Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed 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 1,369 records · Page 76
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale

Sparse matrix-matrix multiplication (SpGEMM) is a widely used kernel in various graph, scientific computing and machine learning algorithms. In this paper, we consider SpGEMMs performed on hundreds of thousands of processors generating trillions of nonzeros in the output matrix. Distributed SpGEMM at this extreme scale faces two key challenges: (1) high communication cost and (2) inadequate memory to generate the output. Furthermore, we address these challenges with an integrated communication-avoiding and memory-constrained SpGEMM algorithm that scales to 262,144 cores (more than 1 million hardware threads) and can multiply sparse matrices of any size as long as inputs and a fraction of output fit in the aggregated memory. As we go from 16,384 cores to 262,144 cores on a Cray XC40 supercomputer, the new SpGEMM algorithm runs 10x faster when multiplying large-scale protein-similarity matrices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Performance-Aligned LLMs for Generating Fast HPC Code

Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor performance can originate from disparate sources and be difficult to diagnose. Recent years have seen a multitude of work that use large language models (LLMs) to assist in software development tasks. However, these tools are trained to model the distribution of code as text, and are not specifically designed to understand performance aspects of code. In this work, we introduce a reinforcement learning based methodology to align the outputs of code LLMs with performance. This allows us to build upon the current code modeling capabilities of LLMs and extend them to generate better performing code. Here, we demonstrate that our fine-tuned model improves the expected speedup of generated code over base models for a set of benchmark tasks from 0.9 to 1.6 for serial code and 1.9 to 4.5 for OpenMP parallel code.

Computer science↗
DOE OSTI2017

A Data-Driven Methodology for Probabilistic Wind Power Ramp Forecasting

With increasing wind penetration, wind power ramps (WPRs) are currently drawing great attention to balancing authorities, since these wind ramps largely affect power system operations. To help better manage and dispatch the wind power, this paper develops a data-driven probabilistic WPR forecasting (p-WPRF) method based on a large number of simulated scenarios. A machine learning technique is first adopted to forecast the basic wind power forecasting scenario and produce the historical forecasting errors. To accurately model the distribution of wind power forecasting errors, a generalized Gaussian mixture model is developed and the cumulative distribution function (CDF) is also analytically deduced. The inverse transform method based on the CDF is used to generate a large number of forecasting error scenarios. An optimized swinging door algorithm is adopted to extract all the WPRs from the complete set of wind power forecasting scenarios. The p-WPRF is generated based on all generated scenarios under different weather and time conditions. Numerical simulations on publicly available wind power data show that the developed p-WPRF method can predict WPRs with a high level of reliability and accuracy.

17 WIND ENERGY↗
DOE OSTI2019

ErrFilter

ErrFilter is a tool that allows an analyst to explore data by defining simple Boolean filters on data. The tool also allows the user to sort the results by any attribute. The user sees both the distribution of filtered data as well as selected examples. The tool was designed to be applied generally to multivariate data associated with machine learning models.

Arendt, Dustin↗
DOE OSTI2024

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling

Recent advances in differentiable modeling, a genre of physics-informed machine learning that trains neural networks (NNs) together with process-based equations, have shown promise in enhancing hydrological models' accuracy, interpretability, and knowledge-discovery potential. Current differentiable models are efficient for NN-based parameter regionalization, but the simple explicit numerical schemes paired with sequential calculations (operator splitting) can incur numerical errors whose impacts on models' representation power and learned parameters are not clear. Implicit schemes, however, cannot rely on automatic differentiation to calculate gradients due to potential issues of gradient vanishing and memory demand. Here we propose a “discretize-then-optimize” adjoint method to enable differentiable implicit numerical schemes for the first time for large-scale hydrological modeling. The adjoint model demonstrates comprehensively improved performance, with Kling–Gupta efficiency coefficients, peak-flow and low-flow metrics, and evapotranspiration that moderately surpass the already-competitive explicit model. Therefore, the previous sequential-calculation approach had a detrimental impact on the model's ability to represent hydrological dynamics. Furthermore, with a structural update that describes capillary rise, the adjoint model can better describe baseflow in arid regions and also produce low flows that outperform even pure machine learning methods such as long short-term memory networks. The adjoint model rectified some parameter distortions but did not alter spatial parameter distributions, demonstrating the robustness of regionalized parameterization. Despite higher computational expenses and modest improvements, the adjoint model's success removes the barrier for complex implicit schemes to enrich differentiable modeling in hydrology.

58 GEOSCIENCES↗
DOE OSTI2019

The dynamic conformational landscape of the protein methyltransferase SETD8

Elucidating the conformational heterogeneity of proteins is essential for understanding protein function and developing exogenous ligands. With the rapid development of experimental and computational methods, it is of great interest to integrate these approaches to illuminate the conformational landscapes of target proteins. SETD8 is a protein lysine methyltransferase (PKMT), which functions in vivo via the methylation of histone and nonhistone targets. Utilizing covalent inhibitors and depleting native ligands to trap hidden conformational states, we obtained diverse X-ray structures of SETD8. These structures were used to seed distributed atomistic molecular dynamics simulations that generated a total of six milliseconds of trajectory data. Markov state models, built via an automated machine learning approach and corroborated experimentally, reveal how slow conformational motions and conformational states are relevant to catalysis. These findings provide molecular insight on enzymatic catalysis and allosteric mechanisms of a PKMT via its detailed conformational landscape.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Physics-assisted Latent Space Dynamics Learning for Stiff Collisional-radiative Models

Collisional-radiative (CR) models describe the atomic processes in a plasma by tracking the population density in the ground and excited states for each charge state of the atom/ion. These models predict important plasma properties such as charge state distributions and radiative emissivity and opacity. Accurate descriptions of the CR balance of the plasma are essential in fusion whole device modeling, especially when significant impurities are introduced into the plasmas. In an integrated fusion plasma and CR simulation, a CR model, which is a high-dimensional stiff ODE, needs to be solved on each grid point in the configuration space, and can overwhelm the overall computational cost. In this work, we propose a machine-learning-based method that discovers a latent space and learns its corresponding latent dynamics, which can capture the essential physics to make accurate predictions at much lower online computational cost. The proposed approach is physics-assisted, due to its combination of a physical latent space and a data-driven latent space. It has been demonstrated that the proposed architecture can predict both the full-order CR dynamics and a physical quantity of interest accurately.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Learning earthquake ground motions via conditional generative modeling

Predicting high-fidelity ground motions for future earthquakes is crucial for seismic hazard assessment and infrastructure resilience. Conventional empirical simulations suffer from sparse sensor distribution and geographically localized earthquake locations, while physics-based methods are computationally intensive and require accurate representations of Earth structures and earthquake sources. We propose an artificial intelligence (AI) spectrogram generator, Conditional Generative Modeling for Ground Motion (CGM-GM). CGM-GM leverages earthquake magnitudes and geographic coordinates of earthquakes and sensors as inputs, when postprocessed with phase information, capturing spatially continuous Fourier amplitude spectra (FAS) as well as properties such as P and S arrivals, and waveform durations, without explicit physics constraints. This is achieved through a probabilistic autoencoder that extracts latent distributions in the time-frequency domain and variational sequential models for prior and posterior distributions. We evaluate the performance of CGM-GM using small-magnitude earthquake records from the San Francisco Bay Area, a region with high seismic risks. Here, we report that CGM-GM demonstrates potential for complementing physics-based simulations and non-ergodic empirical ground motion models, as well as shows promise in seismology and beyond.

geophysics↗
DOE OSTI2025

Multi-fidelity is the new annealing: Gradient-free learning of posterior densities via transport maps

To tackle concentrated, multi-modal Bayesian inference problems, we propose using an annealed importance sampling procedure. To do this, we form a sequence of annealed distributions and employ transport maps to act as a surrogate of each distribution. This process is demonstrated on a few examples, favorably showing its potential for efficiently parallelizing the process of PDE evaluations and allowing for surrogates that we can sample from exactly.

van Bloemen Waanders, Bart G [Sandia National Labo↗
DOE OSTI2024

Deep Reinforcement Learning for Microgrid Cost Optimization Considering Load Flexibility

This paper proposes a novel Soft-Actor-Critic (SAC) based Deep Reinforcement Learning (DRL) method for optimizing the cost of microgrid operation by leveraging load flexibility. The proposed SAC-DRL method is designed to coordinate the control of distributed energy resources (DERs) and flexible load, addressing practical energy billing formation by power distribution utilities. Key contributions include an innovative reward function to mitigate sparse reward challenges and a mixed control strategy for discrete and continuous variables, ensuring radial network topology and minimizing power loss. We evaluate the proposed method on the model of a real microgrid located in Southern California, U.S.. The SAC-DRL model is tested to demonstrate its efficacy in reducing grid dependence, optimizing resource use, and minimizing costs. The results highlight the potential of DRL in modern energy systems, offering a sustainable and economically efficient solution for energy management in microgrids.

deep reinforcement learning↗
DOE OSTI2026

Inverse Mapping of the Collision Kernel and Wall Flux Scaling in a Tall Convection‐Cloud Chamber Using Local Sensors and Knowledge‐Informed Deep Learning

Droplet collision–coalescence is a crucial process in cloud physics, but accurately representing this process under different dynamical conditions remains challenging. A proposed future convective‐cloud chamber aims to investigate this key process, but the method for observing it remains unclear, even though it is theoretically established that collision‐coalescence will occur. This study serves as a proof‐of‐concept demonstration of how knowledge‐informed deep learning, combined with measurement data from local sensors in the chamber, can be used to estimate the collision kernels, which determine how the droplet size distribution evolves during collision‐coalescence. In addition to estimating the collision kernel, we also address wall fluxes, another uncertain but important process that acts as a source of heat and moisture in the chamber. Ensemble runs of large‐eddy simulations are conducted by scaling the wall fluxes and the collision kernel, while the measured flow and cloud properties are used as inputs for a neural network. Results indicate that this approach successfully maps the scaling of wall fluxes and the collision kernel with biases of approximately 1% or less relative to the range of the target data. This proof‐of‐concept lays the groundwork for future applications; when the real measurements are available, real sensor data combined with the trained model presented in this work will enable estimation of the actual wall fluxes and collision kernel.

cloud chamber↗
DOE OSTI2022

Smart detection of indoor occupant thermal state via infrared thermography, computer vision, and machine learning

The ability to measure occupants’ thermal state in real time will enable major advances in the control of air conditioning systems. This study proposes predicting occupant thermal state by a combination of infrared thermography, computer vision, and machine learning. The approach (1) uses cheek, nose, and hand temperatures because they are least subject to blockage by hair, glasses, and clothing; (2) measures the distribution of skin temperatures within geometrically defined sub-areas of the face and hand; and (3) uses temperature differences within and between these areas to eliminate the effects of calibration drift that are unavoidable in thermal infrared (TIR) cameras. Two series of tests were conducted, respectively in an outdoor carport and an indoor environmental chamber, collecting a total of 48,422 sets of cheek, nose, and hand skin temperatures using a TIR camera and computer-vision technology, coupled with 715 subjective responses of thermal sensations. To predict occupant thermal state, Random Forest classification models were built using either absolute skin temperatures (the maximum and median temperatures of cheek and hand segments, and the temperature of the central spot on the nose), or intra- and inter-segment temperature differences of cheeks, hands, and nose. These measurements were found to accurately predict occupant thermal state. Using the maximum and median temperatures for cheek and nose, or for cheek and hand, predicts thermal state with an accuracy of 92–96%. In conclusion, using only the intra- and inter-segment temperature differences from cheek and nose is 83% accurate; adding the hand temperature differences increases the accuracy to 96%.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

A biomass map of the Brazilian Amazon from multisource remote sensing

The Amazon Forest, the largest contiguous tropical forest in the world, stores a significant fraction of the carbon on land. Changes in climate and land use affect total carbon stocks, making it critical to continuously update and revise the best estimates for the region, particularly considering changes in forest dynamics. Forest inventory data cover only a tiny fraction of the Amazon region, and the coverage is not sufficient to ensure reliable data interpolation and validation. This paper presents a new forest above-ground biomass map for the Brazilian Amazon and the associated uncertainty both with a resolution of 250 meters and baseline for the satellite dataset the year of 2016 (i.e., the year of the satellite observation). A significant increase in data availability from forest inventories and remote sensing has enabled progress towards high-resolution biomass estimates. This work uses the largest airborne LiDAR database ever collected in the Amazon, mapping 360,000 km 2 through transects distributed in all vegetation categories in the region. The map uses airborne laser scanning (ALS) data calibrated by field forest inventories that are extrapolated to the region using a machine learning approach with inputs from Synthetic Aperture Radar (PALSAR), vegetation indices obtained from the Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite, and precipitation information from the Tropical Rainfall Measuring Mission (TRMM). A total of 174 field inventories geolocated using a Differential Global Positioning System (DGPS) were used to validate the biomass estimations. The experimental design allowed for a comprehensive representation of several vegetation types, producing an above-ground biomass map varying from a maximum value of 518 Mg ha -1 , a mean of 174 Mg ha -1 , and a standard deviation of 102 Mg ha -1 . This unique dataset enabled a better representation of the regional distribution of the forest biomass and structure, providing further studies and critical information for decision-making concerning forest conservation, planning, carbon emissions estimate, and mechanisms for supporting carbon emissions reductions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Projection pursuit adaptation on polynomial chaos expansions

Here, the present work addresses the issue of accurate stochastic approximations in high-dimensional parametric space using tools from uncertainty quantification (UQ). The basis adaptation method and its accelerated algorithm in polynomial chaos expansions (PCE) were recently proposed to construct low-dimensional approximations adapted to specific quantities of interest (QoI). The present paper addresses one difficulty with these adaptations, namely their reliance on quadrature point sampling, which limits the reusability of potentially expensive samples. Projection pursuit (PP) is a statistical tool to find the “interesting” projections in high-dimensional data and thus bypass the curse-of-dimensionality. In the present work, we combine the fundamental ideas of basis adaptation and projection pursuit regression (PPR) to propose a novel method to simultaneously learn the optimal low-dimensional spaces and PCE representation from given data. While this projection pursuit adaptation (PPA) can be entirely data-driven, the constructed approximation exhibits mean-square convergence to the solution of an underlying governing equation and thus captures the supports and probability distributions associated with the physics constraints. The proposed approach is demonstrated on a borehole problem and a structural dynamics problem, demonstrating the versatility of the method and its ability to discover low-dimensional manifolds with high accuracy with limited data. In addition, the method can learn surrogate models for different quantities of interest while reusing the same data set.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

AI-Driven Smart Community Control for Accelerating PV Adoption and Enhancing Grid Resilience

Rapid deployment of residential photovoltaic (PV) systems helps decarbonize our electricity supplies, but under certain circumstances, high-penetration PV may pose challenges to the electrical distribution grid. In a project funded by the U.S. Department of Energy's Solar Energy Technologies Office and Building Technologies Office, the National Renewable Energy Laboratory and its partners studied how flexible building loads and battery storage, when coordinated at home-level and community-level scales, can be used to address those challenges and enhance grid resilience. In this webinar, we will discuss the methodology, simulation and field pilot results, insights from partners, and lessons learned from the project.

artificial intelligence↗
DOE OSTI2023

Advanced characterization-informed machine learning framework and quantitative insight to irradiated annular U-10Zr metallic fuels

Abstract U-10Zr Metal fuel is a promising nuclear fuel candidate for next-generation sodium-cooled fast spectrum reactors. Since the Experimental Breeder Reactor-II in the late 1960s, researchers accumulated a considerable amount of experience and knowledge on fuel performance at the engineering scale. However, a mechanistic understanding of fuel microstructure evolution and property degradation during in-reactor irradiation is still missing due to a lack of appropriate tools for rapid fuel microstructure assessment and property prediction based on post irradiation examination. This paper proposed a machine learning enabled workflow, coupled with domain knowledge and large dataset collected from advanced post-irradiation examination microscopies, to provide rapid and quantified assessments of the microstructure in two reactor irradiated prototypical annular metal fuels. Specifically, this paper revealed the distribution of Zr-bearing secondary phases and constitutional redistribution across different radial locations. Additionally, the ratios of seven different microstructures at various locations along the temperature gradient were quantified. Moreover, the distributions of fission gas pores on two types of U-10Zr annular fuels were quantitatively compared.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Detecting Anomalies for Fire Prevention in Distribution Systems: Challenges and Analytical Techniques

Electric utilities in California have historically been linked to up to 10% of wildfires. To mitigate this risk, Southern California Edison has invested significantly in wildfire prevention strategies, including undergrounding cables and enhancing equipment inspections. This article explores a novel approach to fire prevention by detecting anomalies in the distribution system that may indicate potential fire hazards. The focus is on identifying arcing conditions through high-resolution point-on-wave (POW) measurements. Arcing, a precursor to fires, is challenging to detect due to its subtle transients and complex system topology. The article discusses the use of advanced signal processing and machine learning techniques, such as spectral correlation function and discrete wavelet transform, to extract features from POW data and accurately identify arcing events. The study demonstrates a high accuracy rate in detecting arcing, paving the way for improved fire prevention measures in electric distribution systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Application of Advanced Metering Infrastructure Data to Advanced Utility System Operations: Cooperative Research and Development, CRADA Number CRD-17-00712 (Final Report)

The primary objective of the proposed project is to evaluate the capabilities of Advanced Metering Infrastructure (AMI) based controls for grid operations. This includes monitoring and control at the secondary transformer level using existing AMI infrastructure. In addition, some of the challenges of using a model-less control will also be identified. The lessons learned will be disseminated to other utilities around the country through peer-reviewed publications with the consent of SDG&E. The scope of the work includes using data from SDG&E's existing AMI infrastructure and working with third party vendors selected by SDG&E. The grid edge monitoring systems and controls provided by the selected vendors will perform grid operations using AMI data. The National Renewable Energy Laboratory (NREL) will perform a software and controller-based evaluation of the grid edge controller, intelligent devices and sensors, at the Energy System Integration Facility (ESIF) laboratory.

24 POWER TRANSMISSION AND DISTRIBUTION↗