On the development of steady-state and dynamic mass-constrained neural networks using noisy transient data
Not provided.
Computer Science↗
SEARCH · Engineering Papers
Results for “Dynamic networks”
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.
Continuous-time echo state networks for predicting power system dynamics
Not Available
24 POWER TRANSMISSION AND DISTRIBUTION↗
Lytic polysaccharide monooxygenase synergized with lignin-degrading enzymes for efficient lignin degradation
Even though the discovery of lytic polysaccharide monooxygenases (LPMOs) has fundamentally shifted our understanding of biomass degradation, most of the current studies focused on their roles in carbohydrate oxidation. However, no study demonstrated if LPMO could directly participate to the process of lignin degradation in lignin-degrading microbes. This study showed that LPMO could synergize with lignin-degrading enzymes for efficient lignin degradation in white-rot fungi. The transcriptomics analysis of fungi Irpex lacteus and Dichomitus squalens during their lignocellulosic biomass degradation processes surprisingly highlighted that LPMOs co-regulated with lignin-degrading enzymes, indicating their more versatile roles in the redox network. Biochemical analysis further confirmed that the purified LPMO from I. lacteus CD2 could use diverse electron donors to produce H 2 O 2 , drive Fenton reaction, and synergize with manganese peroxidase for lignin oxidation. The results thus indicated that LPMO might uniquely leverage the redox network toward dynamic and efficient degradation of different cell wall components.
59 BASIC BIOLOGICAL SCIENCES↗
Probing criticality with deep learning in relativistic heavy-ion collisions
Systems with different interactions could develop the same critical behavior due to the underlying symmetry and universality. Using this principle of universality, we can embed critical correlations modeled on the 3D Ising model into the simulated data of heavy-ion collisions, hiding weak signals of a few inter-particle correlations within a large particle cloud. Employing a point cloud network with dynamical edge convolution, we are able to identify events with critical fluctuations through supervised learning, and pick out a large fraction of signal particles used for decision-making in each single event.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs
Not Available
97 MATHEMATICS AND COMPUTING↗
Chemodiversity of riverine dissolved organic matter: Effects of local environments and watershed characteristics
Riverine dissolved organic matter (DOM) is crucial to global carbon cycling and aquatic ecosystems. However, the geographical patterns and environmental correlates of DOM chemodiversity remain elusive especially in surface waters and sediments of global rivers. Here, we systematically analyzed DOM molecular diversity and composition in surface waters and sediments across 97 globally distributed rivers using data from the Worldwide Hydrobiogeochemistry Observation Network for Dynamic River Systems (WHONDRS) consortium. Here, we further examined the associations of molecular richness and composition with geographical, climatic, physicochemical variables, as well as the watershed characteristics. We found that molecular richness significantly decreased toward higher latitudes, but only in sediments (r = -0.24, P < 0.001). The environmental variables like precipitation and non-purgeable organic carbon showed strong associations with DOM molecular richness and composition. Interestingly, we identified that less-documented factors like watershed characteristics were also related to DOM molecular richness and composition, and were stronger in waters than sediments. Such associations were further supported by the fact that 11 out of 13 watershed characteristics (e.g., land cover variables) showed more positive than negative correlations with molecular abundance especially in waters. The molecules positively and negatively correlated with specific watershed characteristics had distinct traits, such as stoichiometric ratios and aromaticity. Land covers shifted from natural (e.g., forests) to human-modified (e.g., impervious area) were associated with systematic changes in DOM molecular chemistry. Our findings imply that it may be possible to use a small set of broadly available data types to predict DOM molecular richness and composition across diverse river systems. Elucidation of mechanisms underlying these relationships will provide further enhancements to such predictions, especially when extrapolating to unsampled systems.
54 ENVIRONMENTAL SCIENCES↗
Molecular transport enhancement in pure metallic carbon nanotube porins
Nanofluidic channels impose extreme confinement on water and ions, giving rise to unusual transport phenomena strongly dependent on the interactions at the channel–wall interface. Yet how the electronic properties of the nanofluidic channels influence transport efficiency remains largely unexplored. Here we measure transport through the inner pores of sub-1 nm metallic and semiconducting carbon nanotube porins. We find that water and proton transport are enhanced in metallic nanotubes over semiconducting nanotubes, whereas ion transport is largely insensitive to the nanotube bandgap value. Molecular simulations using polarizable force fields highlight the contributions of the anisotropic polarizability tensor of the carbon nanotubes to the ion–nanotube interactions and the water friction coefficient. We also describe the origin of the proton transport enhancement in metallic nanotubes using deep neural network molecular dynamics simulations. Finally, these results emphasize the complex role of the electronic properties of nanofluidic channels in modulating transport under extreme nanoscale confinement.
77 NANOSCIENCE AND NANOTECHNOLOGY↗
Molecular diversity of dissolved organic matter reflects macroecological patterns in river networks
Deciphering dissolved organic matter (DOM) molecular complexity is crucial for understanding ecosystem function. Using the continental-scale Worldwide Hydrobiogeochemistry Observation Network for Dynamic Rivers Systems (WHONDRS) Fourier-transform ion cyclotron resonance mass spectrometry (FTICR-MS) dataset, we reveal fundamental scaling patterns of DOM chemodiversity with watershed characteristics. Analysis of 54 river sites shows local and regional watershed features significantly influence DOM chemodiversity (2500–8718 unique formulae), exhibiting consistent scaling patterns across compound classes and a novel latitudinal gradient (decreasing diversity with increasing latitude). Scaling relationships for DOM composition vary by compound class. Crucially, the scaling parameters (B, baseline chemodiversity; Z, sensitivity) are linearly interrelated. This B–Z relationship is most robust for potentially bio-labile carbohydrates (coefficient of determination R 2 ≈ 0.85), diminishing for recalcitrant, plant-derived molecules (such as lignin), and indicates (potential) biolability-dependent coupling between baseline diversity and environmental responsiveness. These quantitative scaling relationships, with scaling exponents ranging from − 2.1 to 2.2 across compound classes, enable prediction of DOM composition across watersheds, offering a framework to understand ecosystem responses to environmental change. This research bridges biogeochemistry and ecology, providing tools to anticipate molecular transformations across scales.
59 BASIC BIOLOGICAL SCIENCES↗
Predicting impurity spectral functions using machine learning
The Anderson Impurity Model (AIM) is a canonical model of quantum many-body physics. Here we investigate whether machine learning models, both neural networks (NN) and kernel ridge regression (KRR), can accurately predict the AIM spectral function in all of its regimes, from empty orbital, to mixed valence, to Kondo. To tackle this question, we construct two large spectral databases containing approximately 410 000 and 600 000 spectral functions of the single-channel impurity problem. We show that the NN models can accurately predict the AIM spectral function in all of its regimes, with pointwise mean absolute errors down to 0.003 in normalized units. We find that the trained NN models outperform models based on KRR and enjoy a speedup on the order of 10 5 over traditional AIM solvers. Finally, the required size of the training set of our model can be significantly reduced using farthest point sampling in the AIM parameter space, which is important for generalizing our method to more complicated multichannel impurity problems of relevance to predicting the properties of real materials.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Convolutional neural networks for large-scale dynamical modeling of itinerant magnets
Not Available
Cheng, Xinlun (ORCID:0000000270093957)↗
NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning
Spiking Neural Networks (SNNs) are computational models inspired by the event-driven communication and connectivity patterns of biological neural circuits. They enable high energy efficiency and natural support for diverse architectures ranging from layered networks to small-world and graphstructured topologies. In this work, we introduce NeuroCoreX, an open-source, FPGA-based spiking neural network emulator that provides real-time, on-chip learning and flexible network organization. NeuroCoreX supports both feedforward sensory inputs streamed directly from sensors or PCs via UART and recurrent on-chip connectivity, enabling simultaneous processing and learning from external stimuli and internal network dynamics-capabilities rarely available in existing FPGA SNN platforms. The system implements a Leaky Integrate-and-Fire (LIF) neuron model with current-based synapses and supports pair-based STDP learning on both feedforward and recurrent synapses. A lightweight Python interface enables interactive configuration, live monitoring, weight read-back, and experiment control. Importantly, NeuroCoreX is tightly integrated with the SuperNeuroMAT simulator, allowing SNN models to be transferred seamlessly from software to hardware for hardware-in-the-loop development. By combining real-time plasticity, flexible connectivity, and an open-source VHDL implementation, NeuroCoreX provides an extensible and accessible platform for neuromorphic research, algorithm-hardware co-design, and energy-efficient edge intelligence.
Gautam, Ashish [ORNL]↗
Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches
In superconducting magnets, the irreversible transition of a portion of the conductor to resistive state is called a “quench.” Having large stored energy, magnets can be damaged by quenches due to localized heating, high voltage, or large force transients. Unfortunately, current quench protection systems can only detect a quench after it happens, and mitigating risks in Low Temperature Superconducting (LTS) accelerator magnets often requires fast response (down to ms). Additionally, protection of High Temperature Superconducting (HTS) magnets is still suffering from prohibitively slow quench detection. In this study, we lay the groundwork for a quench prediction system using an auto-encoder fully-connected deep neural network. After dynamically trained with data features extracted from acoustic sensors around the magnet, the system detects anomalous events seconds before the quench in most of our data. While the exact nature of the events is under investigation, we show that the system can “forecast” a quench before it happens under magnet training conditions through a randomized experiment. This opens up the way of integrated data processing, potentially leading to faster and better diagnostics and detection of magnet quenches
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
Approximating Trajectory Constraints With Machine Learning – Microgrid Islanding With Frequency Constraints
Here, we introduce deep earning aided constraint encoding to tackle the frequency-constraint microgrid scheduling problem. The nonlinear function between system operating condition and frequency nadir is approximated by using a neural network, which admits an exact mixed-integer formulation (MIP). This formulation is then integrated with the scheduling problem to encode the frequency constraint. With the stronger representation power of the neural network, the resulting commands can ensure adequate frequency response in a realistic setting in addition to islanding success. The proposed method is validated on a modified 33-node system. Successful islanding with a secure response is simulated under the scheduled commands using a detailed three-phase model in Simulink. The advantages of our model are particularly remarkable when the inertia emulation functions from wind turbine generators are considered.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Closed-loop additive manufacturing of upcycled commodity plastic through dynamic cross-linking
A sustainable closed-loop manufacturing would become reality if commodity plastics can be upcycled into higher-performance materials with facile processability. Such circularity will be realized when the upcycled plastics can be (re)processed into custom-designed structures through energy/resource-efficient additive manufacturing methods, especially by approachable and scalable fused filament fabrication (FFF). Here, we introduce a circular model epitomized by upcycling a prominent thermoplastic, acrylonitrile butadiene styrene (ABS) into a recyclable, robust adaptive dynamic covalent network (ABS-vitrimer) (re)printable via FFF. The full FFF processing of ABS-vitrimer overcomes the major challenge of (re)printing cross-linked materials and produces stronger, tougher, solvent-resistant three-dimensional objects directly reprintable and separable from unsorted plastic waste. This study thus offers an imminently adoptable approach for advanced manufacturing toward the circular plastics economy.
36 MATERIALS SCIENCE↗
The mechanics of plant morphogenesis
Understanding the mechanism by which patterned gene activity leads to mechanical deformation of cells and tissues to create complex forms is a major challenge for developmental biology. Plants offer advantages for addressing this problem because their cells do not migrate or rearrange during morphogenesis, which simplifies analysis. We synthesize results from experimental analysis and computational modeling to show how mechanical interactions between cellulose fibers translate through wall, cell, and tissue levels to generate complex plant tissue shapes. Genes can modify mechanical properties and stresses at each level, though the values and pattern of stresses differ from one level to the next. Here, the dynamic cellulose network provides elastic resistance to deformation while allowing growth through fiber sliding, which enables morphogenesis while maintaining mechanical strength.
59 BASIC BIOLOGICAL SCIENCES↗
The Computational Capacity of Mem-LRC Reservoirs
Reservoir computing has a emerged as a powerful tool in data-driven time series analysis. The possibility of utilizing hardware reservoirs as specialized co-processors has generated interest in the properties of electronic reservoirs, especially those based on memristors as the nonlinearity of these devices should translate to an improved nonlinear computational capacity of the reservoir. However, designing these reservoirs requires a detailed understanding of how memristive networks process information which has thus far been lacking. In this work, we derive an equation for general memristor-inductor-resistor-capacitor (MEM-LRC) reservoirs that includes all network and dynamical constraints explicitly. Utilizing this we undertake a study of the computational capacity of these reservoirs. We demonstrate that hardware reservoirs may be constructed with extensive memory capacity and that the presence of memristors enacts a tradeoff between memory capacity and nonlinear computational capacity. Here, using these principles, we design reservoirs to tackle problems in signal processing, paving the way for applying hardware reservoirs to high-dimensional spatiotemporal systems.
Circuits with memory↗