Search NASA⌕ Search

SEARCH · Search NASA

Results for “Machine 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 1,027 records · Page 57

Communication-Avoiding Parallel Sparse-Dense Matrix-Matrix Multiplication

Multiplication of a sparse matrix with a dense matrix is a building block of an increasing number of applications in many areas such as machine learning and graph algorithms. However, most previous work on parallel matrix multiplication considered only both dense or both sparse matrix operands. This paper analyzes the communication lower bounds and compares the communication costs of various classic parallel algorithms in the context of sparse-dense matrix-matrix multiplication. We also present new communication-avoiding algorithms based on a 1D decomposition, called 1.5D, which - while suboptimal in dense-dense and sparse-sparse cases - outperform the 2D and 3D variants both theoretically and in practice for sparse-dense multiplication. Our analysis separates one-time costs from per iteration costs in an iterative machine learning context. Experiments demonstrate speedups up to 100x over a baseline 3D SUMMA implementation and show parallel scaling over 10 thousand cores.

Koanantakool, Penporn↗

Bond order predictions using deep neural networks

Machine learning is an extremely powerful tool for the modern theoretical chemist since it provides a method for bypassing costly algorithms for solving the Schrödinger equation. Already, it has proven able to infer molecular and atomic properties such as charges, enthalpies, dipoles, excited state energies, and others. Most of these machine learning algorithms proceed by inferring properties of individual atoms, even breaking down total molecular energy into individual atomic contributions. In this paper, we introduce a modified version of the Hierarchically Interacting Particle Neural Network (HIP-NN) capable of making predictions on the bonds between atoms rather than on the atoms themselves. We train the modified HIP-NN to infer bond orders for a large number of small organic molecules as computed via the Natural Bond Orbital package. We demonstrate that the trained model is extensible to molecules much larger than those in the training set by studying its performance on the COMP6 dataset. This method has applications in cheminformatics and force field parameterization and opens a promising future for machine learning models to predict other quantities that are defined between atoms such as density matrix elements, Hamiltonian parameters, and molecular reactivities.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

On the Use of Satellite Nightlights for Power Outages Prediction

Hurricanes are a dominant disaster in the Caribbean, always causing serious power outages throughout the islands. Hurricane Maria was a prime example, causing unimaginable destruction of the power infrastructure of Puerto Rico (PR). Consequently, one month after the hurricane landfall, approximately 80% of the population was still without power. After an event of such massive destruction, the electric power restoration process progresses very slowly. This timeline can be improved using power outage (PO) forecast models that help identify the vulnerable places before the hurricane landfall. Generally, these models are trained with historical power outages records, associated data on weather conditions, and additional information about the natural and built environments. However, PO records are often difficult to acquire, and, in many instances, the power utility companies may not record them. This study utilizes a satellite-based Visible Infrared Imaging Radiometer Suite (VIIRS) night light data product as a surrogate for the power delivery to predict hurricane-induced PO in areas having limited to nonexistent historical data records. The processed satellite data is then used along with geographic variables, and simulated weather data to formulate machine learning-based algorithms to predict PO for future hurricane events. These models are applied and validated in the context of the PR catastrophic storm, Hurricane Maria.

54 ENVIRONMENTAL SCIENCES↗

Particle Filter Based Inference Testing

The primary intent of PAR-FIT (Particle Filter based Inference Testing) is to provide hard inductive evidence that a machine learning model is capable and proven for an individual test input. By examining training data used to form the underlying model functional correlation, an estimate of the reliability that a model will make the correct prediction can be made. The Sequential Probability Ratio Test is used to derive a qualitative evaluation for reliability based on hypothesis testing. The PAR-FIT framework achieves this by implementing a particle filter and the sequential probability ratio test algorithms on the machine learning model training data to determine relevancy of new individual test samples to the training dataset. The kernel function evaluates the local proximity and density of training data used to derive a prediction outcome. Particles are used to probabilistically determine which training data to evaluate for proximity. For test samples that are within a close proximity to and surrounded by multiple training data points, the evaluated reliability of the prediction is high. For test samples that are anomalies not represented by the training dataset, in low density data clusters, or are far from existing data points, the evaluated reliability is low as insufficient training evidence exists to suggest the model is capable of making the correct prediction. Sequential Probability Ratio Test is further used to determine when a hypothesis on whether a signal can be rejected or accepted for use. The ratio test collects sequence information from the particle filter to test whether the signal is anomalous or normal via hypothesis testing of the underlying distributions.

Chen, Edward [Idaho National Laboratory (INL), Ida↗

DEGAS: Dynamic Exascale Global Address Space Programming Environments

The Dynamic, Exascale Global Address Space programming environment (DEGAS) project will develop the next generation of programming models and runtime systems to meet the challenges of Exascale computing. The Berkeley part of the project concentrated on communication-optimal code generation to optimize speed and energy efficiency by reducing data movement. Our work developed communication lower bounds, and/or communication avoiding algorithms (that either meet the lower bound, or do much less communication than their conventional counterparts) for a variety of algorithms, including linear algebra, machine learning and genomics. The Berkeley part of the project concentrated on communication-optimal code generation to optimize speed and energy efficiency by reducing data movement. Our work developed communication lower bounds, and/or communication avoiding algorithms (that either meet the lower bound, or do much less communication than their conventional counterparts) for a variety of algorithms, including linear algebra, machine learning and genomics.

97 MATHEMATICS AND COMPUTING↗

Modular performance prediction for scientific workflows using Machine Learning

Scientific workflows provide an opportunity for declarative computational experiment design in an intuitive and efficient way. A distributed workflow is typically executed on a variety of resources, and it uses a variety of computational algorithms or tools to achieve the desired outcomes. Such a variety imposes additional complexity in scheduling these workflows on large scale computers. As computation becomes more distributed, insights into expected workload that a workflow presents become critical for effective resource allocation. In this paper, we present a modular framework that leverages Machine Learning for creating precise performance predictions of a workflow. The central idea is to partition a workflow in such a way that makes the task of forecasting each atomic unit manageable and gives us a way to combine the individual predictions efficiently. We recognize a combination of an executable and a specific physical resource as a single module. This gives us a handle to characterize workload and machine power as a single unit of prediction. Overall, our modular technique of creating atomic modules and deployment of longest-path approach to estimate workflow performance, allows the framework to adapt to highly complex nested directed acyclic workflows and scale to new scenarios, since it does not make assumptions of underlying workflow structure. We present performance estimation results of independent workflow modules executed on the XSEDE SDSC Comet cluster using various Machine Learning algorithms. The results provide insights into the behavior and effectiveness of different algorithms in the context of scientific workflow performance prediction.

97 MATHEMATICS AND COMPUTING↗

TU-F-17A-01: BEST IN PHYSICS (JOINT IMAGING-THERAPY) - An Automatic Toolkit for Efficient and Robust Analysis of 4D Respiratory Motion

Purpose: To provide an automatic image analysis toolkit to process thoracic 4-dimensional computed tomography (4DCT) and extract patient-specific motion information to facilitate investigational or clinical use of 4DCT. Methods: We developed an automatic toolkit in MATLAB to overcome the extra workload from the time dimension in 4DCT. This toolkit employs image/signal processing, computer vision, and machine learning methods to visualize, segment, register, and characterize lung 4DCT automatically or interactively. A fully-automated 3D lung segmentation algorithm was designed and 4D lung segmentation was achieved in batch mode. Voxel counting was used to calculate volume variations of the torso, lung and its air component, and local volume changes at the diaphragm and chest wall to characterize breathing pattern. Segmented lung volumes in 12 patients are compared with those from a treatment planning system (TPS). Voxel conversion was introduced from CT# to other physical parameters, such as gravity-induced pressure, to create a secondary 4D image. A demon algorithm was applied in deformable image registration and motion trajectories were extracted automatically. Calculated motion parameters were plotted with various templates. Machine learning algorithms, such as Naive Bayes and random forests, were implemented to study respiratory motion. This toolkit is complementary to and will be integrated with the Computational Environment for Radiotherapy Research (CERR). Results: The automatic 4D image/data processing toolkit provides a platform for analysis of 4D images and datasets. It processes 4D data automatically in batch mode and provides interactive visual verification for manual adjustments. The discrepancy in lung volume calculation between this and the TPS is <±2% and the time saving is by 1–2 orders of magnitude. Conclusion: A framework of 4D toolkit has been developed to analyze thoracic 4DCT automatically or interactively, facilitating both investigational and clinical use. More software tools are under development for automatic analysis of other 4D imaging modalities. This research is in part supported by NIH (U54CA137788/132378) and City Seed FY13(Grant No. 93348-14 01). AY would like to thank MSKCC summer medical student research program supported by National Cancer Institute and hosted by Department of Medical Physics at MSKCC.

60 APPLIED LIFE SCIENCES↗

DOE Express Quantum Computing Application Teams (QCAT FY20 Report)

The QCOR project consists of 4 main research tasks: 1) scientific applications and algorithm development for machine learning (ML) and quantum theories of condensed matter systems and lattice gauge theories; 2) high-level quantum-classical (HLQC) language and domain specific language (DSL) development; 3) compiler and interfaces development for the HLQC language; and 4) hardware-level control, optimization, and algorithms libraries. In the succeeding sections we report on progress towards our research tasks during the 2020 calendar year.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

RADAI: A Large-Scale Realistic Dataset for Radiation Detection Algorithm Development

Open, realistic datasets are essential for developing and benchmarking radiation detection algorithms, yet they remain scarce. The Radiological Anomaly Detection and Identification (RADAI) project was develop to create datasets that meet the training and testing needs for sophisticated radiation detection algorithms. The RADAI dataset is a large-scale synthetic resource that integrates high-fidelity Monte Carlo simulations with realistic urban scenarios to capture both background variability and source signatures. RADAI models construction-material NORM, people and vehicles, urban clutter, and dynamic environmental effects such as cosmic-ray and rain-induced transients, and they provide list-mode detector data with motion and response modeling suitable for algorithm training and evaluation. The RADAI project resulted in three publicly-released complementary datasets together with an online scoring portal for standardized performance assessment and an open software toolkit that supports data access, augmentation, model development, and evaluation. These resources enable reproducible comparisons across methods and promote rigorous studies at the scale required by contemporary machine learning. By grounding algorithm development in realistic, well-documented conditions, RADAI supports progress toward more robust detection, identification, and localization in complex urban environments.

Ghawaly, James M. [Division of Computer Science an↗

Machine Learning technique for isotopic determination of radioisotopes using HPGe γ-ray spectra

γ-ray spectroscopy is a quantitative, non-destructive technique that may be utilized for the identification and quantitative isotopic estimation of radionuclides. Traditional methods of isotopic determination have various challenges that contribute to statistical and systematic uncertainties in the estimated isotopics. Furthermore, these methods typically require numerous pre-processing steps, and have only been rigorously tested in laboratory settings with limited shielding. Here, in this work, we examine the application of a number of machine learning based regression algorithms as alternatives to conventional approaches for analyzing γ-ray spectroscopy data in the Emergency Response arena. This approach not only eliminates many steps in the analysis procedure, and therefore offers potential to reduce this source of systematic uncertainty, but is also shown to offer comparable performance to conventional approaches in the Emergency Response Application.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

HLS4ML Integration with QICK

The QICK (Quantum Instrumentation Control Kit) integration aims to enhance the readout of superconducting qubits by leveraging machine learning (ML) techniques. These techniques offer high accuracy, increased speed, and better state preservation for qubit readouts. The integration process employs neural network algorithms to optimize system performance and achieve high accuracy rates. The QICK board uses an FPGA, allowing for efficient real-time processing and high-performance execution of machine learning algorithms.

Ali, Mohamud↗

Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation

Non-intrusive reduced-order models (ROMs) have recently generated considerable interest for constructing computationally efficient counterparts of nonlinear dynamical systems emerging from various domain sciences. They provide a low-dimensional emulation framework for systems that may be intrinsically high-dimensional. This is accomplished by utilizing a construction algorithm that is purely data-driven. It is no surprise, therefore, that the algorithmic advances of machine learning have led to non-intrusive ROMs with greater accuracy and computational gains. However, in bypassing the utilization of an equation-based evolution, it is often seen that the interpretability of the ROM framework suffers. This becomes more problematic when black-box deep learning methods are used which are notorious for lacking robustness outside the physical regime of the observed data. In this article, we propose the use of a novel latent-space interpolation algorithm based on Gaussian process regression. Notably, this reduced-order evolution of the system is parameterized by control parameters to allow for interpolation in space. The use of this procedure also allows for a continuous interpretation of time which allows for temporal interpolation. The latter aspect provides information, with quantified uncertainty, about full-state evolution at a finer resolution than that utilized for training the ROMs. This research assesses the viability of this algorithm for an advection-dominated system given by the inviscid shallow water equations.

97 MATHEMATICS AND COMPUTING↗

Chapter 7: Predictive Analytics in Future Power Systems: A Panorama and State-of-the-Art of Deep Learning Applications

The challenges surrounding the optimal operation of power systems are growing in various dimensions, due in part to increasingly distributed energy resources and a progression towards large-scale transportation electrification. Currently, the increasing uncertainties associated with both renewable energy generation and demand are largely being managed by increasing operational reserves - potentially at the cost of suboptimal economic conditions - in order to maintain the reliability of the system. This chapter looks at the big picture role of forecasting in power systems from generation to consumption and provides a comprehensive review of traditional approaches for forecasting generation and load in various contexts. This chapter then takes a deep dive into the state-of-the-art machine learning and deep learning approaches for power systems forecasting. Furthermore, a case study of multi-time-horizon solar irradiance forecasting using deep learning is discussed in detail. Smart grids form the backbone of the future interdependent networks. For addressing the challenges associated with the operations of smart grid, development and wide adoption of machine learning and deep learning algorithms capable of producing better forecasting accuracies is urgently needed. Along with exploring the implementation and benefits of these approaches, this chapter also considers the strengths and limitations of deep learning algorithms for power systems forecasting applications. This chapter, thus, provides a panoramic view of state-of-the-art of predictive analytics in power systems in the context of future smart grid operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Toward interactive search in remote sensing imagery

To move from data to information in almost all science and defense applications requires a human-in-the-loop to validate information products, resolve inconsistencies, and account for incomplete and potentially deceptive sources of information. This is a key motivation for visual analytics which aims to develop techniques that complement and empower human users. By contrast, the vast majority of algorithms developed in machine learning aim to replace human users in data exploitation. In this paper we describe a recently introduced machine learning problem, called rare category detection, which may be a better match to visual analytic environments. We describe a new design criteria for this problem, and present comparisons to existing techniques with both synthetic and real-world datasets. We conclude by describing an application in broad-area search of remote sensing imagery.

99 GENERAL AND MISCELLANEOUS↗

Image feature extraction and galaxy classification: a novel and efficient approach with automated machine learning

ABSTRACT In this work, we explore the possibility of applying machine learning methods designed for 1D problems to the task of galaxy image classification. The algorithms used for image classification typically rely on multiple costly steps, such as the point spread function deconvolution and the training and application of complex Convolutional Neural Networks of thousands or even millions of parameters. In our approach, we extract features from the galaxy images by analysing the elliptical isophotes in their light distribution and collect the information in a sequence. The sequences obtained with this method present definite features allowing a direct distinction between galaxy types. Then, we train and classify the sequences with machine learning algorithms, designed through the platform Modulos AutoML. As a demonstration of this method, we use the second public release of the Dark Energy Survey (DES DR2). We show that we are able to successfully distinguish between early-type and late-type galaxies, for images with signal-to-noise ratio greater than 300. This yields an accuracy of $86{{\ \rm per\ cent}}$ for the early-type galaxies and $93{{\ \rm per\ cent}}$ for the late-type galaxies, which is on par with most contemporary automated image classification approaches. The data dimensionality reduction of our novel method implies a significant lowering in computational cost of classification. In the perspective of future data sets obtained with e.g. Euclid and the Vera Rubin Observatory, this work represents a path towards using a well-tested and widely used platform from industry in efficiently tackling galaxy classification problems at the peta-byte scale.

79 ASTRONOMY AND ASTROPHYSICS↗

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↗

Modular machine learning-based elastoplasticity: Generalization in the context of limited data

The development of highly accurate constitutive models for materials that undergo path-dependent processes continues to be a complex challenge in computational solid mechanics. Challenges arise both in considering the appropriate model assumptions and from the viewpoint of data availability, verification, and validation. Recently, data-driven modeling approaches have been proposed that aim to establish stress-evolution laws that avoid user-chosen functional forms by relying on machine learning representations and algorithms. However, these approaches not only require a significant amount of data but also need data that probes the full stress space with a variety of complex loading paths. Furthermore, they rarely enforce all necessary thermodynamic principles as hard constraints. Hence, they are in particular not suitable for low-data or limited-data regimes, where the first arises from the cost of obtaining the data and the latter from the experimental limitations of obtaining labeled data, which is commonly the case in engineering applications. In this work, we discuss a hybrid framework that can work on a variable amount of data by relying on the modularity of the elastoplasticity formulation where each component of the model can be chosen to be either a classical phenomenological or a data-driven model depending on the amount of available information and the complexity of the response. The method is tested on synthetic uniaxial data coming from simulations as well as cyclic experimental data for structural materials. The discovered material models are found to not only interpolate well but also allow for accurate extrapolation in a thermodynamically consistent manner far outside the domain of the training data. This ability to extrapolate from limited data was the main reason for the early and continued success of phenomenological models and the main shortcoming in machine learning-enabled constitutive modeling approaches. Training aspects and details of the implementation of these models into Finite Element simulations are discussed and analyzed.

42 ENGINEERING↗