Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative modeling”

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 559 records · Page 31

Generative unfolding with distribution mapping

Machine learning enables unbinned, highly-differential cross section measurements. A recent idea uses generative models to morph a starting simulation into the unfolded data. We show how to extend two morphing techniques, Schrödinger Bridges and Direct Diffusion, in order to ensure that the models learn the correct conditional probabilities. This brings distribution mapping (DM) to a similar level of accuracy as the state-of-the-art conditional generative unfolding methods. Numerical results are presented with a standard benchmark dataset of single jet substructure as well as for a new dataset describing a 22-dimensional phase space of Z+2 -jets.

Butter, Anja↗

Integration of real-time measurements and atomistic modeling to license nuclear components

An improved testing and data gathering method is described herein with reference to testing a new fuel, as an exemplary component to be tested for licensure purposes. The method includes generally: generating models for the new system; making samples and getting them accepted for a reactor; and testing the samples in a test or commercial reactor until the exposure time is reached for the expected cycle length of the fuel at final use. The method is preferably done concurrent to submitting a license application for commercial use of the new component to the relevant government body to expedite license testing review.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

A Data-Driven Algorithm for Enabling Delay Tolerance in Resilient Microgrid Controls Using Dynamic Mode Decomposition

The increased implementation of smart grid technologies in the power distribution grid presents unique opportunities that enable resiliency, but also brings challenges motivating needs for novel solutions and mitigation techniques. The bi-directional power and data flow allow for the grid to operate with increased resiliency, which is the ability to avoid discontinuity of service to end-use loads during extreme events. However, in applications where control of the distribution grid or microgrid relies on communication networks, the degradation of communication systems in the form of loss or high latency can cause maloperation and result in loss of end-use loads. Here this paper presents a novel framework to enable delay tolerance of centralized microgrid control schemes to mitigate communication system latency impacts and guarantee successful control action. We demonstrate the delay tolerance on a control scheme that operates a battery energy storage system (BESS) to offset the sudden loss of generation and maintain system frequency. During periods of severely degraded communication system performance, the proposed delay-tolerant algorithm compensates for the latency by utilizing a data-driven model generated at the device level using dynamic mode decomposition (DMD) to determine the performance of the communications. The DMD technique predicts the system’s frequency using device-level terminal measurements and provides updated control signals. The HELICS cosimulation platform evaluates the cyber-physical interaction of the power system model in GridLAB-D, the centralized control agent in Python, and the discrete network model in NS-3. The framework is tested and validated on the IEEE-123 node system modified to represent a networked remote microgrid model, and the results show an improvement in the dynamic performance

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Probabilistic Autoencoder for Type Ia Supernova Spectral Time Series

We construct a physically parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of Type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an autoencoder that is interpreted probabilistically after training using a normalizing flow. We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multistage training setup alongside our physically parameterized network, we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including the automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an rms of 0.091 ± 0.010 mag, which corresponds to 0.074 ± 0.010 mag if peculiar velocity contributions are removed.

79 ASTRONOMY AND ASTROPHYSICS↗

OpenCGRA: An Open-Source Unified Framework for Modeling,Testing, and Evaluating CGRAs

Coarse-grained reconfigurable arrays (CGRAs),loosely defined as arrays of functional units (e.g, adder, sub-tractor, multiplier, divider, or larger multi-operation units, butsmaller than a general-purpose core) interconnected through aNetwork-on-Chip, provide higher flexibility than domain-specificASIC accelerators while offering increased hardware efficiencywith respect to fine-grained reconfigurable devices, such as FieldProgrammable Gate Arrays (FPGAs). The fast evolving fieldsof machine learning and edge computing, which are seeing acontinuous flow of novel algorithms and larger models, makeCGRAs ideal target architectures to allow domain specializationwithout loosing too much generality. They also generally offerquicker and more effective reconfigurability than FPGAs, po-tentially allowing adaptation during actual algorithm execution,and implement a dataflow programming paradigm that adaptswell to these emerging workloads. Designing and generating aCGRA, however, still requires to define the type and number ofthe specific functional units, implement their interconnect andthe network topology, and perform its simulation and validation,given a variety of workloads of interest.In this paper, we propose OpenCGRA, a Python-based unifiedframework that integrates generation, modeling, testing and eval-uation for CGRAs. OpenCGRA is the first open-source integratedframework able to support the full top-to-bottom design flow forspecializing and implementing CGRAs: modeling at different ab-straction levels (functional level, cycle level, register-transfer level),generation, simulation, testing at different granularities (unit test-ing, integration testing, property-based testing), and characteriza-tion (area, power, and timing). OpenCGRAs will be made availableon GitHub.

CGRA, synthesis↗

Technical Report on Modeling for Quasispecies Abundance Inference with Confidence Intervals from Metagenomic Sequence Data

The overall aim of this project is to develop a software package, called MetaQuant, that can determine the constituents of a complex microbial sample and estimate their relative abundances by analysis of metagenomic sequencing data. The goal for Task 1 is to create a generative model describing the stochastic process underlying the creation of sequence read pairs in the data set. The stages in this generative process include the selection of a source genome sequence for each read pair, with probability dependent on its abundance in the sample. The other stages describe the evolution of the source genome from its nearest common ancestor with a reference genome, breakage of the source DNA into short fragments, and the errors in sequencing the ends of the fragments to produce read pairs.

59 BASIC BIOLOGICAL SCIENCES↗

ASSESSING FUEL PROPERTY EFFECTS ON CAVITATION AND EROSION PROPENSITY USING A COMPUTATIONAL FUEL SCREENING TOOL

To advance compression ignition combustion strategies, researchers have evaluated fuel property effects and their impact on achieving higher efficiencies and lower emissions levels relative to current capabilities. Within the Department of Energy's Co-Optima initiative, there has been a recent focus on understanding the influence of fuel properties on fuel injection performance. To help identify candidate fuels that can meet desired injector performance metrics, a computational fuel screening tool is under development that can link fuel properties with the tendency of a given fuel to cavitate and lead to cavitation-induced erosion. In the initial development of this tool, five liquid fuel properties were selected to represent candidate fuels, namely density, viscosity, vapor pressure, surface tension, and heat of vaporization. A design of experiments methodology was employed to generate a set of pseudo fuel cases, which can represent the main effects and interactions among the fuel properties and be related to cavitation erosion predictions. Large eddy simulations were performed using a mixture modeling approach to predict the cavitation and erosion propensity of these pseudo-fuels in terms of the mean fuel vapor mole fraction and stored impact energy from repeated cloud collapse events. The low order regression models generated from this study revealed the importance of liquid fuel density on cavitation formation, whereas liquid viscosity was found to have a strong negative correlation with erosion severity. The surrogate models were then used in the fuel screening tool to rank the cavitation and erosion tendency of four candidate single-component fuels: methyl decanoate, isooctane, ethanol and n-dodecane. While the fuel screening tool was not able to quantitatively predict the cavitation and erosion response metrics, the tool was able to accurately rank the relative cavitation and erosion propensity of the four fuels. Overall, ethanol and iso-octane were observed to produce the highest levels of cavitation and erosion, respectively.

cavitation-induced erosion↗

Engagement: Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations

We present our SciDAC FASTMath-HEP partnership results for tuning generative adversarial models (GANs) for high energy physics applications. The GANs are used in hybrid simulations to accelerate otherwise time-consuming computations. We optimize for both, prediction accuracy and variability with the goal to find GAN architectures that are reliable and robust.

high energy physics↗

Implementation of INCL Nuclear Model in GENIE Generator

The Li ge Intranuclear Cascade (INCL) model is a nuclear-physics model that simulates hadron (baryon, anti-baryon and meson) reactions on nuclei, for incident energies ranging from a few tens of MeV to 10-20 GeV. The INCL model has been well validated by hadron scattering data. In my work, I implement an interface in GENIE to use the INCL nuclear model in the simulations of both the initial state of the target nucleus and the Final State Interaction in neutrino-nucleus interaction. It has a consistent treatment of nuclear models in both neutrino interaction and hadron rescattering. A full event record including neutrino vertex and each vertex of hadron rescattering has been accomplished. Several processes, e.g. cluster production, Delta transportation and de-excitation will also be included as benefits of the implementation of the INCL model in GENIE. I will show some initial simulation results showcasing the new GENIE features and discuss plans for making them available for use in experimental analyses.

Liu, Liang [Fermilab]↗

Potential of Data Center Controls in Grid Services

The rapid proliferation of large data centers brings both challenges and opportunities for grid reliability. The data center resources and their potential flexibility have the potential to contribute resources to grid operations. Through capabilities like energy shifting and resource coordination, data centers can help reduce their net demand on the transmission network, as well as provide additional grid services to support reliable operation on the grid. While transient and long-term grid planning and operations are the scenarios that draw most attention, the quasi-steady state timeseries (QSTS) operation of data centers and grid bring interesting scenarios that can help evaluate the data center controls to aid grid services. This work is focused on modeling data centers for QSTS applications – incorporating the AI data center load profiles and building on the PNNL digital twin model for the thermal management loads to enable simulation studies to reveal the impact of data center controls on grid performance. This includes the integration of a QSTS battery and natural gas generator model to incorporate local resource impacts to the system. The simulation study is performed with a modified IEEE 24-Bus transmission system. Scenarios are focused on evaluating the data center load impacts on the transmission system and leveraging both data center and local generation controls to mitigate those impacts and provide additional grid services. The data center controls revealed the ability to contribute to two main kinds of grid services: preventing congestion on a weak grid by coordinating the data center resources with the collocated BESS and onsite generation; and the ability to help the grid operations during stressed times of operation like during a contingency. Leveraging these and other capabilities has the potential to help data centers become grid responsive assets, aiding in both their integration into the power system and grid reliability.

power grid simulation↗

Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior

The increasing incidence and severity of wildfires underscores the necessity of accurately predicting their behavior. While high-fidelity models derived from first principles offer physical accuracy, they are too computationally expensive for use in real-time fire response. Low-fidelity models sacrifice some physical accuracy and generalizability via the integration of empirical measurements, but enable real-time simulations for operational use in fire response. Machine learning techniques have demonstrated the ability to bridge these objectives by learning first-principles physics while achieving computational speedups. While deep learning approaches have demonstrated the ability to predict wildfire propagation over large time periods, time-resolved fire-spread predictions are needed for active fire management. Here, in this work, we evaluate the ability of deep learning approaches in accurately modeling the time-resolved dynamics of wildfires. We use an autoregressive process in which a convolutional recurrent deep learning model makes predictions that propagate a wildfire over 15 min increments. We apply the model to four simulated datasets of increasing complexity, containing both field fires with homogeneous fuel distribution as well as real-world topologies sampled from the California region of the United States. We show that even after 100 autoregressive predictions representing more than 24 h of simulated fire spread, the resulting models generate stable and realistic propagation dynamics, achieving a Jaccard score between 0.89 and 0.94 when predicting the resulting fire scar. The inference time of the deep learning models are examined and compared, and directions for future work are discussed.

54 ENVIRONMENTAL SCIENCES↗

New representation of the nonlocal ghost-free gravity theory

A new representation is found for the action of the recently suggested ghost-free nonlocal gravity models generating de Sitter or Anti-de Sitter background with an arbitrary value of the effective cosmological constant. This representation allows one to extend applications of these models from maximally symmetric to generic Einstein spaces and black hole solutions, but clearly indicates violation of the general relativistic limit in this class of theories, induced by their infrared behavior. It is shown that this limit can be recovered in a special conformal frame of these theories, and their relation to critical gravity models is also briefly discussed.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Dataset for the paper titled "Investigating the relationship between bolide entry angle and apparent direction of infrasound signal arrivals"

This dataset includes outputs generated for the journal publication titled: "Investigating the relationship between bolide entry angle and apparent direction of infrasound signal arrivals". The outputs include .csv files with model-generated synthetic trajectories of asteroids entering Earth at a variety of impact and approach (azimuthal) angles. All outputs are based on hypothetical but realistic scenarios.

Herrera, Natalie [Sandia National Laboratories (SN↗

Scientific discovery in a model-centric framework: Reproducibility, innovation, and epistemic diversity

Consistent confirmations obtained independently of each other lend credibility to a scientific result. We refer to results satisfying this consistency as reproducible and assume that reproducibility is a desirable property of scientific discovery. Yet seemingly science also progresses despite irreproducible results, indicating that the relationship between reproducibility and other desirable properties of scientific discovery is not well understood. These properties include early discovery of truth, persistence on truth once it is discovered, and time spent on truth in a long-term scientific inquiry. We build a mathematical model of scientific discovery that presents a viable framework to study its desirable properties including reproducibility. In this framework, we assume that scientists adopt a model-centric approach to discover the true model generating data in a stochastic process of scientific discovery. We analyze the properties of this process using Markov chain theory, Monte Carlo methods, and agent-based modeling. We show that the scientific process may not converge to truth even if scientific results are reproducible and that irreproducible results do not necessarily imply untrue results. The proportion of different research strategies represented in the scientific population, scientists’ choice of methodology, the complexity of truth, and the strength of signal contribute to this counter-intuitive finding. Important insights include that innovative research speeds up the discovery of scientific truth by facilitating the exploration of model space and epistemic diversity optimizes across desirable properties of scientific discovery.

97 MATHEMATICS AND COMPUTING↗

Automated Discovery of DOminaNt physics Informed Surrogates (ADDONIS) Framework for Improving Water Cycling Predictability

Focal Areas: The primary alignment of the proposed framework is with focal area 2, because it guides the construction of a hierarchy of predictive models generated from Statistical and AI/ ML techniques. There are connections to focal areas 1 and 3 because surrogates allow for coupled data assimilation techniques where the full model is too expensive (1) and the discovered balance laws can be used as an insightful analysis tool to validate the structure of models (3).

54 ENVIRONMENTAL SCIENCES↗

3D-Scaffold: A Deep Learning Framework to Generate 3D Coordinates of Drug-like Molecules with Desired Scaffolds

The prerequisite of therapeutic drug design is to identify novel molecules with desired biophysical and biochemical properties. Deep generative models have demonstrated their ability to find such molecules by exploring a huge chemical space efficiently. An effective way to obtain molecules with desired target properties is the preservation of critical scaffolds in the generation process. To this end, we propose a domain aware generative framework called 3D-Scaffold that takes 3D coordinates of a desired scaffold as an input and generates 3D coordinates of novel therapeutic candidates as an output while always preserving the desired scaffolds in generated structures. We show that our framework generates predominantly valid, unique, novel, and experimentally synthesizable molecules that have drug-like properties similar to the molecules in the training set. Using domain specific datasets, we generate covalent and non-covalent antiviral inhibitors. Therefore, to measure the success of our framework in generating therapeutic candidates, generated structures were subjected to high throughput virtual screening via docking simulations, which shows favorable interaction against SARS-CoV-2 main protease and non-structural protein endoribonuclease (NSP15) targets. Most importantly, our model performs well with relatively small volumes of training data and generalizes to new scaffolds, making it applicable to other domain.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

High‐Asymmetry Metasurface: A New Solution for Terahertz Resonance via Active Learning‐Augmented Diffusion Model

Terahertz (THz) metamaterials with high‐figure‐of‐merit (high‐FoM) performance resonance are essential for advancing sensors, detectors, and imagers. Conventional designs focus on symmetric or low‐asymmetry geometric structures, leaving high‐asymmetry designs largely unexplored due to the inefficiency of trial‐and‐error‐based rational design. Recent deep learning techniques offer automation and acceleration but are constrained by the need for large datasets inherent to their data‐driven nature. Here, a novel prior knowledge‐guided generative model augmented by a physics‐constrained active learning mechanism to design high‐asymmetry metamaterials. An advanced diffusion model learns features from a small set of classical structures with high‐FoM THz resonance and generates new high‐asymmetry structures. To mitigate the limited number of classical structures, the generated high‐asymmetry structures are actively selected and integrated into the initial training dataset based on their physical characteristics. Experimental results demonstrate the superior resonance performance of the generated high‐asymmetry metamaterials over classical designs, exhibiting improvements exceeding 30% in key resonance metrics. Remarkably, this performance is attained using only 68 classical structures as the initial training dataset, significantly reducing the data requirements for deep learning‐based metamaterial design. The proposed scheme for generating high‐asymmetry structures provides a new effective and efficient solution for high‐FoM resonance, expanding applications in high‐sensitivity THz metadevices.

diffusion model↗