Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning systems”

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 1,099 records · Page 61

Open Power System Datasets and Open Simulation Engines: A Survey Toward Machine Learning Applications

A major factor behind the success of machine learning (ML) models in multiple domains is the availability and accessibility of large, labeled, and well-organized datasets for training and benchmarking. In comparison, power grid datasets face three major challenges: (i) real-world data is often restricted by regulatory constraints, privacy reasons, or security concerns, making it difficult to obtain and work with; (ii) synthetic datasets, which are created to address these limitations, often have incomplete information and are released using specialized tools, making them inaccessible to the broader community; and, (iii) input-output datasets are difficult to generate through simulation for non-experts because open-source simulators are not known outside the power system community. This survey addresses these challenges by serving as an entry point to publicly available datasets and simulators for researchers venturing in this area. We review the current landscape of open-source power network data, machine models, consumer demand profiles, renewable generation data, and inverter models. We also examine open-source power system simulators, which are crucial for generating high-quality, high-fidelity power grid datasets. We aim to provide a foundation for overcoming data scarcity and advance towards a structured web of datasets and simulators to support the development of ML for power systems.

42 ENGINEERING↗

PERIODIC SIGNALS IN BINARY MICROLENSING EVENTS

Gravitational microlensing events are powerful tools for the study of stellar populations. In particular, they can be used to discover and study a variety of binary systems. A large number of binary lenses have already been found through microlensing surveys and a few of these systems show strong evidence of orbital motion on the timescale of the lensing event. We expect that more binary lenses of this kind will be detected in the future. For binaries whose orbital period is comparable to the event duration, the orbital motion can cause the lensing signal to deviate drastically from that of a static binary lens. The most striking property of such light curves is the presence of quasi-periodic features, which are produced as the source traverses the same regions in the rotating lens plane. These repeating features contain information about the orbital period of the lens. If this period can be extracted, then much can be learned about the lensing system even without performing time-consuming, detailed light-curve modeling. However, the relative transverse motion between the source and the lens significantly complicates the problem of period extraction. To resolve this difficulty, we present a modification of the standard Lomb–Scargle periodogram analysis. We test our method for four representative binary lens systems and demonstrate its efficiency in correctly extracting binary orbital periods.

79 ASTRONOMY AND ASTROPHYSICS↗

A pre-training and self-training approach for biomedical named entity recognition

Named entity recognition (NER) is a key component of many scientific literature mining tasks, such as information retrieval, information extraction, and question answering; however, many modern approaches require large amounts of labeled training data in order to be effective. This severely limits the effectiveness of NER models in applications where expert annotations are difficult and expensive to obtain. In this work, we explore the effectiveness of transfer learning and semi-supervised self-training to improve the performance of NER models in biomedical settings with very limited labeled data (250-2000 labeled samples). We first pre-train a BiLSTM-CRF and a BERT model on a very large general biomedical NER corpus such as MedMentions or Semantic Medline, and then we fine-tune the model on a more specific target NER task that has very limited training data; finally, we apply semi-supervised self-training using unlabeled data to further boost model performance. We show that in NER tasks that focus on common biomedical entity types such as those in the Unified Medical Language System (UMLS), combining transfer learning with self-training enables a NER model such as a BiLSTM-CRF or BERT to obtain similar performance with the same model trained on 3x-8x the amount of labeled data. We further show that our approach can also boost performance in a low-resource application where entities types are more rare and not specifically covered in UMLS.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Wind-To-Hydrogen Project: Operational Experience, Performance Testing, and Systems Integration

The Wind2H2 system is fully functional and continues to gather performance data. In this report, specifications of the Wind2H2 equipment (electrolyzers, compressor, hydrogen storage tanks, and the hydrogen fueled generator) are summarized. System operational experience and lessons learned are discussed. Valuable operational experience is shared through running, testing, daily operations, and troubleshooting the Wind2H2 system and equipment errors are being logged to help evaluate the reliability of the system.

08 HYDROGEN↗

Learning of networked spreading models from noisy and incomplete data

Recent years have seen a lot of progress in algorithms for learning parameters of spreading dynamics from both full and partial data. Some of the remaining challenges include model selection under the scenarios of unknown network structure, noisy data, missing observations in time, as well as an efficient incorporation of prior information to minimize the number of samples required for an accurate learning. Here, in this work, we introduce a universal learning method based on a scalable dynamic message-passing technique that addresses these challenges often encountered in real data. The algorithm leverages available prior knowledge on the model and on the data, and reconstructs both network structure and parameters of a spreading model. We show that a linear computational complexity of the method with the key model parameters makes the algorithm scalable to large network instances.

97 MATHEMATICS AND COMPUTING↗

Reinforcement Learning-based Output Structured Feedback for Distributed Multi-Area Power System Frequency Control

Load frequency control (LFC) is a key factor to maintain the stable frequency in multi-area power systems. As the modern power systems evolve from centralized to decentralized paradigm, LFC needs to consider the decentralized scheme that considers limited information from the information-exchange graph for the generator control of each interconnected area. This paper aims to solve a data-driven constrained LQR problem with mean-variance risk constraints and output structured feedback, and applies this framework to solve the LFC problem in multi-area power systems. By reformulating the constrained optimization problem into a minimax problem, the stochastic gradient descent max-oracle (SGDmax) algorithm with zero-order policy gradient (ZOPG) is adopted to find the optimal feedback gain from the learning, while guaranteeing the convergence. In addition, to improve the adaptation of the proposed learning method to new or varying models, we construct an emulator grid that approximates the dynamics of a physical grid and performs training based on this model. Once the feedback gain is obtained from the emulator grid, it is applied to the physical grid with a robustness test to check whether the controller from the approximated emulator applies to the actual system. Numerical tests show that the obtained feedback controller can successfully control the frequency of each area, while mitigating the uncertainty from the loads, with reliable robustness that ensures the adaptability of the obtained feedback gain to the actual physical grid.

Kwon, Kyung-bin↗

On Distributed Model-Free Reinforcement Learning Control with Stability Guarantee

Distributed learning can enable scalable and effective decision making in numerous complex cyber-physical systems such as smart transportation, robotics swarm, power systems, etc. However, the stability of the system is usually not guaranteed in most existing learning paradigms; and this limitation can hinder the wide deployment of machine learning in decision making of safety-critical systems. This paper presents a stability guaranteed distributed reinforcement learning (SGDRL) framework for interconnected linear subsystems, without knowing the subsystem models. While the learning process requires data from a peer-to-peer (p2p) communication architecture, the control implementation of each subsystem is only based on its local state. The stability of the interconnected subsystems will be ensured by a diagonally dominant eigenvalue condition, which will then be used in a model-free RL algorithm to learn the feedback control gains. The RL algorithm structure follows an off-policy iterative framework, with interleaved policy evaluation and policy update steps. We numerically validate our theoretical results by performing simulations on four interconnected sub-systems.

Mukherjee, Sayak↗

Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools

Large language models (LLMs) show promise in supporting differential diagnosis, but their performance is challenging to evaluate due to the unstructured nature of their responses, and their accuracy compared to existing diagnostic tools is not well characterized. To assess the current capabilities of LLMs to diagnose genetic diseases, we benchmarked these models on 5213 previously published case reports using the Phenopacket Schema, the Human Phenotype Ontology and Mondo disease ontology. Prompts generated from each phenopacket were sent to seven LLMs, including four generalist models and three LLMs specialized for medical applications. The same phenopackets were used as input to a widely used diagnostic tool, Exomiser, in phenotype-only mode. The best LLM ranked the correct diagnosis first in 23.6% of cases, whereas Exomiser did so in 35.5% of cases. While the performance of LLMs for supporting differential diagnosis has been improving, it has not reached the level of commonly used traditional bioinformatics tools. Future research is needed to determine the best approach to incorporate LLMs into diagnostic pipelines.

Reese, Justin T. [Lawrence Berkeley National Labor↗

Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference

This work introduces a method for learning low-dimensional models from data of high-dimensional black-box dynamical systems. The novelty is that the learned models are exactly the reduced models that are traditionally constructed with classical projection-based model reduction techniques. Thus, the proposed approach learns models that are guaranteed to have the well-studied properties of reduced models known from model reduction, without requiring full knowledge of the governing equations and without requiring the operators of the high-dimensional systems. The key ingredient is a new data sampling scheme to obtain re-projected trajectories of high-dimensional systems that correspond to Markovian dynamics in low-dimensional subspaces. The exact recovery of reduced models from these re-projected trajectories is guaranteed pre-asymptotically under certain conditions for finite amounts of data and for a large class of systems with polynomial nonlinear terms. Numerical results demonstrate that the low-dimensional models learned with the proposed approach match reduced models from traditional model reduction up to numerical errors in practice. In conclusion, the numerical results further indicate that low-dimensional models fitted to re-projected trajectories are predictive even in situations where models fitted to trajectories without re-projection are inaccurate and unstable.

97 MATHEMATICS AND COMPUTING↗

Facility Detection and Popularity Assessment from Text Classification of Social Media and Crowdsourced Data

Advances in technology have continually progressed our understanding of where people are, how they use the environment around them, and why they are at their current location. Having a better knowledge of when various locations become popular through space and time could have large impacts on research fields like urban dynamics and energy consumption. In this paper, we discuss the ability to identify and locate various facility types (e.g. restaurant, airport, stadiums) using social media, and assess methods in determining when these facilities become popular over time. We use natural language processing tools and machine learning classifiers to interpret geotagged Twitter text and determine if a user is seemingly at a location of interest when the tweet was sent. On average our classifiers are approximately 85% accurate varying across multiple facility types, with a peak precision of 98%. By using these methods to classify unstructured text, geotagged social media data can be an extremely useful tool to better understanding the composition of places and how and when people use them.

crowd-sourced data↗

A Novel Deep Reinforcement Learning Approach to Traffic Signal Control with Connected Vehicles

The advent of connected vehicle (CV) technology offers new possibilities for a revolution in future transportation systems. With the availability of real-time traffic data from CVs, it is possible to more effectively optimize traffic signals to reduce congestion, increase fuel efficiency, and enhance road safety. The success of CV-based signal control depends on an accurate and computationally efficient model that accounts for the stochastic and nonlinear nature of the traffic flow. Without the necessity of prior knowledge of the traffic system’s model architecture, reinforcement learning (RL) is a promising tool to acquire the control policy through observing the transition of the traffic states. In this paper, we propose a novel data-driven traffic signal control method that leverages the latest in deep learning and reinforcement learning techniques. By incorporating a compressed representation of the traffic states, the proposed method overcomes the limitations of the existing methods in defining the action space to include more practical and flexible signal phases. The simulation results demonstrate the convergence and robust performance of the proposed method against several existing benchmark methods in terms of average vehicle speeds, queue length, wait time, and traffic density.

42 ENGINEERING↗

Effects of Deployment Investment on the Growth of the Biofuels Industry

In support of the national goals for biofuel use in the United States, numerous technologies have been developed that convert biomass to biofuels. Some of these biomass to biofuel conversion technology pathways are operating at commercial scales, while others are in earlier stages of development. The advancement of a new pathway toward commercialization involves various types of progress, including yield improvements, process engineering, and financial performance. Actions of private investors and public programs can accelerate the demonstration and deployment of new conversion technology pathways. These investors (both private and public) will pursue a range of pilot, demonstration, and pioneer scale biorefinery investments; the most cost-effective set of investments for advancing the maturity of any given biomass to biofuel conversion technology pathway is unknown. In some cases, whether or not the pathway itself will ultimately be technically and financially successful is also unknown. This report presents results from the Biomass Scenario Model -- a system dynamics model of the biomass to biofuels system -- that estimate effects of investments in biorefineries at different maturity levels and operational scales. The report discusses challenges in estimating effects of such investments and explores the interaction between this deployment investment and a volumetric production incentive. Model results show that investments in demonstration and deployment have a substantial positive effect on the development of the biofuels industry. Results also show that other conditions, such as supportive policies, have major impacts on the effectiveness of such investments.

09 BIOMASS FUELS↗

Adaptive Learning for Concept Drift in Application Performance Modeling

Supervised learning is a promising approach for modeling the performance of applications running on large HPC systems. A key assumption in supervised learning is that the training and testing data are obtained under the same conditions. However, in production HPC systems these conditions might not hold because the conditions of the platform can change over time as a result of hardware degradation, hardware replacement, software upgrade, and configuration updates. These changes could alter the data distribution in a way that affects the accuracy of the predictive performance models and render them less useful; this phenomenon is referred to as concept drift. Ignoring concept drift can lead to suboptimal resource usage and decreased efficiency when those performance models are deployed for tuning and job scheduling in production systems. To address this issue, we propose a concept-drift-aware predictive modeling approach that comprises two components: (1) an online Bayesian changepoint detection method that can automatically identify the location of events that lead to concept drift in near-real time and (2) a moment-matching transformation inspired by transfer learning that converts the training data collected before the drift to be useful for retraining. We use application input/output performance data collected on Cori, a production supercomputing system at the National Energy Research Scientific Computing Center, to demonstrate the effectiveness of our approach. The results show that concept-drift-aware models obtain significant improvement in accuracy; the median absolute error of the best-performing Gaussian process regression improved by 58.8% when the proposed approaches were used.

adaptive learning↗

Computation of the Thermal Expansion Coefficient of Graphene with Gaussian Approximation Potentials

Direct experimental measurement of thermal expansion coefficient without substrate effects is a challenging task for two-dimensional (2D) materials, and its accurate estimation with large-scale ab initio molecular dynamics is computationally very expensive. Machine learning-based interatomic potentials trained with ab initio data have been successfully used in molecular dynamics simulations to decrease the computational cost without compromising the accuracy. In this work, we investigated using Gaussian approximation potentials to reproduce the density functional theory-level accuracy for graphene within both lattice dynamical and molecular dynamical methods, and to extend their applicability to larger length and time scales. Two such potentials are considered, GAP17 and GAP20. GAP17, which was trained with pristine graphene structures, is found to give closer results to density functional theory calculations at different scales. Further vibrational and structural analyses verify that the same conclusions can be deduced with density functional theory level in terms of the reasoning of the thermal expansion behavior, and the negative thermal expansion behavior is associated with long-range out-of-plane phonon vibrations. Thus, it is argued that the enabled larger system sizes by machine learning potentials may even enhance the accuracy compared to small-size-limited ab initio molecular dynamics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materials

The Abisko project aims to develop an energy-efficient spiking neural network (SNN) computing architecture and software system capable of autonomous learning and operation. The SNN architecture explores novel neuromorphic devices that are based on resistive-switching materials, such as memristors and electrochemical RAM. Equally important, Abisko uses a deep codesign approach to pursue this goal by engaging experts from across the entire range of disciplines: materials, devices and circuits, architectures and integration, software, and algorithms. Here, the key objectives of our Abisko project are threefold. First, we are designing an energy-optimized high-performance neuromorphic accelerator based on SNNs. This architecture is being designed as a chiplet that can be deployed in contemporary computer architectures and we are investigating novel neuromorphic materials to improve its design. Second, we are concurrently developing a productive software stack for the neuromorphic accelerator that will also be portable to other architectures, such as field-programmable gate arrays and GPUs. Third, we are creating a new deep codesign methodology and framework for developing clear interfaces, requirements, and metrics between each level of abstraction to enable the system design to be explored and implemented interchangeably with execution, measurement, a model, or simulation. As a motivating application for this codesign effort, we target the use of SNNs for an analog event detector for a high-energy physics sensor.

97 MATHEMATICS AND COMPUTING↗

Information Technology and Community Restoration Studies/Task 1: Information Technology

Executive Summary The Interagency Biological Restoration Demonstration—a program jointly funded by the Department of Defense's Defense Threat Reduction Agency and the Department of Homeland Security's (DHS's) Science and Technology Directorate—is developing policies, methods, plans, and applied technologies to restore large urban areas, critical infrastructures, and Department of Defense installations following the intentional release of a biological agent (anthrax) by terrorists. There is a perception that there should be a common system that can share information both vertically and horizontally amongst participating organizations as well as support analyses. A key question is: "How far away from this are we?" As part of this program, Pacific Northwest National Laboratory conducted research to identify the current information technology tools that would be used by organizations in the greater Seattle urban area in such a scenario, to define criteria for use in evaluating information technology tools, and to identify current gaps. Researchers interviewed 28 individuals representing 25 agencies in civilian and military organizations to identify the tools they currently use to capture data needed to support operations and decision making. The organizations can be grouped into five broad categories: defense (Department of Defense), environmental/ecological (Environmental Protection Agency/Ecology), public health and medical services, emergency management, and critical infrastructure. The types of information that would be communicated in a biological terrorism incident include critical infrastructure and resource status, safety and protection information, laboratory test results, and general emergency information. The most commonly used tools are WebEOC (web-enabled crisis information management systems with real-time information sharing), mass notification software, resource tracking software, and NW WARN (web-based information to protect critical infrastructure systems). It appears that the current information management tools are used primarily for information gathering and sharing—not decision making. Respondents identified the following criteria for a future software system. It is easy to learn, updates information in real time, works with all agencies, is secure, uses a visualization or geographic information system feature, enables varying permission levels, flows information from one stage to another, works with other databases, feeds decision support tools, is compliant with appropriate standards, and is reasonably priced. Current tools have security issues, lack visual/mapping functions and critical infrastructure status, and do not integrate with other tools. It is clear that there is a need for an integrated, common operating system. The system would need to be accessible by all the organizations that would have a role in managing an anthrax incident to enable regional decision making. The most useful tool would feature a GIS visualization that would allow for a common operating picture that is updated in real time. To capitalize on information gained from the interviews, the following activities are recommended: • Rate emergency management decision tools against the criteria specified by the interviewees. • Identify and analyze other current activities focused on information sharing in the greater Seattle urban area. • Identify and analyze information sharing systems/tools used in other regions.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Effects of Deployment Investment on the Growth of the Biofuels Industry. 2016 Update

This report updates the 2013 report of the same title. Some text originally published in that report is retained and indicated in gray. In support of the national goals for biofuel use in the United States, numerous technologies have been developed that convert biomass to biofuels. Some of these biomass to biofuel conversion technology pathways are operating at commercial scales, while others are in earlier stages of development. The advancement of a new pathway toward commercialization involves various types of progress, including yield improvements, process engineering, and financial performance. Actions of private investors and public programs can accelerate the demonstration and deployment of new conversion technology pathways. These investors (both private and public) will pursue a range of pilot, demonstration, and pioneer scale biorefinery investments; the most cost-effective set of investments for advancing the maturity of any given biomass to biofuel conversion technology pathway is unknown. In some cases, whether or not the pathway itself will ultimately be technically and financially successful is also unknown. This report presents results from the Biomass Scenario Model--a system dynamics model of the biomass to biofuels system--that estimate effects of investments in biorefineries at different maturity levels and operational scales. The report discusses challenges in estimating effects of such investments and explores the interaction between this deployment investment and a volumetric production incentive. Model results show that investments in demonstration and deployment have a substantial growth impact on the development of the biofuels industry. Results also show that other conditions, such as accompanying incentives, have major impacts on the effectiveness of such investments. Results from the 2013 report are compared to new results. This report does not advocate for or against investments, incentives, or policies, but analyzes simulations of their hypothetical effects.

09 BIOMASS FUELS↗