Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning Algorithm”

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 1,783 records · Page 99
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Time-lapse seismic data inversion for estimating reservoir parameters using deep learning

Geologic carbon sequestration involves the injection of captured carbon dioxide ([Formula: see text]) into subsurface formations for long-term storage. The movement and fate of the injected [Formula: see text] plume is of great concern to regulators because monitoring helps to identify potential leakage zones and determines the possibility of safe long-term storage. To address this concern, we design a deep-learning framework for [Formula: see text] saturation monitoring to determine the geologic controls on the storage of the injected [Formula: see text]. We use different combinations of porosities and permeabilities for a given reservoir to generate saturation and velocity models. We train the deep-learning model with a few time-lapse seismic images and their corresponding changes in saturation values for a particular [Formula: see text] injection site. The deep-learning model learns the mapping from the change in the time-lapse seismic response to the change in [Formula: see text] saturation during the training phase. We then apply the trained model to data sets comprising different time-lapse seismic image slices (corresponding to different time instances) generated using different porosity and permeability distributions that are not part of the training to estimate the [Formula: see text] saturation values along with the plume extent. Our algorithm provides a deep-learning assisted framework for the direct estimation of [Formula: see text] saturation values and plume migration in heterogeneous formations using the time-lapse seismic data. Our method improves the efficiency of time-lapse inversion by streamlining the large number of intermediate steps in the conventional time-lapse inversion workflow. This method also helps to incorporate the geologic uncertainty for a given reservoir by accounting for the statistical distribution of porosity and permeability during the training phase. Tests on different examples verify the effectiveness of our approach.

Geochemistry & Geophysics↗
DOE OSTI2019

Evaluation of Machine Learning Approaches to Estimate Aerosol Mixing State Metrics in Atmospheric Models

Aerosol mixing state describes how aerosol compositions are distributed among atmospheric aerosol particles in a population. Oversimplified assumptions of aerosol mixing state in atmospheric modeling can introduce errors in estimations of weather and climate-relevant aerosol microphysical properties. A more comprehensive representation of the aerosol mixing state can be achieved in principle with a Particle-resolved Monte Carlo (PartMC) model but at added computational cost that may be prohibitive for direct invocation in operational numerical weather prediction or multi-year climate simulations. The aim of our research is to explore the machine learning (ML) methodologies for estimating aerosol mixing state metrics, which we define here in three different ways: with respect to (a) hygroscopicity; (b) optical properties; and (c) chemical species abundance. We adopted a data-driven approach, leveraging deep learning and statistical learning techniques, to take advantage of massive PartMC model simulations. First, we performed particle-resolved simulations by PartMC to create a series of scenarios considering a range of global environmental conditions. Each scenario consists of aerosol populations and corresponding mixing state metrics. The gas concentration, aerosol mass concentration, environmental variables and mixing state metrics of each population constitute the datasets for machine learning implementations. We have adopted and evaluated various configurations of machine learning methodologies in this investigation, embracing deep learning, Extreme Gradient Boosting (XGBoost) algorithm, and the ensemble approaches. After a rigorous model selection process, we identified an appropriate model to derive estimates of aerosol mixing state metrics. We used the computational and data resources of the Oak Ridge Leadership Computing Facility (OLCF) and the ORNL Compute and Data Environment for Science (CADES). The NVIDIA DGX-1 hardware was used for the prototyping of the ML models. Our approach has allowed us to gain a new understanding of how machine learning methodologies can be applied to improve the representation of aerosol mixing state in atmospheric models and benefit the atmospheric research community. Next, we plan to extend our research and methodology to quantify some of the aerosol-related uncertainties in the E3SM Atmospheric Model (EAM) Version 1.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems

This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (DRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions in the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DRL environment. The proposed method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.

41 EE - Solar Energy Technologies Office (EE-4S)↗
DOE OSTI2016

SU-F-R-10: Selecting the Optimal Solution for Multi-Objective Radiomics Model

Purpose: To develop an evidential reasoning approach for selecting the optimal solution from a Pareto solution set obtained by a multi-objective radiomics model for predicting distant failure in lung SBRT. Methods: In the multi-objective radiomics model, both sensitivity and specificity are considered as the objective functions simultaneously. A Pareto solution set with many feasible solutions will be resulted from the multi-objective optimization. In this work, an optimal solution Selection methodology for Multi-Objective radiomics Learning model using the Evidential Reasoning approach (SMOLER) was proposed to select the optimal solution from the Pareto solution set. The proposed SMOLER method used the evidential reasoning approach to calculate the utility of each solution based on pre-set optimal solution selection rules. The solution with the highest utility was chosen as the optimal solution. In SMOLER, an optimal learning model coupled with clonal selection algorithm was used to optimize model parameters. In this study, PET, CT image features and clinical parameters were utilized for predicting distant failure in lung SBRT. Results: Total 126 solution sets were generated by adjusting predictive model parameters. Each Pareto set contains 100 feasible solutions. The solution selected by SMOLER within each Pareto set was compared to the manually selected optimal solution. Five-cross-validation was used to evaluate the optimal solution selection accuracy of SMOLER. The selection accuracies for five folds were 80.00%, 69.23%, 84.00%, 84.00%, 80.00%, respectively. Conclusion: An optimal solution selection methodology for multi-objective radiomics learning model using the evidential reasoning approach (SMOLER) was proposed. Experimental results show that the optimal solution can be found in approximately 80% cases.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Deep Learning Based Frequency Stability Assessment in Power Grid with High Renewables

Frequency stability assessment is one critical aspect of power system security assessment. Traditional N-1 screening method is based on the simulations of a few typical daily and seasonal operation scenarios. However, the increasing integration of inverter-based renewables and the retirement of conventional synchronous generators result in decreasing system inertia and growing complexity of system operating conditions. Selecting a few typical operation scenarios cannot cover all operating conditions, and the time-domain simulation of all operation conditions requires tremendous time. This paper proposes a more efficient frequency stability assessment method based on deep learning. The affinity propagation clustering algorithm is used to divide the dataset into different clusters, so the selected dataset for training can cover the diversified operating conditions as much as possible. Also, feature normalization is applied to both the training dataset and testing dataset in order to remove any unnecessary bias. Especially, trained model based on full dataset normalization has bounded error in the prediction. The case study on the reduced 240-bus WECC system demonstrates that the proposed method can predict accurate frequency nadir with limited training dataset. The deep learning model using the revised feature normalization can predict more accurate frequency nadir than that using the traditional feature normalization and has very small maximum prediction error.

affinity propagation↗
DOE OSTI2021

Machine Learning Model Geotiffs - Applications of Machine Learning Techniques to Geothermal Play Fairway Analysis in the Great Basin Region, Nevada

This submission contains geotiffs, supporting shapefiles and readmes for the inputs and output models of algorithms explored in the Nevada Geothermal Machine Learning project, meant to accompany the final report. Layers include: Artificial Neural Network (ANN), Extreme Learning Machine (ELM), Bayesian Neural Network (BNN), Principal Component Analysis (PCA/PCAk), Non-negative Matrix Factorization (NMF/NMFk), input rasters of feature sets, and positive/negative training sites. See readme .txt files and final report for additional metadata. A submission linking the full codebase for generating machine learning output models is available under "related resources" on this page.

15 GEOTHERMAL ENERGY↗
DOE OSTI2023

Hybrid stochastic synapses enabled by scaled ferroelectric field-effect transistors

Achieving brain-like density and performance in neuromorphic computers necessitates scaling down the size of nanodevices emulating neuro-synaptic functionalities. However, scaling nanodevices results in reduction of programming resolution and emergence of stochastic non-idealities. While prior work has mainly focused on binary transitions, in this work, we leverage the stochastic switching of a three-state ferroelectric field-effect transistor to implement a long-term and short-term two-tier stochastic synaptic memory with a single device. Experimental measurements are performed on a scaled 28 nm high-k metal gate technology-based device to develop a probabilistic model of the hybrid stochastic synapse. In addition to the advantage of ultra-low programming energies afforded by scaling, our hardware–algorithm co-design analysis reveals the efficacy of the two-tier memory in comparison to binary stochastic synapses in on-chip learning tasks—paving the way for algorithms exploiting multi-state devices with probabilistic transitions beyond deterministic ones.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2023

Quantum Neural Networks: Issues, Training, and Applications

Our work in the field aims at explaining the limitations and expressive power of Quantum Machine Learning models, as well as finding feasible training algorithms that could be implemented in near-term Quantum Computers. The promise of Quantum Machine Learning is that by incorporating quantum effects, such as entanglement, into machine learning models researchers can improve model performance and understand more complex datasets. This pledge is particularly pronounced in the design of Quantum neural networks (QNNs), a promising framework for creating quantum algorithms, that promise to outperform classical models by combining the speedups of quantum computation with the widespread successes of deep learning. We show that applying this approach alone to quantum deep learning is problematic given that an excess of entanglement between the hidden and visible layers can destroy the predictive power of our QNN models. We address the barren plateau problem by suggesting the use of a generative, unbounded, nonlinear loss function with simple gradients. The loss function quantifies how much the quantum states generated by the QNNs differ from the data and the goal during training is to minimize it. Finally, we showcase how to use generative training to construct a "classical-quantum" neural network to accurately interpolate between the ground states of a Molecular Hamiltonian, a central question in Quantum Chemistry.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Micropulse Lidar Cloud Mask Machine-Learning Value-Added Product Report

Cloud detection algorithms of various techniques have been developed and applied to atmospheric ground-based lidar data to identify cloud boundaries and produce clouds masks. While these algorithms are able to identify a wide variety of cloud types and conditions, it is often observed that the algorithms can still fail to accurately detect clouds that are readily discernible when inspecting the lidar imagery. Based on this observation, an alternative approach for cloud detection is to take advantage of machine-learning capabilities and the trained human eye as an interpreter of lidar images, and in turn, to train a neural network to recognize the desired features in the lidar data.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Stopping criteria for ending autonomous, single detector radiological source searches

While the localization of radiological sources has traditionally been handled with statistical algorithms, such a task can be augmented with advanced machine learning methodologies. The combination of deep and reinforcement learning has provided learning-based navigation to autonomous, single-detector, mobile systems. However, these approaches lacked the capacity to terminate a surveying/search task without outside influence of an operator or perfect knowledge of source location (defeating the purpose of such a system). Two stopping criteria are investigated in this work for a machine learning navigated system: one based upon Bayesian and maximum likelihood estimation (MLE) strategies commonly used in source localization, and a second providing the navigational machine learning network with a “stop search” action. A convolutional neural network was trained via reinforcement learning in a 10 m × 10 m simulated environment to navigate a randomly placed detector-agent to a randomly placed source of varied strength (stopping with perfect knowledge during training). The network agent could move in one of four directions (up, down, left, right) after taking a 1 s count measurement at the current location. During testing, the stopping criteria for this navigational algorithm was based upon a Bayesian likelihood estimation technique of source presence, updating this likelihood after each step, and terminating once the confidence of the source being in a single location exceeded 0.9. A second network was trained and tested with similar architecture as the previous but which contained a fifth action: for self-stopping. The accuracy and speed of localization with set detector and source initializations were compared over 50 trials of MLE-Bayesian approach and 1000 trials of the CNN with self-stopping. The statistical stopping condition yielded a median localization error of ~1.41 m and median localization speed of 12 steps. The machine learning stopping condition yielded a median localization error of 0 m and median localization speed of 17 steps. This work demonstrated two stopping criteria available to a machine learning guided, source localization system.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
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

Control simulations of many-body quantum systems by a synergism of discrete real-time learning and optimal control theory

We present a self-consistent algorithm for optimal control simulations of many-body quantum systems. The algorithm features a two-step synergism that combines discrete real-time machine learning (DRTL) with Quantum Optimal Control Theory (QOCT) using the time-dependent Schrödinger equation. Specifically, in step (1), DRTL is employed to identify a compact working space (i.e., the important portion of the Hilbert space) for the time evolution of the many-body quantum system in the presence of a control field (i.e., the initial or previously updated field), and in step (2), QOCT utilizes the DRTL-determined working space to find a newly updated control field for a chosen objective. Steps 1 and 2 are iterated until a self-consistent control objective value is reached such that the resulting optimal control field yields the same targeted objective value when the corresponding working space is systematically enlarged. Furthermore, to demonstrate this two-step self-consistent DRTL-QOCT synergistic algorithm, we perform optimal control simulations of strongly interacting 1D as well as 2D Heisenberg spin systems. In both scenarios, only a single spin (at the left end site for 1D and the upper left corner site for 2D) is driven by the time-dependent control fields to create an excitation at the opposite site as the target. It is found that, starting from all spin-down zero excitation states, the synergistic method is able to identify working spaces and convergence of the desired controlled dynamics with just a few iterations of the overall algorithm. In the cases studied, the dimensionality of the working space scales only quasi-linearly with the number of spins.

Artificial neural networks↗
DOE OSTI2025

High Fidelity Digital Twins for BWRX-300 Critical Systems

This project developed and demonstrated digital-twin technology for advanced nuclear systems under the ARPA-E GEMINA program, with a focus on the BWRX-300 small modular reactor. The primary objective was to reduce operation and maintenance (O&M) costs through predictive health monitoring and model-based fault detection. The project combined MIT’s high-fidelity physics models and machine-learning and digital-twin algorithms, and GE Hitachi’s digital-twin algorithms and operational expertise to build physics-based digital twins capable of real-time system monitoring and maintenance scheduling.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

A differentiable approach to the maximum independent set problem using dataless neural networks

The success of machine learning solutions for reasoning about discrete structures has brought attention to its adoption within combinatorial optimization algorithms. Such approaches generally rely on supervised learning by leveraging datasets of the combinatorial structures of interest drawn from some distribution of problem instances. Reinforcement learning has also been employed to find such structures. Here, in this paper, we propose a different approach in that no data is required for training the neural networks that produce the solution. In this sense, what we present is not a machine learning solution, but rather one that is dependent on neural networks and where backpropagation is applied to a loss function defined by the structure of the neural network architecture as opposed to a training dataset. In particular, we reduce the popular combinatorial optimization problem of finding a maximum independent set to a neural network and employ a dataless training scheme to refine the parameters of the network such that those parameters yield the structure of interest. Additionally, we propose a universal graph reduction procedure to handle large-scale graphs. The reduction exploits community detection for graph partitioning and is applicable to any graph type and/or density. Experimental results on both real and synthetic graphs demonstrate that our proposed method performs on par or outperforms state-of-the-art learning-based methods in terms of the size of the found set without requiring any training data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Data-Driven Performance Optimization of Gamma Spectrometers With Many Channels

In gamma spectrometers with variable spectroscopic performance across many channels (e.g., many pixels or voxels), a tradeoff exists between including data from successively worse-performing readout channels and increasing efficiency. Brute-force calculation of the optimal set of included channels is exponentially infeasible as the number of channels grows, and approximate methods are required. In this work, we present a data-driven framework for attempting to find near-optimal sets of included detector channels. The framework leverages non-negative matrix factorization (NMF) to learn the behavior of gamma spectra across the detector and clusters similarly-performing detector channels together. Performance comparisons are then made between spectra with channel clusters removed, which is more feasible than brute force. The framework is general and can be applied to arbitrary, user-defined performance metrics depending on the application. We apply this framework to optimizing gamma spectra measured by H3D M400 CdZnTe (CZT) spectrometers, which exhibit variable performance across their crystal volumes. In particular, we show several examples optimizing various performance metrics for uranium and plutonium gamma spectra in non-destructive assay (NDA) for nuclear safeguards, and explore trends in performance versus parameters such as clustering algorithm type. We also compare the NMF + clustering pipeline to several non-machine-learning (ML) algorithms, including several greedy algorithms. Although, we find that the NMF + clustering pipeline tends to find the best-performing set of detector voxels, significantly improving over the unoptimized spectra, but that a greedy accumulation of spectra segmented by detector depth can, in some cases, give similar performance improvements in much less computation time.

Energy resolution↗
DOE OSTI2024

Flat and Level Analysis Tool (FLAT) for real-time automated segmentation and analysis of concrete slab point clouds

In the United States, the flatness and levelness of concrete floors during construction is traditionally specified by a maximum allowable gap under a 3 meter straightedge. However, the straightedge method is inexact and rarely representative of the entire floor since the technician is free to choose any location on the floor to perform the measurement. In cases requiring a higher degree of precision and repeatability, concrete floor flatness and levelness can be measured using the standard test method ASTM E1155. With the recent introduction of advanced surveying instruments such as robotic theodolites and terrestrial laser scanners (TLS), the means now exist to modernize and expedite the measurement of floor flatness and levelness. This paper details the development and demonstration of a digital tool, named the Flat and Level Analysis Tool (FLAT), to automate and expedite the segmentation and analysis of flatness and levelness from dense point cloud data of concrete floor slabs. Segmentation algorithms were developed using unsupervised machine learning to extract the set of points belonging to the concrete floor slab from a full 360 scan of a construction site. After segmentation, automated analysis algorithms report the results according to the standard method. The developed algorithms were demonstrated on a dense point cloud captured from a concrete slab-on-grade at a construction site. Results show that the digital tool can quickly provide estimates for floor flatness and levelness with minimal human involvement with comparable accuracy to manual methods.

Hayes, Nolan↗
DOE OSTI2019

Recent advances in machine learning towards multiscale soft materials design

The multiscale design of soft materials requires an ensemble of computational techniques spanning quantum-chemistry to molecular dynamics to continuum modeling. The recent emergence of machine-learning (ML) and modern optimization algorithms has accelerated material property prediction, as well as stimulated the development of hybrid ML/molecular modeling methodologies capable of providing physical insights unobtainable from purely physics-based modeling and intuition. Such hybrid techniques also have important ramifications for the ML-enhanced interpretation of results from simulations and experiments alike. Leveraging ML techniques for the design of chemical or morphological structures based on a target property or functionality represents an exciting goal for the general area of soft materials, including polymers, liquid crystals, colloids, or biomolecules, to name a few representative classes of systems. Furthermore, we provide a perspective on recent work using ML techniques of relevance for the multiscale design of soft materials and outline potential future directions of interest to the soft materials community.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Machine Learning-based Cyber-Physical Anomaly Detection in Wide Area Voltage Control Systems

Wide-area voltage control systems (WAVCS) are widely deployed in power grid to improve the voltage stability in transmission system using Flexible AC Transmission System (FACTS) devices. The WAVCS relies on wide-area measurement and control signals for closed-loop control of FACTS devices to improve the transient voltage stability in power grid in real-time. Since the WAVCS utilizes a cyber-layer communication during its normal operation, they are susceptible to cyber attacks from adversaries which can lead to a voltage collapse if the attacks go undetected and unmitigated. This paper proposes a supervised machine learning (ML)-based anomaly detection algorithm for detecting various stealthy cyber attacks in the context of WAVCS cybersecurity. In particular, a fuzzy logic-based wide-area controller, as proposed by the Bonneville Power Administration (BPA), is implemented on the Kundur’s four machine two-area system that is integrated with a static var compensator (SVC) to improve voltage profile on sensitive buses. Later, different types of data integrity attacks, including pulse and ramp attacks, are considered on the wide-area measurement and control signals to analyze the performance of the proposed anomaly detector. Our experimental evaluation shows a promising performance with a high true-positive rate (more than 99%) and low false-negative rate (less than 1%) while exhibiting a small prediction time.

24 POWER TRANSMISSION AND DISTRIBUTION↗