Deep Reinforcement Learning in a Connected Environment

Freeway bottlenecks such as on-ramp merging areas account for about 40% of recurring freeway congestion. It is generally agreed that building more roads and adding more lanes to existing infrastructure does not solve the congestion problem, and so dynamic traffic control measures offer a more cost-effective alternative. Ramp meters, traffic signal devices that regulate traffic flow entering freeways, are among the most effective measures to mitigate congestion at on-ramp merging areas on freeways. The confluence of deep reinforcement learning (RL) and connectivity provides a possible solution to advance ramp meter signal control. Deep RL is a group of machine-learning methods that enables an agent learning from the environment to improve its performance. In this study, three deep RL methods-proximal policy optimization (PPO), Ape-X deep Q-network (DQN), and asynchronous advantage actor-critic agents (A3C)-are explored for ramp meter signal control to maximize vehicle speed and traffic throughput, as well as to minimize energy consumption and emissions at freeway on-ramp merging areas in a connected environment. The low computational requirement and scalability of deep RL for deployment make it a powerful optimization tool for time-sensitive applications such as ramp meter signal control. The results of this study show that deep RL methods yield superior performance to both a fixed-time controller and ALINE A, a state-of-the-art feedback controller.

ADVANCED PROPULSION SYSTEMS,MATHEMATICS AND COMPUT↗

Meta-Learning Enhanced Physics-Informed Graph Attention Convolutional Network for Distribution Power System State Estimation

Promptly perceiving distribution system states is challenged by frequent topology changes and uncertain power injections. To address these issues, a Meta-learning enhanced physics-informed graph attention convolutional network (Meta-PIGACN) model is proposed to handle topological variability in distribution system state estimation (DSSE). Specifically, physics information is integrated into the graph convolutional network, enabling a physics-informed edge-weighting process that incorporates physical information to control the aggregation of neighboring nodes. Besides, the graph attention mechanism automatically adjusts the importance of different neighboring nodes, allowing the capture and preservation of inherent system features across varying topologies, thereby improving state estimation accuracy. Furthermore, meta-learning is proposed to acquire empirical knowledge across multiple topologies so that the model can rapidly adapt to new configurations through iterative gradient descent updates even in large-scale systems. In conclusion, the simulation results based on the 33/118/1746-node distribution systems show the high accuracy and efficiency of the proposed model.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Peer Review to Peer Learning in Radiology: Where Have We Been, What Have We Learned and Where Are We Headed?

Purpose of review: To review and contrast varying methods of peer assessment driven practice quality improvement programs in radiology with an emphasis on peer review and peer learning. Recent findings: Review of the literature revealed that the current consensus is that a shift away from the original peer review system toward a peer learning process has the most beneficial effects for organizations seeking to maximally improve performance. This requires altering perceptions towards the peer review process itself, and significant time, effort, and resources. Summary: The transition to a peer learning process is a necessity to advance the field of radiology into an era of delivering near faultless quality health care.

62 RADIOLOGY AND NUCLEAR MEDICINE↗