Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network Models”

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 1,729 records · Page 96

Rapid quantitative analysis of trace elements in plutonium alloys using a handheld laser-induced breakdown spectroscopy (LIBS) device coupled with chemometrics and machine learning

Here, we present the first reported quantification of trace elements in plutonium via a portable laser-induced breakdown spectroscopy (LIBS) device and demonstrate the use of chemometric analysis to enhance the handheld device's sensitivity and precision. Quantification of trace elements such as iron and nickel in plutonium metal via LIBS is a challenging problem due to the complex nature of the plutonium optical emission spectra. While rapid analysis of plutonium alloys has been demonstrated using portable LIBS devices, such as the SciAps Z300, their detection limits for trace elements are severely constrained by their achievable pulse power and length, light collection optics, and detectors. In this paper, analytical methods are evaluated as a means to circumvent the detection constraints. Three chemometric methods often used in analytical spectroscopy are evaluated; principal component regression, partial least-squares regression, and artificial neural networks. These models are evaluated based on goodness-of-fit metrics, root mean-squared error, and their achievable limits of detection (LoDs). Partial least squares proved superior for determining content of iron and nickel in plutonium metal, yielding LoDs of 15 and 20 ppm, respectively. These results of identifying the undesirable trace elements in plutonium components are critical for applications such as fabricating radioisotope thermoelectric generators or nuclear fuel.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Deep‐learning‐based power distribution network switch action identification leveraging dynamic features of distributed energy resources

This study proposes a data‐driven approach for identifying switch actions in power distribution networks. Simulated micro‐phasor measurement unit data is utilised to train a convolutional neural network (CNN) model. The trained CNN model can identify multi‐phase multi‐switch actions. Instead of working as a blackbox, the proposed approach extracts the features from the hidden layers of the trained CNN for engineering interpretation and error check. In addition, a random‐forest‐based feature ranking algorithm is proposed to identify the most important features. The proposed approach is validated on the IEEE 123‐node feeder modelled in GridLAB‐D. The CNN model is built and trained using TensorFlow. The proposed approach achieves 96.57% identification accuracy.

42 ENGINEERING↗

Flow distribution analysis on the cooling tube network of ITER thermal shield

Thermal shield (TS) is to be installed between the vacuum vessel or the cryostat and the magnets in ITER tokamak to reduce the thermal radiation load to the magnets operating at 4.2K. The TS is cooled by pressurized helium gas at the inlet temperature of 80K. The cooling tube is welded on the TS panel surface and the composed flow network of the TS cooling tubes is complex. The flow rate in each panel should be matched to the thermal design value for effective radiation shielding. This paper presents one dimensional analysis on the flow distribution of cooling tube network for the ITER TS. The hydraulic cooling tube network is modeled by an electrical analogy. Only the cooling tube on the TS surface and its connecting pipe from the manifold are considered in the analysis model. Considering the frictional factor and the local loss in the cooling tube, the hydraulic resistance is expressed as a linear function with respect to mass flow rate. Sub-circuits in the TS are analyzed separately because each circuit is controlled by its own control valve independently. It is found that flow rates in some panels are insufficient compared with the design values. In order to improve the flow distribution, two kinds of design modifications are proposed. The first one is to connect the tubes of the adjacent panels. This will increase the resistance of the tube on the panel where the flow rate is excessive. The other design suggestion is that an orifice is installed at the exit of tube routing where the flow rate is to be reduced. The analysis for the design suggestions shows that the flow mal-distribution is improved significantly.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A spatial DB model to simulate the road network efficiency in hydrogeological emergency

We deal with the theme of the simulation of risk analysis using a technological approach based on the integration of exclusively free and open source tools: PostgreSQL as Database Management System (DBMS) and Quantum GIS-GRASS as Geographic Information System (GIS) platform. The case study is represented by a seismic land in Sicily characterized by steep slopes and frequent instability phenomena. This area includes a city of about 30.000 inhabitants (Enna) that lies on the top of a mountain at about 990 m a.s.l.. The access to the city is assured by few and very winding roads that are also highly vulnerable to seismic and hydrogeological hazards. When exceptional rainfall events occur, the loss of efficiency of these roads should compromise timeliness and effectiveness of rescue operations. The data of the sample area have been structured into the adopted DBMS, and the connection to the GIS functionalities allows simulating the exceptional events. We analyzed the hazard, vulnerability and exposure related to these events and calculated the final risk defining three classes for each scenario: low (L), medium (M) and high (H). This study can be a valuable tool to prioritize risk levels and set priorities for intervention to the main road networks.

54 ENVIRONMENTAL SCIENCES↗

Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak

Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications. Here, in this study, we process high-speed camera data, at rates exceeding 100 kfps, on in situ field-programmable gate array (FPGA) hardware to track magnetohydrodynamic (MHD) mode evolution and generate control signals in real time. Our system utilizes a convolutional neural network (CNN) model, which predicts the n = 1 MHD mode amplitude and phase using camera images with better accuracy than other tested non-deep-learning-based methods. By implementing this model directly within the standard FPGA readout hardware of the high-speed camera diagnostic, our mode tracking system achieves a total trigger-to-output latency of 17.6 μs and a throughput of up to 120 kfps. This study at the High Beta Tokamak-Extended Pulse (HBT-EP) experiment demonstrates an FPGA-based high-speed camera data acquisition and processing system, enabling application in real-time machine-learning-based tokamak diagnostic and control as well as potential applications in other scientific domains.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Toward machine-learning-assisted PW-class high-repetition-rate experiments with solid targets

We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such a framework for future autonomous exploration platforms in high-repetition-rate experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Microscopic insights into the solvation of polyethylene glycol chains in water: A machine learning potential approach

Polyethylene glycol (PEG) is a structurally simple, nontoxic, and water-soluble polymer widely utilized in medical and pharmaceutical applications. Notably, when a PEG chain is immersed in water, the surrounding water molecules play a key role in driving conformational changes of this macromolecule. In this study, we explore the solvation behavior of PEG under mechanical strain using molecular dynamics simulations, with an interatomic potential obtained from machine learning. Our focus is on the transition from the favored coil-like conformation to an extended one under external force. Through analyses of radial distribution functions, hydrogen bonding, and solvation dynamics, we uncover how mechanical stretching influences the local hydration environment. Furthermore, we disentangle the enthalpic and entropic contributions to the conformational stability of PEG in water. Surprisingly, our neural network potential model identifies dewetting of PEG C-atoms, and not water H-bonding with PEG O-atoms, as the main enthalpic driving force for the coiling of PEG in water.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Fast and stable deep-learning predictions of material properties for solid solution alloys

We present a novel deep learning (DL) approach to produce highly accurate predictions of macroscopic physical properties of solid solution binary alloys and magnetic systems. The major idea is to make use of the correlations between different physical properties in alloy systems to improve the prediction accuracy of neural network (NN) models. We use multitasking NN models to simultaneously predict the total energy, charge density and magnetic moment. These physical properties mutually serve as constraints during the training of the multitasking NN, resulting in more reliable DL models because multiple physics properties are correctly learned by a single model. Two binary alloys, copper–gold (CuAu) and iron–platinum (FePt), were studied. Our results show that once the multitasking NN's are trained, they can estimate the material properties for a specific configuration hundreds of times faster than first-principles density functional theory calculations while retaining comparable accuracy. We used a simple measure based on the root-mean-squared errors to quantify the quality of the NN models, and found that the inclusion of charge density and magnetic moment as physical constraints leads to more stable models that exhibit improved accuracy and reduced uncertainty for the energy predictions.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

In situ saxs characterization of thermoresponsive behavior of a poly(ethylene glycol)-graft-(poly(vinyl caprolactam)-co-poly(vinyl acetate)) amphiphilic graft copolymer

In this work, we report the thermoresponsive assembly and rheology of an amphiphilic thermosensitive graft copolymer, poly(ethylene glycol)-graft-(poly(vinyl caprolactam)-co-poly(vinyl acetate)) (commercial name Soluplus ® ), which has been investigated for potential biomedical applications. It has received attention due to is ability to solubilize hydrophobic drugs and for its thickening behavior close to body temperature. Through use of the synchrotron at Brookhaven National Lab, and collaboration with the department of energy, the nanoscale structure and properties can be probed in greater detail. Soluplus ® undergoes two structural changes as temperature is increased; the first, a concentration independent change where samples become turbid at 32 °C. Increasing the temperature further causes the formation of physically associated hydrogels. This sol-gel transition is concentration dependent and occurs at 32 °C for 40 wt% samples, and increases to 42 °C for 10 wt% samples. From variable temperature SAXS characterization micelles of 20–25 nm in radius can be seen and maintain their size and packing below 32 °C. A gradual increase in the aggregation of micelles corresponding to a thickening of the material is also observed. Close to and above the gelation temperature, micelles collapse and form a physically associated 3D network. A model is proposed to explain these physical effects, where the poly(vinyl caprolactam) group transitions from the hydrophilic corona at room temperature to the hydrophobic core as temperature is increased.

36 MATERIALS SCIENCE↗

Prospects for Simulating Macromolecular Surfactant Chemistry at the Ocean-Atmosphere Boundary

Biogenic lipids and polymers are surveyed for their ability to adsorb at the water-air interfaces associated with bubbles, marine microlayers and particles in the overlying boundary layer. Representative ocean biogeochemical regimes are defined in order to estimate local concentrations for the major macromolecular classes. Surfactant equilibria and maximum excess are then derived based on a network of model compounds. Relative local coverage and upward mass transport follow directly, and specific chemical structures can be placed into regional rank order. Lipids and denatured protein-like polymers dominate at the selected locations. The assigned monolayer phase states are variable, whether assessed along bubbles or at the atmospheric spray droplet perimeter. Since oceanic film compositions prove to be irregular, effects on gas and organic transfer are expected to exhibit geographic dependence as well. Moreover, the core arguments extend across the sea-air interface into aerosol-cloud systems. Fundamental nascent chemical properties including mass to carbon ratio and density depend strongly on the geochemical state of source waters. High surface pressures may suppress the Kelvin effect, and marine organic hygroscopicities are almost entirely unconstrained. While bubble adsorption provides a well-known means for transporting lipidic or proteinaceous material into sea spray, the same cannot be said of polysaccharides. Carbohydrates tend to be strongly hydrophilic so that their excess carbon mass is low despite stacked polymeric geometries. Since sugars are abundant in the marine aerosol, gel-based mechanisms may be required to achieve uplift. Uncertainties in the surfactant logic distill to a global scale dearth of information regarding two dimensional kinetics and equilibria. Nonetheless simulations are recommended, to initiate the process of systems level quantification.

aerosol↗

Deep learning symmetries and their Lie groups, algebras, and subalgebras from first principles

Abstract We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the symmetry transformations and the corresponding generators. The constructed loss functions ensure that the applied transformations are symmetries and the corresponding set of generators forms a closed (sub)algebra. Our procedure is validated with several examples illustrating different types of conserved quantities preserved by symmetry. In the process of deriving the full set of symmetries, we analyze the complete subgroup structure of the rotation groups SO (2), SO (3), and SO (4), and of the Lorentz group S O ( 1 , 3 ) . Other examples include squeeze mapping, piecewise discontinuous labels, and SO (10), demonstrating that our method is completely general, with many possible applications in physics and data science. Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.

97 MATHEMATICS AND COMPUTING↗

SymbolNet: neural symbolic regression with adaptive dynamic pruning for compression

Abstract Compact symbolic expressions have been shown to be more efficient than neural network (NN) models in terms of resource consumption and inference speed when implemented on custom hardware such as field-programmable gate arrays (FPGAs), while maintaining comparable accuracy (Tsoi et al 2024 EPJ Web Conf. 295 09036). These capabilities are highly valuable in environments with stringent computational resource constraints, such as high-energy physics experiments at the CERN Large Hadron Collider. However, finding compact expressions for high-dimensional datasets remains challenging due to the inherent limitations of genetic programming (GP), the search algorithm of most symbolic regression (SR) methods. Contrary to GP, the NN approach to SR offers scalability to high-dimensional inputs and leverages gradient methods for faster equation searching. Common ways of constraining expression complexity often involve multistage pruning with fine-tuning, which can result in significant performance loss. In this work, we propose S y m b o l N e t , a NN approach to SR specifically designed as a model compression technique, aimed at enabling low-latency inference for high-dimensional inputs on custom hardware such as FPGAs. This framework allows dynamic pruning of model weights, input features, and mathematical operators in a single training process, where both training loss and expression complexity are optimized simultaneously. We introduce a sparsity regularization term for each pruning type, which can adaptively adjust its strength, leading to convergence at a target sparsity ratio. Unlike most existing SR methods that struggle with datasets containing more than O ( 10 ) inputs, we demonstrate the effectiveness of our model on the LHC jet tagging task (16 inputs), MNIST (784 inputs), and SVHN (3072 inputs).

Tsoi, Ho Fung (ORCID:0000000225502184)↗

American cities in a time of global environmental change: the case of the Baltimore Social-Environmental Collaborative

The Baltimore Social-Environmental Collaborative (BSEC) Urban Integrated Field Laboratory seeks a new paradigm for urban climate research. Motivated by deep uncertainties in urban climate and the future of urban systems, BSEC works collaboratively across institutions and stakeholder groups to co-generate the science needed to advance energy security and resilience to extreme events across the city of Baltimore, Maryland, USA, and to do so in a manner that can inform similar efforts in other cities. BSEC begins with stakeholder priorities (health, affordable energy, etc) and designs observation networks and models to deliver climate science to address them. This takes the form of an iterative collaborative cycle, in which an initial research strategy is repeatedly updated in conversation with community partners, and researchers and stakeholders learn from each other. To date, this cycle has included multiple rounds of collaborative deliberation on urban heat mitigation, in which a multicriteria decision tool has been updated with more community-relevant spatial structure and modified optimization metrics. The guiding objective of this cycle is to inform potential ‘secure and resilient pathways’ for energy and infrastructure. In doing so, BSEC addresses fundamental urban science questions in natural and social sciences. It also tests our ability to integrate this science in a manner that advances participatory decision-making for urban resilience.

climate↗

cMonkey2: Automated, systematic, integrated detection of co-regulated gene modules for any organism

The cMonkey integrated biclustering algorithm identifies conditionally co-regulated modules of genes (biclusters). cMonkey integrates various orthogonal pieces of information which support evidence of gene co-regulation, and optimizes biclusters to be supported simultaneously by one or more of these prior constraints. The algorithm served as the cornerstone for constructing the first global, predictive Environmental Gene Regulatory Influence Network (EGRIN) model for a free-living cell, and has now been applied to many more organisms. However, due to its computational inefficiencies, long run-time and complexity of various input data types, cMonkey was not readily usable by the wider community. To address these primary concerns, we have significantly updated the cMonkey algorithm and refactored its implementation, improving its usability and extendibility. These improvements provide a fully functioning and user-friendly platform for building co-regulated gene modules and the tools necessary for their exploration and interpretation. We show, via three separate analyses of data for E. coli, M. tuberculosis and H. sapiens, that the updated algorithm and inclusion of novel scoring functions for new data types (e.g. ChIP-seq and transcription factor over-expression [TFOE]) improve discovery of biologically informative co-regulated modules. The complete cMonkey2 software package, including source code, is available at https://github.com/baliga-lab/cmonkey2.

59 BASIC BIOLOGICAL SCIENCES↗

Deep neural network for the dielectric response of insulators

In this work, we introduce a deep neural network to model in a symmetry preserving way the environmental dependence of the centers of the electronic charge. The model learns from ab initio density functional theory, wherein the electronic centers are uniquely assigned by the maximally localized Wannier functions. When combined with the deep potential model of the atomic potential energy surface, the scheme predicts the dielectric response of insulators for trajectories inaccessible to direct ab initio simulation. The scheme is nonperturbative and can capture the response of a mutating chemical environment. We demonstrate the approach by calculating the infrared spectra of liquid water at standard conditions, and of ice under extreme pressure, when it transforms from a molecular to an ionic crystal.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗