Search NASA⌕ Search

SEARCH · Search NASA

Results for “knowledge discovery”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Domain-specific text embedding model for accelerator physics

Accelerator physics presents unique challenges for natural language processing (NLP) due to its specialized terminology and complex concepts. A key component in overcoming these challenges is the development of robust text embedding models that transform textual data into dense vector representations, facilitating efficient information retrieval and semantic understanding. In this work, we introduce AccPhysBERT, a sentence embedding model fine-tuned specifically for accelerator physics. Our model demonstrates superior performance across a range of downstream NLP tasks, surpassing existing models in capturing the domain-specific nuances of the field. We further showcase its practical applications, including semantic paper-reviewer matching and integration into retrieval-augmented generation systems, highlighting its potential to enhance information retrieval and knowledge discovery in accelerator physics. Published by the American Physical Society 2025

Hellert, Thorsten (ORCID:0000000227970926)↗
DOE OSTI2021

Mitigating Catastrophic Forgetting in Deep Learning in a Streaming Setting Using Historical Summary

Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.

Dash, Sajal↗
DOE OSTI2018

Parallel k-means Clustering of Geospatial Data Sets Using Manycore CPU Architectures

The increasing availability of high-resolution geospatiotemporal data sets from sources such as observatory networks, remote sensing platforms, and computational Earth system models has opened new possibilities for knowledge discovery and mining of weather, climate, ecological, and other geoscientific data sets fused from disparate sources. Many of the standard tools used on individual workstations are impractical for the analysis and synthesis of data sets of this size; however, new algorithmic approaches that can effectively utilize the complex memory hierarchies and the extremely high levels of parallelism available in state-of-the-art high-performance computing platforms can enable such analysis. Here, we describe pKluster, an open-source tool we have developed for accelerated k-means clustering of geospatial and geospatiotemporal data, and discuss algorithmic modifications and code optimizations we have made to enable it to effectively use parallel machines based on novel CPU architectures—such as the Intel “Knights Landing” Xeon Phi and Skylake Xeon processors—with many cores and hardware threads, and employing significant single instruction, multiple data (SIMD) parallelism. We outline some applications of the code in ecology and climate science contexts and present a detailed discussion of the performance of the code for one such application, LiDAR-derived vertical vegetation structure classification.

Mills, Richard T↗
DOE OSTI2014

Scaling Irregular Applications through Data Aggregation and Software Multithreading

Bioinformatics, data analytics, semantic databases, knowledge discovery are emerging high performance application areas that exploit dynamic, linked data structures such as graphs, unbalanced trees or unstructured grids. These data structures usually are very large, requiring significantly more memory than available on single shared memory systems. Additionally, these data structures are difficult to partition on distributed memory systems. They also present poor spatial and temporal locality, thus generating unpredictable memory and network accesses. The Partitioned Global Address Space (PGAS) programming model seems suitable for these applications, because it allows using a shared memory abstraction across distributed-memory clusters. However, current PGAS languages and libraries are built to target regular remote data accesses and block transfers. Furthermore, they usually rely on the Single Program Multiple Data (SPMD) parallel control model, which is not well suited to the fine grained, dynamic and unbalanced parallelism of irregular applications. In this paper we present {\bf GMT} (Global Memory and Threading library), a custom runtime library that enables efficient execution of irregular applications on commodity clusters. GMT integrates a PGAS data substrate with simple fork/join parallelism and provides automatic load balancing on a per node basis. It implements multi-level aggregation and lightweight multithreading to maximize memory and network bandwidth with fine-grained data accesses and tolerate long data access latencies. A key innovation in the GMT runtime is its thread specialization (workers, helpers and communication threads) that realize the overall functionality. We compare our approach with other PGAS models, such as UPC running using GASNet, and hand-optimized MPI code on a set of typical large-scale irregular applications, demonstrating speedups of an order of magnitude.

Aggregation↗
DOE OSTI2017

Exploring DataVortex Systems for Irregular Applications

Emerging applications for data analytics and knowledge discovery typically have irregular or unpredictable communication patterns that do not scale well on parallel systems designed for traditional bulk-synchronous HPC applications. New network architectures that focus on minimizing (short) message latencies, rather than maximizing (large) transfer bandwidths, are emerging as possible alternatives to better support those applications with irregular communication patterns. We explore a system based upon one such novel network architecture, the Data Vortex interconnection network, and examine how this system performs by running benchmark code written for the Data Vortex network, as well as a reference MPI-over- Infiniband implementation, on the same cluster.

Data Vortex, High-Performance Computing, Networkin↗
DOE OSTI2018

DuoModel: Leveraging Reduced Model for Data Reduction and Re-Computation on HPC Storage

High-performance computing (HPC) applications generate large amounts of floating-point data that need to be stored and analyzed efficiently to extract the insights and advance knowledge discovery. With the growing disparities between compute and I/O, optimizing the storage stack alone may not suffice to cure the I/O problem. There has been a strong push in the HPC communities to perform data reduction before data is transmitted to storage in order to lower the I/O cost. However, as of now, neither lossless nor lossy compressors can achieve the adequate reduction ratio that is desired by applications. This paper proposes DuoModel, a new approach that leverages the similarity between the full and reduced application models, and further improve the data reduction ratio. DouModel further improves the compression ratio of state-of-the-art compressors via compressing the differences (termed as delta) between the data products of the two models. For data analytics, the high fidelity data can be re-computed by launching the reduced model and applying the compressed delta. Our evaluations confirm that DuoModel can further push the limit of data reduction while the high fidelity of data is maintained.

Luo, Huizhang (ORCID:0000000323920267)↗
DOE OSTI2022

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. Here, in this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations—content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a human-understandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2014

Feature-Based Analysis of Plasma-Based Particle Acceleration Data

Plasma-based particle accelerators can produce and sustain thousands of times stronger acceleration fields than conventional particle accelerators, providing a potential solution to the problem of the growing size and cost of conventional particle accelerators. To facilitate scientific knowledge discovery from the ever growing collections of accelerator simulation data generated by accelerator physicists to investigate next-generation plasma-based particle accelerator designs, we describe a novel approach for automatic detection and classification of particle beams and beam substructures due to temporal differences in the acceleration process, here called acceleration features. The automatic feature detection in combination with a novel visualization tool for fast, intuitive, query-based exploration of acceleration features enables an effective top-down data exploration process, starting from a high-level, feature-based view down to the level of individual particles. We describe the application of our analysis in practice to analyze simulations of single pulse and dual and triple colliding pulse accelerator designs, and to study the formation and evolution of particle beams, to compare substructures of a beam and to investigate transverse particle loss.

43 PARTICLE ACCELERATORS↗
DOE OSTI2016

TU-C-HORIZONS-01: The Expanding Horizons Travel Grant Program: ePosters and Discussion

The Expanding Horizons travel grant program provides opportunity for students and trainees to broaden the scope of scientific meetings they attend and gain insight from research outside traditional domains of medical physics. Through participation in such conferences, early-career researchers are introduced to new topics with relevance to medical physics research as a means to expand the scientific horizons of our discipline. This year, 21 Expanding Horizons travel grants were awarded, granting travel to 17 conferences, including: Radiomics, the World Molecular Imaging Society (WMIS), the 3D Printing Conference and Expo, the GPU Technology Conference, the SIAM Imaging Science Conference, the Human Brain Mapping Conference, the OSA Conference on Clinical and Translational Biophotonics, the Society for Neuroscience, the AACR Conference on Tumor Microenvironment, and the Conference on Knowledge Discovery and Data Mining. The Expanding Horizons electronic poster session gives a venue for AAPM conference attendees to meet and discuss with awardees, learn the hot topics and emerging research areas presented at these conferences, and understand the relevance to future medical physics research.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2016

Big Data as a Service from an Urban Information System

Big Data has already proven itself as a valuable tool that lets geographers and urban researchers utilize large data re- sources to generate new insights. However, wider adoption of Big Data techniques in these areas is impeded by a number of difficulties in both knowledge discovery and data and sci- ence production. Typically users face such problems as dis- parate and scattered data, data management, spatial search- ing, insufficient computational capacity for data-driven anal- ysis and modelling, and the lack of tools to quickly visual- ize and summarize large data and analysis results. Here we propose an architecture for an Urban Information Sys- tem (UrbIS) that mitigates these problems by utilizing the Big Data as a Service (BDaaS) concept. With technolog- ical roots in High-performance Computing (HPC), BDaaS is based on the idea of outsourcing computations to dif- ferent computing paradigms, scalable to super-computers. UrbIS aims to incorporate federated metadata search, in- tegrated modeling and analysis, and geovisualization into a single seamless workflow. The system is under active devel- opment and is built around various emerging technologies that include hybrid and NoSQL databases, massively par- allel systems, GPGPU computing, and WebGL-based geo- graphic visualization. UrbIS is designed to facilitate using Big Data across multiple cities to better understand how ur- ban areas impact the environment and how climate change and other environmental change impact urban areas.

Sorokine, Alexandre↗
DOE OSTI2019

Using Digital Trace Data to Identify Regions and Cities

A greater understanding of human dynamics as they play out in both physical space and through inter-personal communication is vital for the design and development of intelligent and resilient cities. Physical context provides insight in to the space-time distribution of population and their activity patterns, while inter-personal communication can, for the first time, be measured at scale through virtual interactions. The confluence of these two enables spatial social network analysis in the built environment for edge computing, knowledge discovery, and artificial intelligence activities. In this work, we propose a novel method to discover such dynamics. We use a dataset of 72 million tweets to develop a spatially embedded network of communication, and then use community detection algorithms to explore regional and urban delineation in the United States. We find that the broad spatial delineation of communities and community sub-structure is consistent with major United States socio-cultural regions, states, and major metropolitan areas. We describe how these methods could be extended to generate a measure of socially cohesive regions that can be consistently applied anywhere there is a sufficiently rich data source. We hope the proposed methods will generate new perspectives on smart and resilient cities.

Brelsford, Christa↗
DOE OSTI2019

Scalable Causal Graph Learning through a Deep Neural Network

Learning the causal graph in a complex system is crucial for knowledge discovery and decision making, yet it remains a challenging problem because of the unknown nonlinear interaction among system components. Most of the existing methods either rely on predefined kernel or data distribution, or they focus simply on the causality between a single target and the remaining system. This work presents a deep neural network for scalable causal graph learning (SCGL) through low-rank approximation. The SCGL model can explore nonlinearity on both temporal and intervariable relationships without any predefined kernel or distribution assumptions. Through low-rank approximation, the noise influence is reduced, and better accuracy and high scalability are achieved. Experiments using synthetic and real-world datasets show that our SCGL algorithm outperforms existing state-of-the-art methods for causal graph learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Fragile Earth: AI for Climate Mitigation, Adaptation, and Environmental Justice

The Fragile EarthWorkshop is a recurring event that gathers the research community to find and explore howdata science can measure and progress climate and social issues, following the framework of the United Nations Sustainable Development Goals (SDGs).Fragile Earth 2022: AI for Climate Mitigation, Adaptation, and Environmental Justice is a workshop taking place as part of the ACM's KDD 2022 Conference on research in knowledge discovery and data mining and their applications. The dates for the Conference are August 14-18, 2022.

Abe, Naoki↗
DOE OSTI2022

Essential Function Analysis Capability

The Essential Function Analysis Capability (EFAC) is an extension of the All Hazards Knowledge Framework (AHA) and is a dynamic analytical framework that enables critical infrastructure knowledge discovery and decision support across the five mission areas – prevention, protection, mitigation, response and recovery. EFAC provides the ability to store and model infrastructure systems as a linked multigraphs providing an intuitive and natural representation. These infrastructure systems can then be tied to the organizational and essential function breakdown of an entity. This capability provides the foundation to rapidly evaluate and understand the potential consequences of manmade and natural disaster on these infrastructure systems and essential functions.

Hoover, MichaelJ.↗
DOE OSTI2025

pnnl/HypoGen

An innovative workflow for automatic knowledge discovery in material science, combining experimental automation with advanced machine learning and artificial intelligence techniques

Yin, Tim [Pacific Northwest National Laboratory (P↗
DOE OSTI2019

All Hazards Analysis Core

The All Hazards Knowledge Framework (AHA) is a dynamic analytical framework that enables critical infrastructure knowledge discovery and decision support across the five mission areas – prevention, protection, mitigation, response and recovery. AHA provides the ability to store and model infrastructure systems as a linked multigraphs providing an intuitive and natural representation. This capability provides the foundation to rapidly evaluate and understand the potential consequences of manmade and natural disaster on these systems.

McGillivary, KentE.↗
DOE OSTI2014

SciDAC Institute for Ultra-Scale Visualization: Activity Recognition for Ultra-Scale Visualization

Understanding the science behind ultra-scale simulations requires extracting meaning from data sets of hundreds of terabytes or more. Developing scalable parallel visualization algorithms is a key step enabling scientists to interact and visualize their data at this scale. However, at extreme scales, the datasets are so huge, there is not even enough time to view the data, let alone explore it with basic visualization methods. Automated tools are necessary for knowledge discovery -- to help sift through the information and isolate characteristic patterns, thereby enabling the scientist to study local interactions, the origin of features and their evolution in large volumes of data. These tools must be able to operate on data of this scale and work with the visualization process. In this project, we developed a framework for activity detection to allow scientists to model and extract spatio-temporal patterns from time-varying data.

97 MATHEMATICS AND COMPUTING↗