Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “simulated data”

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 1,477 records · Page 82
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Systematic Uncertainties in the NOvA \nu_\mu-Disappearance Analysis

As the NOvA long-baseline neutrino oscillation experiment takes more data, systematic uncertainty begins to more heavily impact the oscillation analyses. The largest effects are calibration on calorimetric energy, detector modeling on muon energy scale, and near-detector pileup on normalization of the far-detector expectation. Cross-section systematics will be discussed in another poster. Detailed studies have justified previous systematics as too conservative and suggested smaller values. Focused study of detector modeling using dE/dx and external measurements constrain the calibration and energy scale uncertainties. A novel technique is used to assess the impact of activity from neutrino activity piling up over signal, where a simulated neutrino is overlaid into both data and simulation. The difference in efficiency of selecting that single neutrino among data and simulated spills then dominates the normalization systematic.

Alion, Tyler [Sussex U.]↗
DOE OSTI2022

Bay Area Regional Energy: Network Integrated Commercial Retrofits (BRICR) Project. Final Report

The BRICR project applied large-scale building energy modeling concepts with the aim of reducing the cost of energy efficiency targeting, design, and project development, and measurement of energy savings for energy efficiency programs implemented by local governments that serve small and medium commercial buildings (SMB). The project leveraged the services and resources of existing local government energy programs serving disadvantaged and hard-to-reach SMB customers. In contrast to programs run by utilities, local government programs generally do not have direct access to energy billing records for an entire class of customers in a geographic area, which prior research demonstrated useful for large-scale building energy model baseline development and calibration. , However, local governments are rich in public records that offer important clues about physical attributes and uses that, along with behavior, determine energy use. Relying only on public records, BRICR demonstrated development of credible baseline energy models for 3,792 office, retail, and hotel buildings. Publicly disclosed annual energy use data from a local energy benchmarking program and anonymized data from the Building Performance Database, the nation’s largest dataset about energy-related characteristics of buildings, were utilized to validate and calibrate energy models via an innovative method comparing distributions of energy intensity by fuel type for portfolios of buildings of similar size, vintage, and use. Portfolio calibration does not provide certainty that an energy model fits an individual building; the method is useful when billing data is not accessible – a common situation for researchers, energy service providers and ESCOs, local governments, and any party other than a utility. A software component was developed, the BRICR gem, which automates simulation when relevant data is added or edited by the user to a file saved in the standardized BuildingSync XML schema for energy audit data. The component was demonstrated as a simplified means to generate a mass of energy models corresponding to public records containing basic attributes such as building scale, location, use, year built, and aspect ratio in combination with building energy code prototype data corresponding to use and vintage. The component was also demonstrated as a simplified means to automate energy simulation when attributes are revised; the intention was to enable iterative improvement of the baseline model and energy savings estimates for common energy conservation measures as users revise relevant attributes based on their observations. In the context of institutional change and uncertainty for the participating local government energy programs, 13 whole building retrofits were completed. Impacts were measured by applying the CalTRACK2.0 methods to standardize measurement of normalized metered energy consumption. The GRIDMeter methods of stratified sampling and individual load shape analysis were applied to adjust for impacts of the effect of COVID-19 on retrofitted buildings in the context of all local buildings of similar size and use. Excluding impacts of the pandemic, retrofitted buildings demonstrated between 1.6% and 25.1% reduction in energy use. The project contributed use cases and feedback that helped inform evolution of the software tools and data formats that were combined for the first time in the BRICR project.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2025

Applying Gaussian Process Machine Learning and Modern Probabilistic Programming to Satellite Data to Infer CO 2 Emissions

Satellite data provides essential insights into the spatiotemporal distribution of CO 2 concentrations. However, many atmospheric inverse models fail to adequately incorporate the spatial and temporal correlations inherent in satellite observations and often lack rigorous methods for estimating parameters like spatial length scales. We introduce an inference model that processes the spatiotemporal covariance in satellite data and estimates hyperparameters such as covariance length scales. Our approach uses the Gaussian process (GP) machine learning (ML) and modern probabilistic programming languages (PPLs) to perform atmospheric inversions of emissions from satellite data. We develop a GP ML inversion system based on modern PPLs and the GEOS-Chem chemical transport model, simulating atmospheric CO 2 concentrations corresponding to the Orbiting Carbon Observatory-2/3 (OCO-2/3) data for July 2020. In our supervised learning framework, we treat the GEOS-Chem simulated data set as the target, with predictors derived by scaling the target with sector-specific factors hidden from the GP machine. Our results show that the GP model, combined with GPU-enabled PPLs, effectively retrieves true emission scaling factors and infers noise levels concealed within the data. This suggests that our method could be applied over larger areas with more complex covariance structures, enabling comprehensive analysis of the spatiotemporal patterns observed in OCO-2/3 and similar satellite data sets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Data-driven prediction of scaling and ignition of inertial confinement fusion experiments

Recent advances in inertial confinement fusion (ICF) at the National Ignition Facility (NIF), including ignition and energy gain, are enabled by a close coupling between experiments and high-fidelity simulations. Neither simulations nor experiments can fully constrain the behavior of ICF implosions on their own, meaning pre- and postshot simulation studies must incorporate experimental data to be reliable. Linking past data with simulations to make predictions for upcoming designs and quantifying the uncertainty in those predictions has been an ongoing challenge in ICF research. We have developed a data-driven approach to prediction and uncertainty quantification that combines large ensembles of simulations with Bayesian inference and deep learning. The approach builds a predictive model for the statistical distribution of key performance parameters, which is jointly informed by past experiments and physics simulations. The prediction distribution captures the impact of experimental uncertainty, expert priors, design changes, and shot-to-shot variations. We have used this new capability to predict a 10× increase in ignition probability between Hybrid-E shots driven with 2.05 MJ compared to 1.9 MJ, and validated our predictions against subsequent experiments. We describe our new Bayesian postshot and prediction capabilities, discuss their application to NIF ignition and validate the results, and finally investigate the impact of data sparsity on our prediction results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

What Machine Learning Can and Cannot Do for Inertial Confinement Fusion

Machine learning methodologies have played remarkable roles in solving complex systems with large data, well-defined input–output pairs, and clearly definable goals and metrics. The methodologies are effective in image analysis, classification, and systems without long chains of logic. Recently, machine-learning methodologies have been widely applied to inertial confinement fusion (ICF) capsules and the design optimization of OMEGA (Omega Laser Facility) capsule implosion and NIF (National Ignition Facility) ignition capsules, leading to significant progress. As machine learning is being increasingly applied, concerns arise regarding its capabilities and limitations in the context of ICF. ICF is a complicated physical system that relies on physics knowledge and human judgment to guide machine learning. Additionally, the experimental database for ICF ignition is not large enough to provide credible training data. Most researchers in the field of ICF use simulations, or a mix of simulations and experimental results, instead of real data to train machine learning models and related tools. They then use the trained learning model to predict future events. This methodology can be successful, subject to a careful choice of data and simulations. However, because of the extreme sensitivity of the neutron yield to the input implosion parameters, physics-guided machine learning for ICF is extremely important and necessary, especially when the database is small, the uncertain-domain knowledge is large, and the physical capabilities of the learning models are still being developed. In this work, we identify problems in ICF that are suitable for machine learning and circumstances where machine learning is less likely to be successful. This study investigates the applications of machine learning and highlights fundamental research challenges and directions associated with machine learning in ICF.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Concurrent Relaxation through Accelerated Deep Learning

CRADL captures performance metrics of machine learning algorithms operating on mesh data from multiphysics codes This proxy application is a tool to explore scalability of inference on HPC platforms, and also gather performance metrics for inference on new machine learning specific hardware. CRADL is designed to give users as fine a control as possible over an inference simulation. Users may select the number of cycles, amount of data, and batch size to pass to the accelerator of choice. Additionally the user may select a number of performance optimization libraries and flags. CRADL comes packaged with a repository of anonymized multi-physics simulation data, as well as a pretrained model for inference. The code allows a user to load their own pre-trained model and data if they wish. The code can operate in multiple parallelization schemes, with performance enhancing options such as half-precision libraries, PyTorch benchmarking, and pinned memory with non-blocking data transfers.

Zieb, KristoferJ.↗
DOE OSTI2022

Modeling the partitioning of amphiphilic molecules and co-solvents in biomembranes

We report amphiphilic co-solvents can have a significant impact on the structure, organization and physical properties of lipid bilayers. Describing the mutual impact of partitioning and induced structure changes is therefore a crucial consideration for a range of topics such as anesthesia and other pharmacokinetic effects, as well as microbial solvent tolerance in the production of biofuels and other fermentation products, where molecules such as ethanol, butanol or acetic acid might be generated. Small-angle neutron scattering (SANS) is a key method for studying lipid and polymer bilayer structures, with many models for extracting bilayer structure (thickness, area per lipid etc.) from scattering data in use today. However, the molecular details of co-solvent partitioning are conflated with induced changes to bilayer structure, making interpretation and modeling of the scattering curves a challenge with the existing set of models. To address this, a model of a bilayer structure is presented which invokes a two-term partition constant accounting for the localization of the co-solvent within the bilayer. This model was validated using a series of SANS measurements of lipid vesicles in the presence of the co-solvent tetrahydrofuran (THF), showing several strategies of how to deploy the two-parameter partition constant model to describe scattering data and extract both structure and partitioning information from the data. Molecular dynamics simulations are then used to evaluate assumptions of the model, provide additional molecular scale details and illustrate its complementary nature to the data fitting procedure. This approach results in estimates of the partition coefficient for THF in 1,2-dimyristoyl-sn-glycero-3-phosphocholine at 35°C, along with an estimate of the fraction of THF residing in the hydrophobic core of the membrane. The authors envision that this model will be applicable to a wide range of other bilayer/amphiphile interactions and provide the associated code needed to implement this model as a fitting algorithm for scattering data in the SasView suite.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Analysis of proton bunch parameters in the AWAKE experiment

A precise characterization of the incoming proton bunch parameters is required to accurately simulate the self-modulation process in the Advanced Wakefield Experiment (AWAKE). This paper presents an analysis of the parameters of the incoming proton bunches used in the later stages of the AWAKE Run 1 data-taking period. The transverse structure of the bunch is observed at multiple positions along the beamline using scintillating or optical transition radiation screens. The parameters of a model that describes the bunch transverse dimensions and divergence are fitted to represent the observed data using Bayesian inference. Finally, the analysis is tested on simulated data and then applied to the experimental data.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Impact of Changes in ENDF/B-VII.1 and ENDF/B-VIII.0 235U Nuclear Data Indicated by NDSE Studies on LLNL Pulsed Sphere Simulations

A recent journal article by J.A. Gomez et al. measured gamma-ray die-off curves of three subcritical static highly-enriched uranium (HEU) assemblies driven by an external neutron source with a new detector system. This new detector system was developed for being used in dynamically driven subcritical assemblies as part of the Neutron Diagnosed Subcritical Experiments (NDSE) program. Simulations of these die-off curves with various nuclear data and comparison to experimental data indicated that a decrease of the ENDF/B-VII.1 235 U(n,inl) cross section by a factor 0.8 and 0.85 for ENDF/B-VIII.0 would lead to better predictions of experimental data. Here, we test the proposed changes with another type of measurement response, namely neutron-leakage spectra emitted in LLNL pulsed sphere measurements. These spheres were pulsed by 14-MeV neutrons produced via the D+T reaction in their center. The proposed changes in nuclear data have a distinctly smaller impact on predicting pulsed-sphere neutron-leakage spectra than for the die-off curves; they lead to a worsened prediction of the inelastic valley of LLNL pulsed-sphere neutron spectra indicating that the proposed change could constitute a compensating error. Changes in the inelastic angular distributions along with the cross section might be worthwhile to study

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

Precambrian Crystalline Basement Properties From Pressure History Matching and Implications for Induced Seismicity in the US Midcontinent

Injection-induced seismicity across the US midcontinent has almost exclusively occurred in the crystalline basement that underlies the Arbuckle Group aquifer and its equivalents, the primary wastewater disposal zone in this region. However, the properties of the basement are not well known. Newly compiled data, from Class I wells in Kansas, provide a unique record of pressures in the Arbuckle and an opportunity to constrain the reservoir-scale properties of the basement such as permeability, diffusivity, and specific storage. Constraints on these parameters are critical for modeling fluid flow and pressures across the entire Arbuckle-basement system, and are necessary for accurate evaluation and prediction of injection-induced earthquakes. Here, we present a detailed, three-dimensional geological and pressure history-matched numerical model for the Arbuckle and basement, based on data from >400 wells covering a large region in south-central Kansas, where injection-induced seismicity has been concentrated since 2014. Simulations of dynamic data from 319 wells indicate that Arbuckle pressures have increased by 1.1 MPa in high injection rate areas and an overpressure of <0.1 MPa may be the cause of seismicity in the basement. Pressure-history matching also yields the likely range in porosity (0.3%–7%), permeability (0.1–0.7 mD), and diffusivity (0.004–0.07 m2 /s) for the basement. The resulting estimates suggest reservoir-scale properties of the basement are enhanced by faults and fractures. Importantly, the diffusivities determined in this study are lower than estimates derived from Kansas earthquake triggering fronts, and suggest that such seismicity-based techniques may have limitations, particularly where spacetime patterns between injection and seismicity are complex.

58 GEOSCIENCES↗
DOE OSTI2019

Interpreting the Strain Tensor During Injection into a Reservoir

A suite of well tests was conducted to evaluate the feasibility of measuring and interpreting the strain tensor during injection. Water was injected at 1 liter/s for a few days to a few weeks into a well completed at a depth of 530 m in the Bartlesville sandstone in the North Avant Field in Oklahoma. The strain tensor was measured using strainmeters at a depth of 30m and a distance of 220m from the well. We used a Gladwin strainmeter, a state-of-the-art geodetic strainmeter, as well as novel borehole strainmeters developed for the project. After processing, the horizontal strains were tensile and the vertical strain was compressive during injection. The radial strain was less than the circumferential strain. Strain magnitudes increased during injection and recovered afterward. The strain rate was as fast as 100 nanostrain/d at the start of injection, and decreased to 10 nanostrain/d after a few days. The normal strain signals were approximately proportional to the log of time during the first few days of injection, and the semi-log slope was 50 to 75 nanostrain. Data from the Gladwin strainmeter were essentially identical to data from a strainmeter we developed using optical fiber sensors. Tilt was measured using two tiltmeters, but the tilts were erratic compared to the normal strain and were of limited value. Strain data were analyzed using a strain type-curve method, an analytical solution to a poroelastic inhomogeneity, and a stochastic inversion method. Poroelastic simulations explain the data well. Results from the interpretation methods are consistent with each other, and with independent information characterizing the area. The hydraulic diffusivity is approximately 0.5 m2/s and the permeability is between 100 and 500 mD, according to analysis of the strain signals. This is consistent with measurements of permeability from cores, and with analyses of pressure transients. The analyses indicate that Young’s modulus of the reservoir is between 2 and 6 GPa. Strain interpretations indicate the well intersects a permeable lens with a maximum dimension of 500 to 1,000 m. An isopach map of coarse-grained sand confirms a feature roughly 1,000 m in lateral extent. The results demonstrate that the strain signal measured at shallow (30m) depth can be used to infer properties and heterogeneities in an underlying reservoir or aquifer.

Murdoch, Larry↗
DOE OSTI2026

Developing a Digital Twin for SRF Cavity Assembly at Fermilab

When assembling Superconducting Radio Frequency (SRF) Cavities, maintaining an environment devoid of particulates like dust and other small particles is essential. If a single spec of dust enters the cavity a significant degradation of performance can occur. To avoid a cavity failure Fermilab assembles the SRF cavities within a ISO-4 (Class 10) environment. This environment though is still susceptible to foreign contaminants when technicians enter and new components are added to the cleanroom. To reduce the risk even more Fermilab has introduced a cobot manipulator into the cleanroom environment to speed up the assembly time which will reduce the time that the technicians operate in the cleanroom. But, this still leaves the potential of contaminants to enter the cleanroom if new components need to be tested within the cleanroom. This project aims to lay the groundwork to develop a Digital Twin environment of the cleanroom to aid in manufacturing processes and testing. In its simplest form, a digital twin is a bidirectional link between a physical system and its digital counterpart or twin. NVIDIA Isaac Sim is used as the digital twin foundation for the digital representation of the cleanroom, specifically for the UR16e assembly area. A simulated UR16e was used to validate the performance of Isaac Sim as a testing environment by comparing the tool center points (TCP) positional data between the simulated and digital representation of the UR16e. Due to a new vision based robotic assembly process being introduced to the cleanroom a digital representation of the physical camera was tested and validated to ensure that it will produce close to the same outcome as the physical environment. The TCP comparison results showed a peak translational error of approximately 0.1mm and rotational errors of up to 8 between the simulated and digital UR16es. While the camera validation performed with high repeatability across multiple runs, it still requires minor tuning before it can accurately replicate a physical camera.

Imburgia, Joseph [Northern Illinois U.]↗
DOE OSTI2023

Learning effective SDEs from Brownian dynamic simulations of colloidal particles

We construct a reduced, data-driven, parameter dependent effective stochastic differential equation (eSDE) for electric-field mediated colloidal crystallization using data obtained from Brownian dynamics simulations. We use diffusion maps (a manifold learning algorithm) to identify a set of useful latent observables. In this latent space we identify an eSDE using a deep learning architecture inspired by numerical stochastic integrators and compare it with the traditional Kramers–Moyal expansion estimation. We show that the obtained variables and the learned dynamics accurately encode the physics of the Brownian dynamic simulations. We further illustrate that our reduced model captures the dynamics of corresponding experimental data. Further, our dimension reduction/reduced model identification approach can be easily ported to a broad class of particle systems dynamics experiments/models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Phase transformation path in Aluminum under ramp compression; simulation and experimental study

Abstract We present a framework based on non-equilibrium molecular dynamics (NEMD) to reproduce the phase transformation event of Aluminum under ramp compression loading. The simulated stress-density response, virtual x-ray diffraction patterns, and structure analysis are compared against the previously observed experimental laser-driven ramp compression in-situ x-ray diffraction data. The NEMD simulations show the solid–solid phase transitions are consistent to experimental observations with a close-packed face-centered cubic (fcc) (111), hexagonal close-packed (hcp) structure (002), and body-centered cubic bcc (110) planes remaining parallel. The atomic-level analysis of NEMD simulations identifiy the exact phase transformation pathway happening via Bain transformation while the previous in situ x-ray diffraction data did not provide sufficient information for deducing the exact phase transformation path.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning

One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on existing simulation tools employed in AM. The goal of the present work is to construct a fast and accurate reduced-order model (ROM) for an AM model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) framework, ultimately reducing the time/cost of AM control and optimization processes. Our adoption of the operator learning (OL) approach enabled us to learn a family of differential equations produced by altering process variables in the laser’s Gaussian point heat source. More specifically, we used the Fourier neural operator (FNO) and deep operator network (DeepONet) to develop ROMs for time-dependent responses. Furthermore, we benchmarked the performance of these OL methods against a conventional deep neural network (DNN)-based ROM. Ultimately, we found that OL methods offer comparable performance and, in terms of accuracy and generalizability, even outperform DNN at predicting scalar model responses. The DNN-based ROM afforded the fastest training time. Furthermore, all the ROMs were faster than the original MOOSE model yet still provided accurate predictions. FNO had a smaller mean prediction error than DeepONet, with a larger variance for time-dependent responses. Unlike DNN, both FNO and DeepONet were able to simulate time series data without the need for dimensionality reduction techniques. Finally, the present work can help facilitate the AM optimization process by enabling faster execution of simulation tools while still preserving evaluation accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Thermo-hydro-mechanical analysis of subsurface ice-based thermal energy storage

Ice-based thermal energy storage systems are widely utilized for cooling and managing peak electrical demand globally, offering daily or weekly storage capabilities for both individual homes and larger office buildings. However, scaling these systems for district-level cooling or integrating them with renewable energy sources presents challenges, especially in accommodating larger volumes and addressing seasonal storage requirements in densely populated urban areas. This paper proposes a novel solution by evaluating subsurface ice-based thermal energy storage, in which the underground is subjected to seasonal freeze/thaw cycles. However, these cycles may influence ground behavior, affecting pore pressure and inducing ground movement. To systematically investigate these challenges, we enhance the TOUGH-FLAC simulator by integrating water/ice phase change capabilities and updating the effective stress–strain constitutive relation. Both modifications are validated against analytical solutions or experimental data. Through numerical simulations spanning a decade with ten seasonal freeze/thaw cycles, we evaluate the performance and long-term stability of a generic subsurface ice-based thermal energy storage system, considering factors such as ground permeability, freezing pipe spacing, freeze/thaw damage, and glycol solution temperature. The simulations indicate that ice formation induces pore pressure variations that drive seasonal surface heave and settlement, controlled by ground permeability, pipe spacing, and glycol solution temperature, along with tensile and localized shear deformation around freeze pipes. This highlights the need for accurate ground property characterization and geomechanical analysis for subsurface ice-based thermal energy storage.

Ground freezing↗
DOE OSTI2023

A multiscale recurrent neural network model for predicting energy production from geothermal reservoirs

Optimization of energy production from geothermal reservoirs requires reliable prediction of energy production performance under alternative operation and development scenarios. Traditionally, reservoir simulation models are used for the evaluation and screening of alternative production and development plans. However, simulation models require extensive data collection and modeling efforts and are time-consuming to build, run, and update. Data-driven predictive models, on the other hand, can serve as efficient prediction tools that can be used for decision support and management of daily operations and surveillance activities. Data-driven models become particularly attractive when a reservoir simulation model for a field does not exist and/or is difficult to build. Machine learning (ML)-based data-driven models that have recently become popular in several fields exploit statistical patterns and relations in training data to generate predictions. As such, they tend to perform better in interpolation problems (that is, prediction within the training data range) than when they are used to extrapolate beyond the training data. Production data from geothermal reservoirs tend to exhibit short-term variabilities as well as long-term trends, such as monotonically declining production temperatures. Capturing both short-term features and long-term trends with ML-based models is not trivial. We evaluate the use of recurrent neural networks (RNN) for the prediction of energy production from geothermal reservoirs. RNN is a class of ML architectures that are used to represent and predict sequential/dynamic data. Thus, it can be challenging to apply RNN to problems where long-term trends must be captured and extrapolation beyond the training data range is needed. We introduce the multiscale RNN architecture to extend the application of RNN to detect and predict both short-term variabilities and long-term trends in geothermal data. The developed architecture consists of a long-term component to only capture low-frequency data patterns, and a short-term component to detect features with higher frequency and more nonlinearity. The final prediction is obtained by combining the long-term and short-term predictions. Both synthetic and field data are used to evaluate the presented multiscale RNN model. The prediction performance of the multiscale RNN is compared against those obtained from the regular RNN and the autoregressive (AR) model. The results suggest that the multiscale architecture improves the long-term prediction performance of the regular RNN and enhances its robustness against noise.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

A generative artificial intelligence framework for long-time plasma turbulence simulations

Generative deep learning techniques are employed in a novel framework for the construction of surrogate models capturing the spatiotemporal dynamics of 2D plasma turbulence. The proposed Generative Artificial Intelligence Turbulence (GAIT) framework enables the acceleration of turbulence simulations for long-time transport studies. GAIT leverages a convolutional variational auto-encoder and a recurrent neural network to generate new turbulence data from existing simulations, extending the time horizon of transport studies with minimal computational cost. The application of the GAIT framework to plasma turbulence using the Hasegawa–Wakatani (HW) model is presented, evaluating its performance via various analyses. Very good agreement is found between the GAIT and the HW models in the spatiotemporal Fourier and Proper Orthogonal Decomposition spectra, the flow topology characterized by the Okubo–Weiss parameter, and the time autocorrelation function of turbulent fluctuations. Excellent agreement has also been obtained in the probability distribution function of particle displacements and the effective turbulent diffusivity. In-depth analyses of the latent space of turbulent states, choice of hyperparameters and alternative deep learning models for the time prediction are presented. Our results highlight the potential of Artificial Intelligence-based surrogate models to overcome the computational challenges in turbulence simulation, which can be extended to other situations such as geophysical fluid dynamics.

Artificial intelligence↗