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 1,639 records · Page 91

Star–Galaxy Image Separation with Computationally Efficient Gaussian Process Classification

Abstract We introduce a novel method for discerning optical telescope images of stars from those of galaxies using Gaussian processes (GPs). Although applications of GPs often struggle in high-dimensional data modalities such as optical image classification, we show that a low-dimensional embedding of images into a metric space defined by the principal components of the data suffices to produce high-quality predictions from real large-scale survey data. We develop a novel method of GP classification hyperparameter training that scales approximately linearly in the number of image observations, which allows for application of GP models to large-size Hyper Suprime-Cam Subaru Strategic Program data. In our experiments, we evaluate the performance of a principal component analysis embedded GP predictive model against other machine-learning algorithms, including a convolutional neural network and an image photometric morphology discriminator. Our analysis shows that our methods compare favorably with current methods in optical image classification while producing posterior distributions from the GP regression that can be used to quantify object classification uncertainty. We further describe how classification uncertainty can be used to efficiently parse large-scale survey imaging data to produce high-confidence object catalogs.

79 ASTRONOMY AND ASTROPHYSICS↗

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Deep learning has surged in popularity and proven to be effective for various artificial intelligence applications including information extraction from cancer pathology reports. Since word representation is a core unit that enables deep learning algorithms to understand words and be able to perform NLP, this representation must include as much information as possible to help these algorithms achieve high classification performance. Therefore, in this work in addition to the distributional information of words in large sized corpora, we use UMLS vocabulary resources to enrich the vector space representation of words with the semantic relations between words. These resources provide many terminologies pertaining to cancer. The refined word embeddings are used with a convolutional neural (CNN) model to extract four data elements from cancer pathology reports; ICD-O-3 tumor topography codes, tumor laterality, behavior, and histological grade. We observed that using UMLS vocabulary resources to enrich word embeddings of CNN models consistently outperformed CNN models without pre-training word embeddings and even with pre-trained word embeddings on a domain specific corpus across all four tasks. The results show marginal improvement on the laterality task, but a significant improvement on the other tasks, especially for the macro-f score. Specifically, the improvements are 3%, 13%, and 15% for tumor site, histological grade, and behavior tasks, respectively. This approach is encouraging to enrich word embeddings with more clinical data resources to be used for information abstraction tasks from clinical pathology reports.

Alawad, Mohammed↗

Optimizing the shape of photometric redshift distributions with clustering cross-correlations

We present an optimization method for the assignment of photometric galaxies to a chosen set of redshift bins. This is achieved by combining simulated annealing, an optimization algorithm inspired by solid-state physics, with an unsupervised machine learning method, a self-organizing map (SOM) of the observed colours of galaxies. Starting with a sample of galaxies that is divided into redshift bins based on a photometric redshift point estimate, the simulated annealing algorithm repeatedly reassigns SOM-selected subsamples of galaxies, which are close in colour, to alternative redshift bins. We optimize the clustering cross-correlation signal between photometric galaxies and a reference sample of galaxies with well-calibrated redshifts. Depending on the effect on the clustering signal, the reassignment is either accepted or rejected. By dynamically increasing the resolution of the SOM, the algorithm eventually converges to a solution that minimizes the number of mismatched galaxies in each tomographic redshift bin and thus improves the compactness of their corresponding redshift distribution. This method is demonstrated on the synthetic Legacy Survey of Space and Time cosmoDC2 catalogue. We find a significant decrease in the fraction of catastrophic outliers in the redshift distribution in all tomographic bins, most notably in the highest redshift bin with a decrease in the outlier fraction from 57 percent to 16 percent.

79 ASTRONOMY AND ASTROPHYSICS↗

DASEventNet: AI‐Based Microseismic Detection on Distributed Acoustic Sensing Data From the Utah FORGE Well 16A (78)‐32 Hydraulic Stimulation

Abstract Distributed acoustic sensing (DAS) has emerged as a promising seismic technology for monitoring microearthquakes (MEQs) with high spatial resolution. Efficient algorithms are needed for processing large DAS data volumes. This study introduces a deep learning (DL) model based on a Residual Convolutional Neural Network (ResNet) for detecting MEQs using DAS data, named as DASEventNet. The test data were collected from the Utah FORGE 16A (78)‐32 hydraulic stimulation experiments conducted in April 2022. The DASEventNet model achieves a remarkable accuracy of 100% when discriminating MEQs from noise in the raw test set of 260 examples. Surprisingly, the model identified weak MEQ signatures that have been manually categorized as noise. The decision‐making process with the model is decoded by the classic activation map, which illuminates learning features of the DASEventNet model. These features provide clear illustrations of weak MEQs and varied noise types. Finally, we apply the trained model to the entire period (∼7 days) of continuous DAS recordings and find that it discovers >5,700 new MEQs, previously unregistered in the public Silixa DAS catalog. The DASEventNet model significantly outperforms the traditional seismic method Short‐Term Average/Long‐Term Average (STA/LTA), which detected only 1,307 MEQs. The DASEventNet detection threshold is M w −1.80 compared to the minimum magnitude of M w −1.14 detected by STA/LTA. The spatiotemporal distribution of the newly identified MEQs defines an extensive stimulation zone and more accurately characterizes fracture geometry. Our results highlight the potential of DL for long‐term, real‐time microseismic monitoring that can improve enhanced geothermal systems and other activities that include subsurface hydraulic fracturing.

15 GEOTHERMAL ENERGY↗

FatMan vs. LittleBoy: Scaling Up Linear Algebraic Operations in Scale-Out Data Platforms

Linear algebraic operations such as matrix manipulations form the kernel of many machine learning and other crucial algorithms. Scaling up as well as scaling out such algorithms are highly desirable to enable efficient processing over millions of data points. To this end, we present a matrix manipulation approach to effectively scale-up each node in a scale-out data parallel platform such as Apache Spark. Specifically, we enable hardware acceleration for matrix multiplications in a distributed Spark setup without user intervention. Our approach supports both dense and sparse distributed matrices, and provides flexible control of acceleration by matrix density. We demonstrate the benefit of our approach for generalized matrix multiplication operations over large matrices with up to four billion elements. To connect the effectiveness of our approach with machine learning applications, we performed Gramian matrix computation via generalized matrix multiplications. Our experiments show that our approach achieves more than 2× performance speed-up, and up to 96.1% computation improvement, compared to a state of the art Spark MLlib for dense matrices.

97 MATHEMATICS AND COMPUTING↗

FatMan vs. LittleBoy: Scaling up Linear Algebraic Operations in Scale-out Data Platforms

Linear algebraic operations such as matrix manipulations form the kernel of many machine learning and other crucial algorithms. Scaling up as well as scaling out such algorithms are highly desirable to enable efficient processing over millions of data points. To this end, we present a matrix manipulation approach to effectively scale-up each node in a scale-out data parallel platform such as Apache Spark. Specifically, we enable hardware acceleration for matrix multiplications in a distributed Spark setup without user intervention. Our approach supports both dense and sparse distributed matrices, and provides flexible control of acceleration by matrix density. We demonstrate the benefit of our approach for generalized matrix multiplication operations over large matrices with up to four billion elements. To connect the effectiveness of our approach with machine learning applications, we performed Gramian matrix computation via generalized matrix multiplications. Our experiments show that our approach achieves more than 2x performance speed-up, and up to 96.1% computation improvement, compared to a state of the art Spark MLlib for dense matrices.

Lim, Seung-Hwan↗

Collaboration and Negotiation

Collaboration and Negotiation is a critical high-level function of an Autonomous Intelligent Cyber-Defense Agent (AICA) that enables communication among agents, central cyber C2, and human operators. Maintaining the Confidentiality, Integrity, and Availability (CIA) triad while achieving mission goals requires stealthy AICA agents to exercise: 1) minimal communication as needed for avoiding detection, 2) verification of information received with possibly limited resources, and 3) active learning during operations to address dynamic conditions. Moreover, negotiations to jointly identify and execute a Course of Action (COA) solution will require building consensus under distributed and/or decentralized multiagent settings with information uncertainties. This chapter presents algorithmic approaches for enabling the collaboration and negotiation function. Strengths and limitations of potential techniques are identified, and a representative example is illustrated. Recommendations for future development are also discussed.

Chatterjee, Samrat↗

A Cellular Automaton Simulation for Predicting Phase Evolution in Solid-State Reactions

New computational tools for solid-state synthesis recipe design are needed in order to accelerate the experimental realization of novel functional materials proposed by high-throughput materials discovery workflows. This work contributes a cellular automaton simulation framework for predicting the time-dependent evolution of intermediate and product phases during solid-state reactions as a function of precursor choice and amount, reaction atmosphere, and heating profile. The simulation captures the effects of reactant particle spatial distribution, particle melting, and reaction atmosphere. Reaction rates based on rudimentary kinetics are estimated using density functional theory data from the Materials Project and machine learning estimators for the melting point and the vibrational entropy component of the Gibbs free energy. The resulting simulation framework allows for the prediction of the likely outcome of a reaction recipe before any experiments are performed. We analyze five experimental solid-state recipes for BaTiO 3 , CaZrN 2 , and YMnO 3 found in the literature to illustrate the performance of the model in capturing reaction selectivity and reaction pathways as a function of temperature and precursor choice. This simulation framework offers an easier way to optimize existing recipes, aid in the identification of intermediates, and design effective recipes for yet unrealized inorganic solids in silico .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Modeling the Behavior of Complex Aqueous Electrolytes Using Machine Learning Interatomic Potentials: The Case of Sodium Sulfate

Understanding the structure and thermodynamics of solvated ions is essential for advancing applications in electrochemistry, water treatment, and energy storage. While ab initio molecular dynamics methods are highly accurate, they are limited by short accessible time and length scales whereas classical force fields struggle with accuracy. Herein, we explore the structure and thermodynamics of complex monovalent-divalent ion pairs using Na 2 SO 4 (aq) as a case study by applying a machine learning interatomic potential (MLIP) trained on density functional theory (DFT) data. Our MLIP-based approach reproduces key bulk properties such as density and radial distribution functions of water. We provide the hydration structure of the sodium and sulfate ions in the 0.1–2 M concentration range and the one-dimensional and two-dimensional potentials of mean force for the sodium–sulfate ion pairing at the low concentration limit (0.1 M), which are inaccessible to DFT. At low concentrations, the sulfate ion is strongly solvated, leading to the stabilization of solvent-separated ion pairs over contact ion pairs. Minimum energy pathway analysis revealed that coordinating two sodium ions with a sulfate ion is a multistep process whereby the sodium ions coordinate to the sulfate ion sequentially. Finally, we demonstrate that MLIPs allow the study of solvated ions beyond simple monovalent pairs with DFT-level accuracy in their low concentration limit (0.1 M) via statistically converged properties from ns-long simulations.

anions↗

Thinking Bayesian for plasma physicists

Bayesian statistics offers a powerful technique for plasma physicists to infer knowledge from the heterogeneous data types encountered. To explain this power, a simple example, Gaussian Process Regression, and the application of Bayesian statistics to inverse problems are explained. The likelihood is the key distribution because it contains the data model, or theoretic predictions, of the desired quantities. By using prior knowledge, the distribution of the inferred quantities of interest based on the data given can be inferred. Because it is a distribution of inferred quantities given the data and not a single prediction, uncertainty quantification is a natural consequence of Bayesian statistics. The benefits of machine learning in developing surrogate models for solving inverse problems are discussed, as well as progress in quantitatively understanding the errors that such a model introduces.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Software-Hardware Co-design of Heterogeneous SmartNIC System for Recommendation Models Inference and Training

Deep Learning Recommendation Models (DLRMs) are critical applications in various domains and have evolved as one of the single largest machine learning applications. Trillions of DLRM parameters exceed the on-chip memory capacity of GPUs. Large-scale multi-node systems are required for distributed DLRM inference and training, which suffer from the all-to-all communication bottleneck, mainly limiting the scalability of ever-growing DLRMs. In recent years, SmartNICs have evolved with coupled computation and communication capabilities providing opportunities for a powerful heterogeneous device in the system. However, there isn't such a distributed system that fully leverages the abundant smartNIC resources that resolve the scalability issue of DLRMs. In this work, we proposed a software-hardware co-design of a heterogeneous smartNIC system that resolves the communication bottleneck of distributed DLRMs, mitigates the memory bandwidth pressure, and improves computation efficiency. We provide a set of smartNIC designs of cache systems (including local cache and remote cache) and smartNIC computation kernels which reduce data movement, relieve memory lookup intensity, and improve the GPU's computation efficiency. In addition, we propose a graph algorithm that improves the data locality of queries within batches which optimizes the overall system performance with higher data reuse. Our evaluation shows that our system achieves 2.1x latency speedup for inference and 1.6x throughput speedup for training.

Guo, Anqi↗

BULKI-Store v0.3.2

BULKI-Store is a distributed object storage system optimized for high-performance computing environments. Built with a Rust core and Python bindings, it efficiently manages scientific and machine learning datasets across HPC clusters. The system employs a client-server architecture with MPI integration, enabling seamless scaling on supercomputers like Perlmutter. BULKI-Store's object-oriented approach provides intuitive data organization with rich metadata support, contrasting with traditional file-based solutions. Key optimizations include selective checkpoint loading, unified checkpoint files, and object chunking for large data transfers. For machine learning workloads, BULKI-Store offers advantages through fine-grained access patterns, dynamic data sharing between training instances, and reduced memory pressure. Memory management features include strategic Python GC calls, minimized data copies, and batch processing capabilities. The system leverages Rayon's thread pool for asynchronous data prefetching and supports multiple CPU architectures (ARM64, x86, AMD, RISC-V). By combining performance optimizations with developer-friendly APIs, BULKI-Store addresses the complex data management challenges of modern HPC applications while maintaining compatibility across heterogeneous computing environments.

Zhang, Wei [Lawrence Berkeley National Laboratory ↗

Machine Learning Enabled Process Optimization for Pharmacologically Relevant Dependent Variables: CRADA Final Report

ABPDU staff worked with Teselagen to provide expertise and perform literature searches for therapeutic carrying strains to maximize fermentation parameters for Teselagen's machine learning platform. The goal was to overcome the COVID-19 crisis and plan for a future where molecules can be detected, diagnosed, built, manufactured, and distributed within months.

59 BASIC BIOLOGICAL SCIENCES↗

Product Distribution Theory for Control of Multi-Agent Systems

Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS's). First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (probability distribution of) the joint stare of the agents. Accordingly we can consider a team game in which the shared utility is a performance measure of the behavior of the MAS. For such a scenario the game is at equilibrium - the Lagrangian is optimized - when the joint distribution of the agents optimizes the system's expected performance. One common way to find that equilibrium is to have each agent run a reinforcement learning algorithm. Here we investigate the alternative of exploiting PD theory to run gradient descent on the Lagrangian. We present computer experiments validating some of the predictions of PD theory for how best to do that gradient descent. We also demonstrate how PD theory can improve performance even when we are not allowed to rerun the MAS from different initial conditions, a requirement implicit in some previous work.

Lee, Chia Fan↗

Shuttle Case Study Collection Website Development

As a continuation from summer 2012, the Shuttle Case Study Collection has been developed using lessons learned documented by NASA engineers, analysts, and contractors. Decades of information related to processing and launching the Space Shuttle is gathered into a single database to provide educators with an alternative means to teach real-world engineering processes. The goal is to provide additional engineering materials that enhance critical thinking, decision making, and problem solving skills. During this second phase of the project, the Shuttle Case Study Collection website was developed. Extensive HTML coding to link downloadable documents, videos, and images was required, as was training to learn NASA's Content Management System (CMS) for website design. As the final stage of the collection development, the website is designed to allow for distribution of information to the public as well as for case study report submissions from other educators online.

Ransom, Khadijah S.↗

Noble Gases in Samples Returned From Asteroids Ryugu and Bennu

Introduction: The asteroid sample return missions, JAXA’s Hayabusa2 [1] and NASA’s OSIRIS-REx [2], fromC-rich asteroids Ryugu and Bennu offer unique opportunities to sample pristine early solar system material, unaffected by terrestrial weathering and contamination, and with a known geological context. The comparison with most primi-tive members of carbonaceous –and inner solar system ordinary and enstatite– chondrite classes allows us to (i) assess the variation (or the lack of thereof) of the distribution of the most volatile elements throughout the entire early solar system, (ii) determine the effects of parent body thermal and aqueous alteration, and (iii) learn about the dynamic evolution and history of the various parent bodies, as sampled by both return missions and meteorite delivery. Here we will present noble gas data obtained from newly received particles from Ryugu and Bennu. Samples & Analysis: We received nine particles allocated by JAXA, with masses of 0.5-1.7 mg mass: four col-lected during Hayabusa2’s first touchdown (chamber A) and five from a small artificial crater (chamber C). We received three particles from Bennu of 0.07, 0.89 and 0.94 mg mass (OREX-800032-102/3/4). All particles were processed, allocated, weighed, and transferred into our UHV sample chamber within pure N2, to prevent any contact with air. We examined all He-Xe isotopes with our custom-built mass spectrometer “Albatros” ([3,4]). Gases were extracted individually from each particle by melting induced by a 1064 μm Nd:YAG IR laser in 2–4 heating steps. Large amounts of water and other reactive volatiles were released, consistent with the presence of abundant volatiles from both Ryugu and Bennu. Residues of Ryugu particles remaining after lasering, subsequently exposed to air, were additionally extracted in a crucible to verify complete gas extraction. Only the particle that still showed a “crystalline” structure after lasering contained detectable Ryugu noble gases, whereas all other particles turned immediately into glassy spheres by laser heating and lacked any gas. Results & Discussion: Ryugu and Bennu matter contains noble gases similar to the most pristine, unheated aqueously altered meteorites, e.g., CM or CI chondrites [5,6]. Remarkably, all four chamber A samples that originated from Ryugu’s surface show solar wind (SW) Ne (trapped (20Ne/22Ne)tr ~12–13), whereas all five chamber C samples do not ((20Ne/22Ne)tr ~9.0–10.7 consistent with the presence of non-solar trapped Ne components such as Q and HL). This demonstrates that JAXA’s sampling strategy succeeded: Chamber C samples analyzed in this work originated from areas shielded from SW, slightly below the surface, that was sampled after the impactor excavated material. The three Bennu particles populate the same range as the Ryugu particles in Ne isotope space with one particle containing SW suggesting that it was part of the uppermost surface layer of Bennu during sampling, while Ne in the smallest sample can be explained best by mixing Ne from presolar diamonds and SiC or graphite, and that in the third one by mixing of, e.g., Q and HL. Using cosmic ray production rates given by [7] yields preliminary exposure ages for Ryugu particles in the same range as determined in [7]. There is, as expected, also no systematic difference between samples from chambers A and C because both sample sets were likely collected within the uppermost layer of Ryugu, which were not shielded from cosmic rays. The concentration of cosmogenic (cos) Ne in the Bennu particle, where Necos was resolvable, is in the same range as found for Ryugu, suggesting roughly similar exposure time to cosmic rays for 5–8 Ma for all particles examined here. The Xe isotopic compositions of all particles are consistent with those of phase Q, with small additions of Xe-HL from presolar diamonds and excess 129Xe* from short-lived 129I decay. The comparably high 129Xe*/129XeQ ratio is similar in all samples, suggesting similar initial I concentrations and closure to Xe loss –or the incorporation of a well-mixed Xe reservoir. The Bennu material was in brief contact with air in the capsule, after atmospheric entry and before storage in pure N2 in a clean room. Both, the –most diagnostic– Xe isotopes and the Ar/Xe vs. Kr/Xe systematics prove that the noble gases are not affected by terrestrial contamination, in contrast to many CI, CY, and CM chondrites found on Earth [5,6], illustrating the importance of sample return. He-Xe concentrations in all particles unaffected bySW are comparable to but at the upper end of ranges reported [5-7]. In accordance with the strong aqueous alteration experienced on the parent bodies of Ryugu and Bennu [1,2], all samples lack the Ar-rich and water-susceptible noble gas components found in less aqueously altered CMs or CRs [e.g., 5,8] and all COs.

Henner Busemann↗

BrazilClim : The overcoming of limitations of pre‐existing bioclimate data

Abstract Species distribution modelling has become instrumental in assessing the influence of environmental conditions on the occurrence or abundance of taxa. The set of environmental layers used for this purpose is a crucial aspect, for which different climate‐based (bioclimatic) datasets have been recently developed. These bioclimatic variables result from combinations of precipitation and temperatures surfaces. Here, we explored both the performance and possibility of improving some of the currently available bioclimatic databases, through an evaluation of the precipitation and temperatures surfaces used to generate them. For this purpose, we used a combination of statistic and graphic approaches. We focused on Brazil, not only due to its natural megadiversity, but also due to its continental size and orographic heterogeneity: an excellent ground for refining methods replicable elsewhere. We found a better match between the climatic data measured on‐field and Tropical Rainfall Measuring Mission (TRMM 3B43 v7) in the case of precipitation, and the surfaces provided by the National Oceanic and Atmospheric Administration (NOAA) in the case of temperatures, sources uncommonly used for species niche modelling. We gauge‐calibrated the best performing surfaces using machine‐learning algorithms and generated corrected surfaces that allowed us to create BrazilClim: a database of bioclimatic variables, based on improved primary surfaces, which will result in more assertive predicted distributions and more actual pictures of the species' ecological requirements for megadiverse Brazil, an approach replicable elsewhere. All primary and bioclimatic surfaces generated for this study may be freely downloaded.

Ramoni‐Perazzi, Paolo↗

An Evaluation of Sustainable Power System Resilience in the Face of Severe Weather Conditions and Climate Changes: A Comprehensive Review of Current Advances

Natural disasters pose significant threats to power distribution systems, intensified by the increasing impacts of climate changes. Resilience-enhancement strategies are crucial in mitigating the resulting social and economic damages. Hence, this review paper presents a comprehensive exploration of weather management strategies, augmented by recent advancements in machine learning algorithms, to show a sustainable resilience assessment. By addressing the unique challenges posed by diverse weather conditions, we propose flexible and intelligent solutions to navigate disaster complications effectively. This proposition emphasizes sustainable practices that not only address immediate disaster complications, but also prioritize long-term resilience and adaptability. Furthermore, the focus extends to mitigation strategies and microgrid technologies adapted to distribution systems. Through statistical analysis and mathematical formulations, we highlight the critical role of these advancements in mitigating severe weather conditions and ensuring the system reliability.

24 POWER TRANSMISSION AND DISTRIBUTION↗