SEARCH · Engineering Papers
Results for “space networking”
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.
Understanding the Design Space of Sparse/Dense Multiphase Dataflows for Mapping Graph Neural Networks on Spatial Accelerators.
Abstract not provided.
Unsupervised learning for identifying events in active target experiments
This article presents novel applications of unsupervised machine learning methods to the problem of event separation in an active target detector, the Active-Target Time Projection Chamber (AT-TPC). The overarching goal is to group similar events in the early stages of the data analysis, thereby improving efficiency by limiting the computationally expensive processing of unnecessary events. The application of unsupervised clustering algorithms to the analysis of two-dimensional projections of particle tracks from a resonant proton scattering experiment on 46 Ar is introduced. We explore the performance of autoencoder neural networks and a pre-trained VGG16 Simonyan and Zisserman (2015) convolutional neural network. We study clustering performance on both data from a simulated 46 Ar experiment, and real events from the AT-TPC detector. We find that a -means algorithm applied to simulated data in the VGG16 latent space forms almost perfect clusters. Additionally, the VGG16+-means approach finds high purity clusters of proton events for real experimental data. Here, we also explore the application of clustering the latent space of autoencoder neural networks for event separation. While these networks show strong performance, they suffer from high variability in their results.
Streamlining latent spaces in machine learning using moment pooling
Many machine learning applications involve learning a latent representation of data, which is often high-dimensional and difficult to directly interpret. In this work, we propose “moment pooling,” a natural extension of deep sets networks which drastically decreases the latent space dimensionality of these networks while maintaining or even improving performance. Moment pooling generalizes the summation in deep sets to arbitrary multivariate moments, which enables the model to achieve a much higher effective latent dimensionality for a fixed learned latent space dimension. We demonstrate moment pooling on the collider physics task of quark/gluon jet classification by extending energy flow networks (EFNs) to moment EFNs. We find that moment EFNs with latent dimensions as small as 1 perform similarly to ordinary EFNs with higher latent dimension. This small latent dimension allows for the internal representation to be directly visualized and interpreted, which in turn enables the learned internal jet representation to be extracted in closed form. Published by the American Physical Society 2024
Cross-Feature Transfer Learning for Efficient Tensor Program Generation
Tuning tensor program generation involves navigating a vast search space to find optimal program transformations and measurements for a program on the target hardware. The complexity of this process is further amplified by the exponential combinations of transformations, especially in heterogeneous environments. This research addresses these challenges by introducing a novel approach that learns the joint neural network and hardware features space, facilitating knowledge transfer to new, unseen target hardware. A comprehensive analysis is conducted on the existing state-of-the-art dataset, TenSet, including a thorough examination of test split strategies and the proposal of methodologies for dataset pruning. Leveraging an attention-inspired technique, we tailor the tuning of tensor programs to embed both neural network and hardware-specific features. Notably, our approach substantially reduces the dataset size by up to 53% compared to the baseline without compromising Pairwise Comparison Accuracy (PCA). Furthermore, our proposed methodology demonstrates competitive or improved mean inference times with only 25–40% of the baseline tuning time across various networks and target hardware. The attention-based tuner can effectively utilize schedules learned from previous hardware program measurements to optimize tensor program tuning on previously unseen hardware, achieving a top-5 accuracy exceeding 90%. This research introduces a significant advancement in autotuning tensor program generation, addressing the complexities associated with heterogeneous environments and showcasing promising results regarding efficiency and accuracy.
Perivascular network segmentations derived from high-field MRI and their implications for perivascular and parenchymal mass transport in the rat brain
A custom segmentation workflow was applied to ex vivo high-field MR images of rat brains acquired following in vivo intraventricular contrast agent infusion to generate maps of the perivascular spaces (PVS). The resulting perivascular network segmentations enabled analysis of perivascular connections to the ventricles, parenchymal solute clearance, and dispersive solute transport within PVS. Numerous perivascular connections between the brain surface and the ventricles suggest the ventricles integrate into a PVS-mediated clearance system and raise the possibility of cerebrospinal fluid (CSF) return from the subarachnoid space to the ventricles via PVS. Assuming rapid solute exchange between the PVS and CSF spaces primarily by advection, the extensive perivascular network decreased the mean clearance distance from parenchyma to the nearest CSF compartment resulting in an over 21-fold reduction in the estimated diffusive clearance time scale, irrespective of solute diffusivity. This corresponds to an estimated diffusive clearance time scale under 10 min for amyloid-beta which suggests that the widespread distribution of PVS may render diffusion an effective parenchymal clearance mechanism. Additional analysis of oscillatory solute dispersion within PVS indicates that advection rather than dispersion is likely the primary transport mechanism for dissolved compounds greater than 66 kDa in the long (> 2 mm) perivascular segments identified here, although dispersion may be significant for smaller compounds in shorter perivascular segments.
Control simulations of many-body quantum systems by a synergism of discrete real-time learning and optimal control theory
We present a self-consistent algorithm for optimal control simulations of many-body quantum systems. The algorithm features a two-step synergism that combines discrete real-time machine learning (DRTL) with Quantum Optimal Control Theory (QOCT) using the time-dependent Schrödinger equation. Specifically, in step (1), DRTL is employed to identify a compact working space (i.e., the important portion of the Hilbert space) for the time evolution of the many-body quantum system in the presence of a control field (i.e., the initial or previously updated field), and in step (2), QOCT utilizes the DRTL-determined working space to find a newly updated control field for a chosen objective. Steps 1 and 2 are iterated until a self-consistent control objective value is reached such that the resulting optimal control field yields the same targeted objective value when the corresponding working space is systematically enlarged. Furthermore, to demonstrate this two-step self-consistent DRTL-QOCT synergistic algorithm, we perform optimal control simulations of strongly interacting 1D as well as 2D Heisenberg spin systems. In both scenarios, only a single spin (at the left end site for 1D and the upper left corner site for 2D) is driven by the time-dependent control fields to create an excitation at the opposite site as the target. It is found that, starting from all spin-down zero excitation states, the synergistic method is able to identify working spaces and convergence of the desired controlled dynamics with just a few iterations of the overall algorithm. In the cases studied, the dimensionality of the working space scales only quasi-linearly with the number of spins.
INL Senior Project
What did my team set out to accomplish:? Can I put a custom Machine Learning Model on FPGA?? Can I analyze network traffic in real time?? Can a QSFP port be used with an FPGA?? Does a visual representation of the latent space enhance our understanding of network traffic?? What is QSFP QSFP (Quad Small Form-Factor Pluggable)? QSFP supports transfer speeds generally up to 100Gb/s? Runs 4 parallel lines running up to 28 Gb/s? Why the latent space is important to our project ?Latent space is the compressed mapping of data points in a non-linear fashion? Create an understanding of the relationship of data collected? Can represent that relationship of a single network packet in 3 points (X, Y, Z) Project Outline FPGA? Custom Xilinx Petalinux Image for the operating system? Python program to collect packets and run them through the DPU (Data Processing Unit)? The program then sends the information over a socket to a computer? Display Program? Python Program that collects the information sent from the FPGA and display it in a graph
Reactor Network Analysis with Various Reaction Mechanisms to Investigate Hydrogen vs. Methane Fuel at Varying Flame Temperatures with Experimental Data
Emissions data were evaluated for a set of test hardware that adapts Collins Aerospace’s aeroengine liquid fueled injector technology to a ground-based turbine. The hardware was specifically developed to operate on 100% hydrogen; however it has the ability to operate on both pure methane and hydrogen and mixtures in between. 16 injector configurations and seven factors (air split, fuel and air swirl, pressure drop, preheat temperature, fuel composition, and flame temperature) were investigated based on a Box Behnken statistical model. Of the 16, configuration 3 was selected for further discussion being in the middle of the statistical design space. A chemical reactor network was developed based on the experimental data obtained and was assessed with three different mechanisms: GRI Mech 3.0, UCSD, and Galway. All factors were held constant except the fuel composition to directly compare chemical pathways for methane and hydrogen. This study was conducted across different flame temperatures of 1500K, 1675K, and 1850K for both hydrogen and methane. Additional lower flame temperatures of 1100K and 1300K were evaluated for hydrogen. Moreover, results for fully premixed and non-premixed results were compared to obtain information on the implications of mixedness on emissions. These results were compared with the Leonard and Stegmaier plot for methane and a similar plot was constructed for hydrogen.
Reliable extrapolation of deep neural operators informed by physics or sparse observations
Deep neural operators can learn nonlinear mappings between infinite-dimensional function spaces via deep neural networks. As promising surrogate solvers of partial differential equations (PDEs) for real-time prediction, deep neural operators such as deep operator networks (DeepONets) provide a new simulation paradigm in science and engineering. Pure data-driven neural operators and deep learning models, in general, are usually limited to interpolation scenarios, where new predictions utilize inputs within the support of the training set. However, in the inference stage of real-world applications, the input may lie outside the support, i.e., extrapolation is required, which may result to large errors and unavoidable failure of deep learning models. Here, we address this challenge of extrapolation for deep neural operators. First, we systematically investigate the extrapolation behavior of DeepONets by quantifying the extrapolation complexity, via the 2-Wasserstein distance between two function spaces and propose a new strategy of bias–variance trade-off for extrapolation with respect to model capacity. Subsequently, we develop a complete workflow, including extrapolation determination, and we propose five reliable learning methods that guarantee a safe prediction under extrapolation by requiring additional information—the governing PDEs of the system or sparse new observations. The proposed methods are based on either fine-tuning a pre-trained DeepONet or multifidelity learning. We demonstrate the effectiveness of the proposed framework for various types of parametric PDEs. Furthermore, our systematic comparisons provide practical guidelines for selecting a proper extrapolation method depending on the available information, desired accuracy, and required inference speed.
Active deep kernel learning of molecular properties from structural embeddings
As vast databases of chemical identities become increasingly available, the challenge shifts to how we effectively explore and leverage these resources to study molecular properties. This paper presents an active learning approach for molecular discovery using deep kernel learning (DKL), demonstrated on the QM9 dataset. DKL links structural embeddings directly to properties, creating organized latent spaces that prioritize relevant property information. By iteratively recalculating embedding vectors in alignment with target properties, DKL uncovers concentrated maxima representing key molecular properties and reveals unexplored regions with potential for innovation. This approach underscores DKL’s potential in advancing molecular research and discovery.
Representations and strategies for transferable machine learning improve model performance in chemical discovery
Strategies for machine-learning (ML)-accelerated discovery that are general across material composition spaces are essential, but demonstrations of ML have been primarily limited to narrow composition variations. By addressing the scarcity of data in promising regions of chemical space for challenging targets such as open-shell transition-metal complexes, general representations and transferable ML models that leverage known relationships in existing data will accelerate discovery. Over a large set (~1000) of isovalent transition-metal complexes, we quantify evident relationships for different properties (i.e., spin-splitting and ligand dissociation) between rows of the Periodic Table (i.e., 3d/4d metals and 2p/3p ligands). We demonstrate an extension to the graph-based revised autocorrelation (RAC) representation (i.e., eRAC) that incorporates the group number alongside the nuclear charge heuristic that otherwise overestimates dissimilarity of isovalent complexes. To address the common challenge of discovery in a new space where data are limited, we introduce a transfer learning approach in which we seed models trained on a large amount of data from one row of the Periodic Table with a small number of data points from the additional row. We demonstrate the synergistic value of the eRACs alongside this transfer learning strategy to consistently improve model performance. Analysis of these models highlights how the approach succeeds by reordering the distances between complexes to be more consistent with the Periodic Table, a property we expect to be broadly useful for other material domains.
Integration of urban science and urban climate adaptation research: opportunities to advance climate action
There is a growing recognition that responding to climate change necessitates urban adaptation. We sketch a transdisciplinary research effort, arguing that actionable research on urban adaptation needs to recognize the nature of cities as social networks embedded in physical space. Given the pace, scale and socioeconomic outcomes of urbanization in the Global South, the specificities and history of its cities must be central to the study of how well-known agglomeration effects can facilitate adaptation. The proposed effort calls for the co-creation of knowledge involving scientists and stakeholders, especially those historically excluded from the design and implementation of urban development policies.
Anomalous temperature dependence of the experimental x-ray structure factor of supercooled water
The structural changes of water upon deep supercooling were studied through wide-angle x-ray scattering at SwissFEL. The experimental setup had a momentum transfer range of 4.5 Å-1, which covered the principal doublet of the x-ray structure factor of water. The oxygen–oxygen structure factor was obtained for temperatures down to 228.5 ± 0.6 K. Similar to previous studies, the second diffraction peak increased strongly in amplitude as the structural change accelerated toward a local tetrahedral structure upon deep supercooling. We also observed an anomalous trend for the second peak position of the oxygen–oxygen structure factor (q 2 ). We found that q 2 exhibits an unprecedented positive partial derivative with respect to temperature for temperatures below 236 K. Based on Fourier inversion of our experimental data combined with reference data, we propose that the anomalous q 2 shift originates from that a repeat spacing in the tetrahedral network, associated with all peaks in the oxygen–oxygen pair-correlation function, gives rise to a less dense local ordering that resembles that of low-density amorphous ice. The findings are consistent with that liquid water consists of a pentamer-based hydrogen-bonded network with low density upon deep supercooling.
Optical noise in a free-space quantum communications link from natural and nuclear disturbed environments*
Satellite communications at radio frequencies can experience a ‘blackout’ period following the atmospheric detonation of a nuclear weapon. The wavelengths used for free-space quantum communications will not incur the same ‘blackout’ effects from a nuclear detonation, but the optical systems will suffer from a phenomenon called redout. Redout occurs in an optical detector when ambient light scatters into the optical receiver, causing elevated background photon counts in the detector such that background noise overwhelms the signal. In this work, the duration of the redout effect is quantified from a nuclear disturbed environment on a ground-to-space quantum optical link. In addition, we comment on various techniques for reducing ambient and nuclear disturbed background counts in a quantum free-space optical link. For low-altitude nuclear detonations (i.e., under 50 km), the maximum interference time will be less than 1 min. Implementing a telescope, timing gate, and wavelength filter to the detector can reduce the background counts in the detector significantly. Aerosol levels and ground albedo are major contributors to background noise in a ground-to-satellite quantum channel, and ground station location should factor in both variables.
Graph reinforcement learning for exploring model spaces beyond the standard model
We present a methodology for performing scans of beyond the standard model (BSM) parameter spaces with reinforcement learning. We identify a novel procedure using graph neural networks that is capable of exploring spaces of models without the user specifying a fixed particle content, allowing broad classes of BSM models to be explored—in theory, the technique is applicable to nearly any model space with a prespecified gauge group. We provide a generic procedure by which a suitable graph grammar can be developed for any BSM model that features user-specified symmetry groups and a finite number of different possible particle species, the use of which is applicable to a variety of machine learning tasks over the actions of BSM theories beyond our particular reinforcement learning use case. As a proof of concept, we construct the graph grammar for theories with vectorlike leptons that may or may not be charged under a dark U ( 1 ) group, inspired by portal matter extensions of the sub-GeV vector portal/kinetic mixing simplified dark matter models. We then use this graph grammar to create a reinforcement learning environment tasked with creating models with these vectorlike leptons that are consistent with a list of a variety of precision observables. The reinforcement learning agent succeeds in developing models that can address the observed muon anomalous magnetic moment discrepancy while remaining consistent with flavor violation and electroweak precision observables, including both constructions that have previously been studied as well as new models that have not, to our knowledge, previously been identified. By inspecting the resulting ensembles of models that the agent produces and experimenting with different configurations for our reinforcement learning environment and graph grammar, we also infer various lessons about the development of these environments that can be transferable to reinforcement learning scans of more complicated model spaces and comment on future directions for the development of this technique into a more mature tool. Published by the American Physical Society 2025
Optimal Energy Scheduling and Sensitivity Analysis for Integrated Power-Water-Heat Systems
The conventionally independent power, water, and heating networks are becoming more tightly connected, which motivates their joint optimal energy scheduling to improve the overall efficiency of an integrated energy system. However, such a joint optimization is known as a challenging problem with complex network constraints and couplings of electric, hydraulic, and thermal models that are nonlinear and nonconvex. We formulate an optimal power-water-heat flow (OPWHF) problem and develop a computationally efficient heuristic to solve it. The proposed heuristic decomposes OPWHF into subproblems, which are iteratively solved via convex relaxation and convex-concave procedure. Simulation results validate that the proposed framework can improve operational flexibility and social welfare of the integrated system, wherein the water and heating networks respond as virtual energy storage to time-varying energy prices and solar photovoltaic generation. Moreover, we perform sensitivity analysis to compare two modes of heating network control: by flow rate and by temperature. Our results reveal that the latter is more effective for heating networks with a wider space of pipeline parameters.
Dtc Commercialization Software Package
This code is the complete software and firmware components supporting DTC model radios H2 and BluSDR6. This software package contains all the hardware boot up code/config files(BSP), user space Linux code (Web, Network, MAC (media access control) & drivers), the field programable gate array HDL (hardware description language) code and the build environment to compile and organize these components together to work in the aforementioned radios. Additional details of these components are as follows: • Hardware support components o Board support package and configuration files o uBoot • Linux Components: o The web components include the user interface for setup, configuration, and status components of the system. o Vulture code configures the radio’s IP network, configures radio parameters and runs the MAC layer of the radio. • The Field Programmable Gate Array HDL contains hardware drivers, interface logic to go between the software to the physical layer and the radio hardware as well as the logic for the physical layer of the radio. • Build environment includes compilers and config files that compile and organize all the other components to be able to be run on the radios.