KSTAR_UEDGE_Dataset: UEDGE Simulation Dataset for Training the KSTAR DivControlNN Surrogate Model
Explore the source record for details and available documents.
Zhao, Menglong [Lawrence Livermore National Labora↗
SEARCH · Search NASA
Results for “train simulation”
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.
Improving Photometric Redshift Estimates with Training Sample Augmentation
Abstract Large imaging surveys will rely on photometric redshifts (photo- z 's), which are typically estimated through machine-learning methods. Currently planned spectroscopic surveys will not be deep enough to produce a representative training sample for Legacy Survey of Space and Time (LSST), so we seek methods to improve the photo- z estimates that arise from nonrepresentative training samples. Spectroscopic training samples for photo- z 's are biased toward redder, brighter galaxies, which also tend to be at lower redshift than the typical galaxy observed by LSST, leading to poor photo- z estimates with outlier fractions nearly 4 times larger than for a representative training sample. In this Letter, we apply the concept of training sample augmentation, where we augment simulated nonrepresentative training samples with simulated galaxies possessing otherwise unrepresented features. When we select simulated galaxies with ( g - z ) color, i -band magnitude, and redshift outside the range of the original training sample, we are able to reduce the outlier fraction of the photo- z estimates for simulated LSST data by nearly 50% and the normalized median absolute deviation (NMAD) by 56%. When compared to a fully representative training sample, augmentation can recover nearly 70% of the degradation in the outlier fraction and 80% of the degradation in NMAD. Training sample augmentation is a simple and effective way to improve training samples for photo- z 's without requiring additional spectroscopic samples.
Moskowitz, Irene (ORCID:0000000222068589)↗
Predicting Local Material Thickness from Steady-State Ultrasonic Wavefield Measurements Using a Convolutional Neural Network
Acoustic steady-state excitation spatial spectroscopy (ASSESS) is a full-field, ultrasonic non-destructive evaluation (NDE) technique used to locate and characterize defects in plate-like structures. ASSESS generates a steady-state, single-tone ultrasonic excitation in a structure and a scanning laser Doppler Vibrometer (LDV) measures the resulting full-field surface velocity response. Traditional processing techniques for ASSESS data rely on wavenumber domain analysis. This paper presents the alternative use of a convolutional neural network (CNN), trained using simulated ASSESS data, to predict the local plate thickness at every pixel in the wavefield measurement directly. The defect detection accuracy of CNN-based thickness predictions are shown to improve for defects of greater size, and for defects with higher thickness reductions. The CNN demonstrates the ability to predict thickness accurately in regions where Lamb wave dispersion relations are complex or unknown, such as near the boundaries of a test specimen, so long as the CNN is trained on data that accounts for these regions. The CNN also shows generalizability to ASSESS experimental data, despite an entirely simulated training dataset.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains
In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.
galaxies: interactions↗
Advancing Building Energy Modeling with Large Language Models: Exploration and Case Studies
The rapid progression in artificial intelligence has facilitated the emergence of large language models like ChatGPT, offering potential applications extending into specialized engineering modeling, especially physics-based building energy modeling. This paper investigates the innovative integration of large language models with building energy modeling software, focusing specifically on the fusion of ChatGPT with EnergyPlus. A literature review is first conducted to reveal a growing trend of incorporating large language models in engineering modeling, albeit limited research on their application in building energy modeling. We underscore the potential of large language models in addressing building energy modeling challenges and outline potential applications including simulation input generation, simulation output analysis and visualization, conducting error analysis, co-simulation, simulation knowledge extraction and training, and simulation optimization. Three case studies reveal the transformative potential of large language models in automating and optimizing building energy modeling tasks, underscoring the pivotal role of artificial intelligence in advancing sustainable building practices and energy efficiency. The case studies demonstrate that selecting the right large language model techniques is essential to enhance performance and reduce engineering efforts. The findings advocate a multidisciplinary approach in future artificial intelligence research, with implications extending beyond building energy modeling to other specialized engineering modeling.
building energy modeling↗
Simulating organic aerosol in Delhi with WRF-Chem using the volatility-basis-set approach: exploring model uncertainty with a Gaussian process emulator
The nature and origin of organic aerosol in the atmosphere remain unclear. The gas–particle partitioning of semi-volatile organic compounds (SVOCs) that constitute primary organic aerosols (POAs) and the multigenerational chemical aging of SVOCs are particularly poorly understood. The volatility basis set (VBS) approach, implemented in air quality models such as WRF-Chem (Weather Research and Forecasting model with Chemistry), can be a useful tool to describe emissions of POA and its chemical evolution. However, the evaluation of model uncertainty and the optimal model parameterization may be expensive to probe using only WRF-Chem simulations. Gaussian process emulators, trained on simulations from relatively few WRF-Chem simulations, are capable of reproducing model results and estimating the sources of model uncertainty within a defined range of model parameters. In this study, a WRF-Chem VBS parameterization is proposed; we then generate a perturbed parameter ensemble of 111 model runs, perturbing 10 parameters of the WRF-Chem model relating to organic aerosol emissions and the VBS oxidation reactions. This allowed us to cover the model's uncertainty space and to compare outputs from each run to aerosol mass spectrometer observations of organic aerosol concentrations and O:C ratios measured in New Delhi, India. The simulations spanned the organic aerosol concentrations measured with the aerosol mass spectrometer (AMS). However, they also highlighted potential structural errors in the model that may be related to unsuitable diurnal cycles in the emissions and/or failure to adequately represent the dynamics of the planetary boundary layer. While the structural errors prevented us from clearly identifying an optimized VBS approach in WRF-Chem, we were able to apply the emulator in the following two periods: the full period (1–29 May) and a subperiod period of 14:00–16:00 h LT (local time) on 1–29 May. The combination of emulator analysis and model evaluation metrics allowed us to identify plausible parameter combinations for the analyzed periods. We demonstrate that the methodology presented in this study can be used to determine the model uncertainty and to identify the appropriate parameter combination for the VBS approach and hence to provide valuable information to improve our understanding of OA production.
54 ENVIRONMENTAL SCIENCES↗
Machine learning enabled lineshape analysis in optical two-dimensional coherent spectroscopy
Optical two-dimensional (2D) coherent spectroscopy excels in studying coupling and dynamics in complex systems. The dynamical information can be learned from lineshape analysis to extract the corresponding linewidth. However, it is usually challenging to fit a 2D spectrum, especially when the homogeneous and inhomogeneous linewidths are comparable. We implemented a machine learning algorithm to analyze 2D spectra to retrieve homogeneous and inhomogeneous linewidths. The algorithm was trained using simulated 2D spectra with known linewidth values. The trained algorithm can analyze both simulated (not used in training) and experimental spectra to extract the homogeneous and inhomogeneous linewidths. Finally, this approach can be potentially applied to 2D spectra with more sophisticated spectral features.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Iterative sampling of expensive simulations for faster deep surrogate training
Deep neural network (DNN) surrogates of expensive physics simulations are enabling a rapid change in the way that common experimental design and analysis tasks are approached. Surrogate models allow simulations to be performed in parallel and separately from downstream tasks, thereby enabling analyses that would be impossible with the simulation in-the-loop; surrogates based on DNNs can effectively emulate diverse non-scalar data of the types collected in fusion and laboratory-astrophysics experiments. The challenge is in training the surrogate model, for which large ensembles of physics simulations must be run, preferably without wasting computational effort on uninteresting simulations. Here, in this paper, we present an iterative sampling scheme that can preferentially propose simulations in interesting regions of parameter space without neglecting unexplored regions, allowing high-quality and wide-ranging surrogate models to be trained using 2–3 times fewer simulations compare to space-filling designs. Our approach uses an explicit importance function defined on the simulation output space, balanced against a measure of simulation density which serves as a proxy for surrogate accuracy. It is easy to implement and can be tuned to find interesting simulations early in the study, allowing surrogates to be trained quickly and refined as new simulations become available; this represents an important step towards the routine generation of deep surrogate models quickly enough to be truly relevant to experimental work.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
Hyperparameter Studies for Vision Transformers Trained on High-Fidelity Simulations
This library is a collection of python modules that define, train, and analyze vision-transformer (ViT) machine learning models. The code implements, with mild modifications, ViT models that have been made publicly available through publication and GitHub code. The training data for these models is hydrodynamic simulation output in the form of numpy arrays. This library contains code to train these ViT models on the hydrodynamic simulation output with a variety of hyperparameters, and to compare the results of such models. Furthermore, the library contains definitions of simple convolutional neural network (CNN) machine learning architectures which can be trained on the same hydrodynamic simulation output. These are included as a reference point to compare the ViT models to. Additionally, the library includes trained ViT and CNN models and example input data for demonstration purposes. The code is based on the PyTorch python library.
Callis, Skylar↗
A Gigaparsec-scale Hydrodynamic Volume Reconstructed with Deep Learning
The next generation of spectroscopic surveys will map the large-scale structure of the Universe at high redshifts (2 ≤ z ≤ 5) using millions of quasar spectra, enabling major advances in constraining both the standard cosmological model and its extensions. Robust cosmological analyses of these data sets require numerical simulations that both cover gigaparsec volumes and resolve features on ∼10 kpc scales and smaller. However, running such large-volume, high-resolution hydrodynamic simulations is computationally prohibitive. We present a generative deep learning model that enhances a low-resolution, gigaparsec-scale (960 h −1 Mpc) hydrodynamic simulation using a smaller (80 h −1 Mpc) high-resolution input hydrodynamic simulation as training data. The resulting enhanced simulation reproduces the line-of-sight power spectrum to within ∼10% and the three-dimensional power spectrum at the ∼20% level at intermediate to small scales (k ≲ 2 h Mpc −1 ). Our method shows strong promise for producing realistic simulations for cosmological analyses with current surveys such as the Dark Energy Spectroscopic Instrument and upcoming next-generation experiments, but further improvements are needed to accurately recover the large-scale modes. We publicly release the enhanced hydrodynamic simulation, along with a halo catalog from a companion N-body dark matter simulation to support the calibration of data analysis pipelines for these large-scale surveys.
Convolutional neural networks↗
Evolution at the Edge: Real-Time Evolution for Neuromorphic Engine Control
Neuromorphic computing systems are attractive for real-time control at the edge because of their low power operation, real-time processing capabilities and their potential ability to do online learning. In this work, we describe an approach for performing real-time evolution of spiking neural networks for neuromorphic systems at the edge called Neuromorphic Optimization using Dynamic Evolutionary Systems or NODES. We apply this approach to real-time combustion engine control and develop an engine-specific hardware platform for NODES called FireBox. We demonstrate how the real-time evolution approach works in simulation and the performance of networks trained in simulation on the physical engine.
Maldonado Puente, Bryan [ORNL] (ORCID:000000033880↗
AN AUTOMATED MACHINE LEARNING-GENETIC ALGORITHM FRAMEWORK WITH ACTIVE LEARNING FOR DESIGN OPTIMIZATION
The use of machine learning (ML)-based surrogate models is a promising technique to significantly accelerate simulation-driven design optimization of internal combustion (IC) engines, due to the high computational cost of running computational fluid dynamics (CFD) simulations. However, training the ML models requires hyperparameter selection, which is often done using trial-and-error and domain expertise. Another challenge is that the data required to train these models are often unknown a priori. In this work, we present an automated hyperparameter selection technique coupled with an active learning approach to address these challenges. The technique presented in this study involves the use of a Bayesian approach to optimize the hyperparameters of the base learners that make up a super learner model. In addition to performing hyperparameter optimization (HPO), an active learning approach is employed, where the process of data generation using simulations, ML training, and surrogate optimization is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The proposed approach is applied to the optimization of a compression ignition engine with control parameters relating to fuel injection, in-cylinder flow, and thermodynamic conditions. It is demonstrated that by automatically selecting the best values of the hyperparameters, a 1.6% improvement in merit value is obtained, compared to an improvement of 1.0% with default hyperparameters. Overall, the framework introduced in this study reduces the need for technical expertise in training ML models for optimization while also reducing the number of simulations needed for performing surrogate-based design optimization.
Owoyele, Opeoluwa↗
In situ Parallel Training of Analog Neural Network Using Electrochemical Random-Access Memory
In-memory computing based on non-volatile resistive memory can significantly improve the energy efficiency of artificial neural networks. However, accurate in situ training has been challenging due to the nonlinear and stochastic switching of the resistive memory elements. One promising analog memory is the electrochemical random-access memory (ECRAM), also known as the redox transistor. Its low write currents and linear switching properties across hundreds of analog states enable accurate and massively parallel updates of a full crossbar array, which yield rapid and energy-efficient training. While simulations predict that ECRAM based neural networks achieve high training accuracy at significantly higher energy efficiency than digital implementations, these predictions have not been experimentally achieved. In this work, we train a 3 × 3 array of ECRAM devices that learns to discriminate several elementary logic gates (AND, OR, NAND). We record the evolution of the network’s synaptic weights during parallel in situ (on-line) training, with outer product updates. Due to linear and reproducible device switching characteristics, our crossbar simulations not only accurately simulate the epochs to convergence, but also quantitatively capture the evolution of weights in individual devices. The implementation of the first in situ parallel training together with strong agreement with simulation results provides a significant advance toward developing ECRAM into larger crossbar arrays for artificial neural network accelerators, which could enable orders of magnitude improvements in energy efficiency of deep neural networks.
97 MATHEMATICS AND COMPUTING↗
DeepLensSBI: Deep inference of simulated strong lenses in ground-based surveys
This code is used to train and test machine learning models and generate results and plots presented in 2501.08524 [astro-ph.IM]. The code is written in python. The goal of this work is to train ML models trained on simulated images of strong gravitational lenses. The trained model can then quickly infer properties of the lensed objects with uncertainty quantification.
Poh, Jason [Univ. of Chicago, IL (United States)] ↗
Machine learning approaches for structural and thermodynamic properties of a Lennard-Jones fluid
Predicting the functional properties of many molecular systems relies on understanding how atomistic interactions give rise to macroscale observables. However, current attempts to develop predictive models for the structural and thermodynamic properties of condensed-phase systems often rely on extensive parameter fitting to empirically selected functional forms whose effectiveness is limited to a narrow range of physical conditions. Here, we illustrate how these traditional fitting paradigms can be superseded using machine learning. Specifically, we use the results of molecular dynamics simulations to train machine learning protocols that are able to produce the radial distribution function, pressure, and internal energy of a Lennard-Jones fluid with increased accuracy in comparison to previous theoretical methods. The radial distribution function is determined using a variant of the segmented linear regression with the multivariate function decomposition approach developed by Craven et al. [J. Phys. Chem. Lett. 11, 4372 (2020)]. The pressure and internal energy are determined using expressions containing the learned radial distribution function and also a kernel ridge regression process that is trained directly on thermodynamic properties measured in simulation. The presented results suggest that the structural and thermodynamic properties of fluids may be determined more accurately through machine learning than through human-guided functional forms.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
HYPHY: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics
Generating large-volume hydrodynamical simulations for cosmological observables is a computationally demanding task necessary for next-generation observations. In this work, we construct a novel fully convolutional variational autoencoder (VAE) to synthesize hydrodynamic fields conditioned on dark matter fields from N -body simulations. After training the model on a single hydrodynamical simulation, we are able to probabilistically map new dark-matter-only simulations to corresponding full hydrodynamical outputs. By sampling over the latent space of our VAE, we can generate posterior samples and study the variance of the mapping. We find that our reconstructed field provides an accurate representation of the target hydrodynamical fields as well as reasonable variance estimates. This approach has promise for the rapid generation of mocks as well as for implementation in a full inverse model of observed data.
79 ASTRONOMY AND ASTROPHYSICS↗
Resilient Control of Networked Microgrids Using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations
Improving system-level resiliency of networked microgrids against adversarial cyber-attacks is an important aspect in the current regime of increased inverter-based resources (IBRs). To achieve that, this paper contributes in designing a hierarchical control layer, in conjunction with the existing control layers, resilient to adversarial attack signals. Considering model complexities, unknown dynamical behaviors of IBRs, and privacy issues regarding data sharing in multi-party-owned microgrids, designing such a control layer is non-trivial. Here, to tackle these issues, a novel federated reinforcement learning (Fed-RL) method is proposed. To grasp the interconnected dynamics of networked microgrids, the paper develops Federated Soft Actor-Critic (FedSAC) algorithm following the vertical structure of implementing Fed-RL. Next, utilizing the OpenAI Gym interface, we built a custom set-up in GridLAB-D/HELICS co-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to train the RL agents with IEEE 123-bus benchmark comprising 3 interconnected microgrids. Finally, the learned policies in the simulation are transferred to the real-time hardware-in-the-loop (HIL) test-bed developed using the high-fidelity Hypersim platform. Finally, experiments show that the simulator-trained RL controllers achieve desirable performance with the test-bed platform, validating the minimization of the sim-to-real gap.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Adversarial autoencoder ensemble for fast and probabilistic reconstructions of few-shot photon correlation functions for solid-state quantum emitters
Second-order photon correlation measurements [g (2) (τ) functions] are widely used to classify single-photon emission purity in quantum emitters or to measure the multiexciton quantum yield of emitters that can simultaneously host multiple excitations – such as quantum dots – by evaluating the value of g (2) (τ = 0). Accumulating enough photons to accurately calculate this value is time consuming and could be accelerated by fitting of few-shot photon correlations. Here, we develop an uncertainty-aware, deep adversarial autoencoder ensemble (AAE) that reconstructs noise-free g (2) (τ) functions from noise-dominated, few-shot inputs. The model is trained with simulated g (2) (τ) functions that are facilely generated by Poisson sampling time bins. The AAE reconstructions are performed orders-of-magnitude faster, with reconstruction errors and estimates of g (2) (τ = 0) that are lower in variance and similar in accuracy compared to Maximum likelihood estimation and Levenberg-Marquardt least-squares fitting approaches, for simulated and experimentally measured few-shot g (2) (τ) functions (~100 two-photon events) of InP/ZnS/ZnSe and CdS/CdSe/CdS quantum dots. The deep-ensemble model comprises eight individual autoencoders, allowing for probabilistic reconstructions of noise-free g (2) (τ) functions, and we show that the predicted variance scales inversely with number of shots, with comparable uncertainties to computationally intensive Markov chain Monte Carlo sampling. Furthermore, this work demonstrates the advantage of machine learning models to perform uncertainty-aware, fast, and accurate reconstructions of simple Poisson-distributed photon correlation functions, allowing for on-the-fly reconstructions and accelerated materials characterization of solid-state quantum emitters.
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗