Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep data”

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 721 records · Page 40

Artificial Intelligence

Artificial intelligence is the study of intelligence agents as demonstrated by machines. It is an interdisciplinary field involving computer science as well as, various kinds of engineering and science, for example, robotics, bio-medical engineering, that accentuates automation of human acts and intelligence through machines. AI represents state-of-the-art use of machines to bring about algorithmic computation and understanding of tasks that include learning, problem solving, mapping, perception, and reasoning. Given the data and a description of its properties and relations between objects of interest, AI methods can perform the aforementioned tasks. Widely applied AI capabilities, e.g. learning, are now achievable at large scale through machine learning (ML), large volumes of data and specialized computational machines. ML encompasses learning without any kind of supervision (unsupervised learning) and learning with full supervision (supervised learning). Widely applied supervised learning techniques include deep learning and other machine learning methods that require less data than deep learning e.g. support vector machines, random forests. Unsupervised learning examples include dictionary learning, independent component analysis, and autoencoders. For application tasks with less labeled data, both supervised and unsupervised techniques can be adapted in a semi-supervised manner to produce accurate models and to increase the size of the labeled training data.

97 MATHEMATICS AND COMPUTING↗

Multi-fidelity information fusion with concatenated neural networks

Recently, computational modeling has shifted towards the use of statistical inference, deep learning, and other data-driven modeling frameworks. Although this shift in modeling holds promise in many applications like design optimization and real-time control by lowering the computational burden, training deep learning models needs a huge amount of data. This big data is not always available for scientific problems and leads to poorly generalizable data-driven models. This gap can be furnished by leveraging information from physics-based models. Exploiting prior knowledge about the problem at hand, this study puts forth a physics-guided machine learning (PGML) approach to build more tailored, effective, and efficient surrogate models. For our analysis, without losing its generalizability and modularity, we focus on the development of predictive models for laminar and turbulent boundary layer flows. In particular, we combine the self-similarity solution and power-law velocity profile (low-fidelity models) with the noisy data obtained either from experiments or computational fluid dynamics simulations (high-fidelity models) through a concatenated neural network. We illustrate how the knowledge from these simplified models results in reducing uncertainties associated with deep learning models applied to boundary layer flow prediction problems. The proposed multi-fidelity information fusion framework produces physically consistent models that attempt to achieve better generalization than data-driven models obtained purely based on data. While we demonstrate our framework for a problem relevant to fluid mechanics, its workflow and principles can be adopted for many scientific problems where empirical, analytical, or simplified models are prevalent. In line with grand demands in novel PGML principles, this work builds a bridge between extensive physics-based theories and data-driven modeling paradigms and paves the way for using hybrid physics and machine learning modeling approaches for next-generation digital twin technologies.

42 ENGINEERING↗

Data-Centric Development of Lignin Structure–Solubility Relationships in Deep Eutectic Solvents Using Molecular Simulations

Lignin is a natural source of aromatic chemicals with significant potential as an abundant, renewable feedstock for value-added products. Deep eutectic solvents (DES)–solvents composed of a hydrogen bond donor (HBD) and acceptor (HBA) in varying ratios–have emerged as a highly tunable class of solvents for lignin solubilization. However, the variety of possible DES compositions and limited molecular-scale understanding of lignin solubility makes solvent selection a challenge without laborious trial-and-error experimentation. To address these challenges, we use classical molecular dynamics (MD) simulations to study the interactions of lignin model compounds with various DES–water systems. Quantitative parameters (descriptors) were calculated by postprocessing the MD results and used to train a regression model that predicts experimentally determined solubilities of lignin model compounds. This approach revealed that the most important descriptors of solubility are the system temperature, solute hydrophilicity, and metrics quantifying hydrogen bonding. Maximizing the interactions between solute–HBD (hydrophobic group), water–HBD (hydrophilic group), and water–HBA molecules led to the highest model compound solubility. Our results support a hydrotropic mechanism in which extensive DES–water hydrogen bonding and favorable HBD interactions with the solute promote high solubility. We applied the regression model derived using model compounds to predict the solubility of representative lignin oligomers. The model predicted lignin oligomers’ solubilities in good agreement with experiments, indicating that the simulations of model compounds can be extended to predict the solubility of larger lignin compounds across a range of solvent compositions and temperatures. Furthermore, these findings provide new molecular-scale insight into lignin solubilization mechanisms and a new method for computationally screening potential solvent systems for lignin valorization.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Deep Learning Approach for In-Network Synchrophasor Missing Data Recovery Using Programmable Network Switches

Phasor measurement unit (PMU) networks deliver accurate and timely measurements, which is essential for managing today’s electric power systems. To ensure data quality and enhance the cyber-resilience of PMU networks against malicious attacks and data errors, this study presents an online PMU missing data recovery scheme by leveraging P4 programmable switches. The data plane incorporates a customized PMU protocol parser that abstracts the necessary payload data for recovery. Recovery processes are executed in the control plane using a pre-trained machine learning model. Both traditional and advanced ML models, such as transformer and TimeGPT, are explicitly employed for data prediction. This approach ensures rapid and precise data recovery. Performance evaluations focus on recovery speed and accuracy, using a real dataset from a campus microgrid. With 20% missing PMU data, the mean absolute percentage error for voltage magnitude is 0.0384%, and the phase angle error discrepancy is approximately 0.4064%.

Phasor Measurement Unit, Machine Learning, Program↗

A global perspective on bacterial diversity in the terrestrial deep subsurface

While recent efforts to catalogue Earth’s microbial diversity have focused upon surface and marine habitats, 12–20% of Earth’s biomass is suggested to exist in the terrestrial deep subsurface, compared to ~1.8% in the deep subseafloor. Metagenomic studies of the terrestrial deep subsurface have yielded a trove of divergent and functionally important microbiomes from a range of localities. However, a wider perspective of microbial diversity and its relationship to environmental conditions within the terrestrial deep subsurface is still required. Our meta-analysis reveals that terrestrial deep subsurface microbiota are dominated by Betaproteobacteria, Gammaproteobacteria and Firmicutes, probably as a function of the diverse metabolic strategies of these taxa. Evidence was also found for a common small consortium of prevalent Betaproteobacteria and Gammaproteobacteria operational taxonomic units across the localities. This implies a core terrestrial deep subsurface community, irrespective of aquifer lithology, depth and other variables, that may play an important role in colonizing and sustaining microbial habitats in the deep terrestrial subsurface. An in silico contamination-aware approach to analysing this dataset underscores the importance of downstream methods for assuring that robust conclusions can be reached from deep subsurface-derived sequencing data. Understanding the global panorama of microbial diversity and ecological dynamics in the deep terrestrial subsurface provides a first step towards understanding the role of microbes in global subsurface element and nutrient cycling.

59 BASIC BIOLOGICAL SCIENCES↗

Data fusion in predicting internal heat gains for office buildings through a deep learning approach

Heating, Ventilation, and Air Conditioning (HVAC) is a major energy consumer in buildings. The predictive control has demonstrated a potential to reduce HVAC energy use. To facilitate predictive HVAC control, internal heat gains prediction is required. Here, we applied Long Short-Term Memory Networks, a special form of deep neural network, to predict miscellaneous electric loads, lighting loads, occupant counts and internal heat gains in two United States office buildings. Compared with the predetermined schedules used in American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) standard 90.1, the Long Short-Term Memory Networks method could reduce the prediction errors of internal heat gains from 12% to 8% in Building A, and from 26% to 16% in Building B. It was also found that for internal heat gains prediction, miscellaneous electric loads is a more important feature than occupant counts for two reasons. First, miscellaneous electric loads is the best proxy variable for internal heat gains, as it is the major component of and has the highest correlation coefficient with the internal heat gains. Second, miscellaneous electric loads contain valuable information to predict occupant count, while occupant count could not help improve miscellaneous electric loads prediction. Lastly, these findings could help researchers and practitioners select the most relevant features to more accurately predict internal heat gains for the implementation of predictive HVAC control in buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

h{sub 1T}{sup perpendicular} and quark orbital angular momentum

We calculate the pretzelosity distribution (h{sub 1T}{sup perpendicular}), which is one of the eight leading twist transverse momentum dependent parton distributions (TMDs), in the light-cone formalism. We find that this quantity has a simple relation with the quark orbital angular momentum distribution, thus it may provide a new possibility to access the quark orbital angular momentum inside the nucleon. The pretzelosity distribution can manifest itself through the sin(3{phi}{sub h}-{phi}{sub S}) asymmetry in semi-inclusive deep inelastic scattering process. We calculate the sin(3{phi}{sub h}-{phi}{sub S}) asymmetry at HERMES, COMPASS, and JLab kinematics and present our prediction on different targets including the proton, deuteron, and neutron targets. Inclusion of transverse momentum cut in data analysis could significantly enhance the sin(3{phi}{sub h}-{phi}{sub S}) asymmetry for future measurements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

First JAM results on the determination of polarized parton distributions

The Jefferson Lab Angular Momentum (JAM) collaboration is a new initiative aimed to the study of the angular-momentum-dependent structure of the nucleon. First results on the determination of spin-dependent parton distribution functions from world data on polarized deep-inelastic scattering will be presented and compared with previous determinations from other groups. Different aspects of global QCD analysis will be discussed, including effects due to nuclear structure, higher twist, and target-mass corrections, as well as the impact of different data selections.

Jimenez-Delgado, Pedro↗

First JAM results on the determination of polarized parton distributions

The Jefferson Lab Angular Momentum (JAM) collaboration is a new initiative aimed to the study of the angular-momentum-dependent structure of the nucleon. First results on the determination of spin-dependent parton distribution functions from world data on polarized deep-inelastic scattering will be presented and compared with previous determinations from other groups. Different aspects of global QCD analysis will be discussed, including effects due to nuclear structure, higher twist, and target-mass corrections, as well as the impact of different data selections.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Biologically inspired approaches for biosurveillance anomaly detection and data fusion

This study developed and tested biologically inspired computational methods to detect anomalous signals in data streams that could indicate a pending outbreak or bio-weapon attack. Current large-scale biosurveillance systems are plagued by two principal deficiencies: (1) timely detection of disease-indicating signals in noisy data and (2) anomaly detection across multiple channels. Anomaly detectors and data fusion components modeled after human immune system processes were tested against a variety of natural and synthetic surveillance datasets. A pilot scale immune-system-based biosurveillance system performed at least as well as traditional statistical anomaly detection data fusion approaches. Machine learning approaches leveraging Deep Learning recurrent neural networks were developed and applied to challenging unstructured and multimodal health surveillance data. Within the limits imposed of data availability, both immune systems and deep learning methods were found to improve anomaly detection and data fusion performance for particularly challenging data subsets.

59 BASIC BIOLOGICAL SCIENCES↗