Search NASA⌕ Search

SEARCH · Search NASA

Results for “synthetic model”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS2009

V3885 Sagittarius: A Comparison With a Range of Standard Model Accretion Disks

A chi-squared analysis of standard model accretion disk synthetic spectrum fits to combined Far Ultraviolet Spectroscopic Explorer and Space Telescope Imaging Spectrograph spectra of V3885 Sagittarius, on an absolute flux basis, selects a model that accurately represents the observed spectral energy distribution. Calculation of the synthetic spectrum requires the following system parameters. The cataclysmic variable secondary star period-mass relation calibrated by Knigge in 2006 and 2007 sets the secondary component mass. A mean white dwarf (WD) mass from the same study, which is consistent with an observationally determined mass ratio, sets the adopted WD mass of 0.7M(solar mass), and the WD radius follows from standard theoretical models. The adopted inclination, i = 65 deg, is a literature consensus, and is subsequently supported by chi-squared analysis. The mass transfer rate is the remaining parameter to set the accretion disk T(sub eff) profile, and the Hipparcos parallax constrains that parameter to mas transfer = (5.0 +/- 2.0) x 10(exp -9) M(solar mass)/yr by a comparison with observed spectra. The fit to the observed spectra adopts the contribution of a 57,000 +/- 5000 K WD. The model thus provides realistic constraints on mass transfer and T(sub eff) for a large mass transfer system above the period gap.

MASS TRANSFER RATE↗
DOE OSTI2023

Predicting partner fitness based on spatial structuring in a light-driven microbial community

Microbial communities have vital roles in systems essential to human health and agriculture, such as gut and soil microbiomes, and there is growing interest in engineering designer consortia for applications in biotechnology ( e . g ., personalized probiotics, bioproduction of high-value products, biosensing). The capacity to monitor and model metabolite exchange in dynamic microbial consortia can provide foundational information important to understand the community level behaviors that emerge, a requirement for building novel consortia. Where experimental approaches for monitoring metabolic exchange are technologically challenging, computational tools can enable greater access to the fate of both chemicals and microbes within a consortium. In this study, we developed an in-silico model of a synthetic microbial consortia of sucrose-secreting Synechococcus elongatus PCC 7942 and Escherichia coli W. Our model was built on the NUFEB framework for Individual-based Modeling (IbM) and optimized for biological accuracy using experimental data. We showed that the relative level of sucrose secretion regulates not only the steady-state support for heterotrophic biomass, but also the temporal dynamics of consortia growth. In order to determine the importance of spatial organization within the consortium, we fit a regression model to spatial data and used it to accurately predict colony fitness. We found that some of the critical parameters for fitness prediction were inter-colony distance, initial biomass, induction level, and distance from the center of the simulation volume. We anticipate that the synergy between experimental and computational approaches will improve our ability to design consortia with novel function.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

DELVE-ing into the Milky Way’s Globular Clusters: Assessing Extratidal Features in NGC 5897, NGC 7492, and Testing Detectability with Deeper Photometry

Extratidal features around globular clusters (GCs) are tracers of their disruption, stellar stream formation, and their host’s gravitational potential. However, these features remain challenging to detect due to their low surface brightness. We conduct a systematic search for such features around 19 GCs in the DECam Local Volume Exploration (DELVE) survey Data Release 2, discovering a new extra-tidal envelope around NGC 5897 and find tentative evidence for an extended envelope surrounding NGC 7492. Through a combination of dynamical modeling and analyzing synthetic stellar populations, we demonstrate these envelopes may have formed through tidal disruption. We use these models to explore the detectability of these features in the upcoming Legacy Survey of Space and Time (LSST), finding that while LSST’s deeper photometry will enhance detection significance, additional methods for foreground removal like proper motions or metallicities may be important for robust stream detection. Our results both add to the sample of globular clusters with extratidal features and provide insights on interpreting similar features in current and upcoming data.

Chiti, A. [Univ. of Chicago, IL (United States); S↗
NASA NTRS2015

Detecting and Constraining N2 Abundances in Planetary Atmospheres Using Collisional Pairs

Characterizing the bulk atmosphere of a terrestrial planet is important for determining surface pressure and potential habitability. Molecular nitrogen (N2) constitutes the largest fraction of Earth's atmosphere and is likely to be a major constituent of many terrestrial exoplanet atmospheres. Due to its lack of significant absorption features, N2 is extremely difficult to remotely detect. However, N2 produces an N2-N2 collisional pair, (N2)2, which is spectrally active. Here we report the detection of (N2)2 in Earth's disk-integrated spectrum. By comparing spectra from NASA's EPOXI mission to synthetic spectra from the NASA Astrobiology Institute's Virtual Planetary Laboratory three-dimensional spectral Earth model, we find that (N2)2 absorption produces a ~35% decrease in flux at 4.15 μm. Quantifying N2 could provide a means of determining bulk atmospheric composition for terrestrial exoplanets and could rule out abiotic O2 generation, which is possible in rarefied atmospheres. To explore the potential effects of (N2)2 in exoplanet spectra, we used radiative transfer models to generate synthetic emission and transit transmission spectra of self-consistent N2-CO2-H2O atmospheres, and analytic N2-H2 and N2-H2-CO2 atmospheres. We show that (N2)2 absorption in the wings of the 4.3 μm CO2 band is strongly dependent on N2 partial pressures above 0.5 bar and can significantly widen this band in thick N2 atmospheres. The (N2)2 transit transmission signal is up to 10 ppm for an Earth-size planet with an N2-dominated atmosphere orbiting within the habitable zone of an M5V star and could be substantially larger for planets with significant H2 mixing ratios.

Schwieterman, Edward W.↗
DOE OSTI2024

Synthetic Streamflow Datasets to Support Emulation of Water Allocations via LSTM

This archive is the data companion to the bonney_et-al_2026_erc metarepo which generates synthetic data, trains an LSTM model, and generates performance metrics on the trained model. While the generation of the synthetic data is fully reprodicible, it is a computationally expensive process. This data archive contains the synthetic datasets needed for training and testing an LSTM model and reproduction of figures and tables. In addition, supplemenatary data products generating and visualizing results is also included, such as geospatial data for the basin. Contents There are two high level directories: `WRAP_archive/` and `repo_data/`. The `WRAP_archive` directory contains compressed intermediate dataproducts from the dataset generation workflow (marked as "I_Dataset_Generation" in the metarepo). These data products are not required by any scripts in the metarepo, but they are archived as they are expensive to generate and may have useful information for other analyses. The `repo_data` directory contains the necessary data for reproducing the workflow in the metarepo and should be decompressed and moved into the top level of the metarepo. Additional details are provided in README.md.

drought↗
DOE OSTI2021

GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files

This submission includes example files associated with the Geothermal Operational Optimization using Machine Learning (GOOML) Big Kahuna fictional power plant, which uses synthetic data to model a fictional power plant. A forecast was produced using the GOOML data model framework and fictional input data, and a genetic optimization is included which determines optimal flash plant parameters. The inputs and outputs associated with the forecast and genetic optimization are included. The input and output files consist of data, configuration files, and plots. A link to the Physics-Guided Neural Networks (phygnn) GitHub repository is also included, which augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints. phygnn is used by the GOOML framework to help integrate its machine learning models into the relevant physics and engineering applications. Note that the data included in this submission are intended to provide a demonstration of GOOML's capabilities. Additional files that have not been released to the public are needed for users to run these models and reproduce these results. Units can be found in the readme data resource.

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

Deep Learning Experiments for Tropical Cyclone Intensity Forecasts

Reducing tropical cyclone (TC) intensity forecast errors is a challenging task that has interested the operational forecasting and research community for decades. To address this, we developed a deep learning (DL)-based multilayer perceptron (MLP) TC intensity prediction model. The model was trained using the global Statistical Hurricane Intensity Prediction Scheme (SHIPS) predictors to forecast the change in TC maximum wind speed for the Atlantic basin. In the first experiment, a 24-h forecast period was considered. To overcome sample size limitations, we adopted a leave one year out (LOYO) testing scheme, where a model is trained using data from all years except one and then evaluated on the year that is left out. When tested on 2010–18 operational data using the LOYO scheme, the MLP outperformed other statistical–dynamical models by 9%–20%. Additional independent tests in 2019 and 2020 were conducted to simulate real-time operational forecasts, where the MLP model again outperformed the statistical–dynamical models by 5%–22% and achieved comparable results as HWFI. The MLP model also correctly predicted more rapid intensification events than all the four operational TC intensity models compared. In the second experiment, we developed a lightweight MLP for 6-h intensity predictions. When coupled with a synthetic TC track model, the lightweight MLP generated realistic TC intensity distribution in the Atlantic basin. Therefore, the MLP-based approach has the potential to improve operational TC intensity forecasts, and will also be a viable option for generating synthetic TCs for climate studies.

58 GEOSCIENCES↗
NASA NTRS2016

The Characterization of a DIRSIG Simulation Environment to Support the Inter-Calibration of Spaceborne Sensors

Climate change studies require long-term, continuous records that extend beyond the lifetime, and the temporal resolution, of a single remote sensing satellite sensor. The inter-calibration of spaceborne sensors is therefore desired to provide spatially, spectrally, and temporally homogeneous datasets. The Digital Imaging and Remote Sensing Image Generation (DIRSIG) tool is a first principle-based synthetic image generation model that has the potential to characterize the parameters that impact the accuracy of the inter-calibration of spaceborne sensors. To demonstrate the potential utility of the model, we compare the radiance observed in real image data to the radiance observed in simulated image from DIRSIG. In the present work, a synthetic landscape of the Algodones Sand Dunes System is created. The terrain is facetized using a 2-meter digital elevation model generated from NASA Goddard's LiDAR, Hyperspectral, and Thermal (G-LiHT) imager. The material spectra are assigned using hyperspectral measurements of sand collected from the Algodones Sand Dunes System. Lastly, the bidirectional reflectance distribution function (BRDF) properties are assigned to the modeled terrain using the Moderate Resolution Imaging Spectroradiometer (MODIS) BRDF product in conjunction with DIRSIG's Ross-Li capability. The results of this work indicate that DIRSIG is in good agreement with real image data. The potential sources of residual error are identified and the possibilities for future work are discussed..

Ambeau, Brittany L.↗
NASA NTRS1990

Observing system simulations using synthetic radiances and atmospheric retrievals derived for the AMSU and HIRS in a mesoscale model

The paper addresses the concept of synthetic satellite imagery as a visualization and diagnostic tool for understanding satellite sensors of the future and to detail preliminary results on the quality of soundings from the current sensors. Preliminary results are presented on the quality of soundings from the combination of the High-Resolution Infrared Radiometer Sounder and the Advanced Microwave Sounding Unit. Results are also presented on the first Observing System Simulation Experiment using this data in a mesoscale numerical prediction model.

Diak, George R.↗
DOE OSTI2025

Unsupervised Process Anomaly Detection and Identification Using the Leave-One-Variable-Out Approach

Automated anomaly detection and identification can signal equipment issues and pinpoint causes in large-scale industrial systems. For systems with limited failure history, unsupervised machine learning methods can be utilized as they do not require past failures. This study introduces the leave-one-variable-out (LOVO) model, which masks one variable at a time to predict the others, learning underlying process correlations. Detection performance was assessed with synthetic and experimental data, while identification performance used only synthetic data due to its ability to generate labeled anomaly types. For detection using synthetic data, the LOVO model generally outperformed comparative models; while using experimental data, the comparative methods outperformed the LOVO model. However, the comparative methods required selecting a latent size, and these conclusions pertain to using the optimal size. In practice, it would not be feasible to always select the optimal value, and incorrect selections impacted performance. In contrast, the LOVO model does not require a latent space. For identification using synthetic data, the LOVO model was slightly outperformed in interpretability and repeatability but still demonstrated impressive results. These outcomes suggest that the LOVO model is an effective model and may be more easily implemented without the challenging tuning process of selecting a latent size.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1997

The Chromosphere/Shock Dilemma of Non-Mira, Late-Type Variable Stars

An investigation of the atmospheric structure of non-Mira, asymptotic giant branch stars through NLTE radiative transfer modeling applied to hydrodynamic models is discussed. Synthetic spectra resulting from these calculations were compared with IUE observations of these stars to test the validity of the models. The development of the hydrodynamic models is detailed.

Willson, Lee Anne↗
NASA NTRS2019

A Suite of High-Resolution Atmospheric Carbon Dioxide Simulations in Support of the OCO-3 Snapshot Area Mapping (SAM) Mode Observation: PSU-WRF, CSU-OLAM and NASA GEOS

Cities and power plants are responsible more than 70% of GHG emissions. The emissions from the subnational localized sources need to be accurately quantified and properly managed in order to achieve the Paris Climate Agreement goals. The accurate estimation of these emission is also crucial for assessing the capacity of natural sinks to uptake the carbon released into the atmosphere that ultimately defines our emission allowance for the 1.5 or 2.0 degree temperature goals. New data collected by the Orbiting Carbon Observatory 3 (OCO-3) Snapshot Area Mapping (SAM) observations should provide a tremendous new opportunity for us to study CO2 emissions from targeted large localized sources, such as cities, power plants and beyond. Since 2018 (prior to the OCO-3 launch), we have studied the observational strategies for the SAM mode observation in order to collect the useful data for estimating CO2 emissions from target sources. To maximize the benefit of the SAM mode observation data for quantifying CO2 emission, it is important to define how to observe the localized sources depending on the local environmental and emission specificities. We employ a suite of state-of-the-art CO2 modeling systems, such as PSU's WRF-CO2, CSU's OLAM and NASA's GEOS models. All of these CO2 modeling systems are prescribedwith the high-resolution fuel CO2 emission estimates from the ODIAC data product to achieve realistic urban CO2 variations. We focus on cities with established ground-based observation networks, such as Los Angeles, Indianapolis, and Paris. We have examined the urban emission signal detectability in response to the influence of local background conditions that can observed by the SAM and biospheric contributions that will be a new challenge for urban emission inverse estimation. Based on the results of our simulation experiments, we plan to propose city-specific observation strategies. Upon the availability of the OCO-3 data, we will attempt to estimate city emissions using inverse models. We also developed synthetic OCO-3 data using NASA's GEOS5 model, which should be useful to assess the utility of the OCO-3 data in combination with data collected by carbon satellites in other orbits, such as NASA's OCO-2 and Japanese GOSAT-1/2. The synthetic data also provide an opportunity to study the errors due to clouds and aerosols, which have been not fully studied in the past.

Oda, Tomohiro↗
DOE OSTI2021

Multiscale Data-Driven Seismic Full-Waveform Inversion With Field Data Study

Seismic full-waveform inversion (FWI), which uses iterative methods to estimate high-resolution subsurface models from seismograms, is a powerful imaging technique in exploration geophysics. In recent years, the computational cost of FWI has grown exponentially due to the increasing size and resolution of seismic data. Moreover, it is a nonconvex problem and can encounter local minima due to the limited accuracy of the initial velocity models or the absence of low frequencies in the measurements. To overcome these computational issues, we develop a multiscale data-driven FWI method based on fully convolutional networks (FCNs). In preparing the training data, we first develop a real-time style transform method to create a large set of synthetic subsurface velocity models from natural images. We then develop two convolutional neural networks with encoder-decoder structures to reconstruct the low- and high-frequency components of the subsurface velocity models, separately. To validate the performance of our data-driven inversion method and the effectiveness of the synthesized training set, we compare it with conventional physics-based waveform inversion approaches using both synthetic and field data. Finally, these numerical results demonstrate that, once our model is fully trained, it can significantly reduce the computation time and yield more accurate subsurface velocity models in comparison with conventional FWI.

58 GEOSCIENCES↗
NASA NTRS1994

Experiments with the Mesoscale Atmospheric Simulation System (MASS) using the synthetic relative humidity

This study is intended to examine the impact of the synthetic relative humidity on the model simulation of mesoscale convective storm environment. The synthetic relative humidity is derived from the National Weather Services surface observations, and non-conventional sources including aircraft, radar, and satellite observations. The latter sources provide the mesoscale data of very high spatial and temporal resolution. The synthetic humidity data is used to complement the National Weather Services rawinsonde observations. It is believed that a realistic representation of initial moisture field in a mesoscale model is critical for the model simulation of thunderstorm development, and the formation of non-convective clouds as well as their effects on the surface energy budget. The impact will be investigated based on a real-data case study using the mesoscale atmospheric simulation system developed by Mesoscale Environmental Simulations Operations, Inc. The mesoscale atmospheric simulation system consists of objective analysis and initialization codes, and the coarse-mesh and fine-mesh dynamic prediction models. Both models are a three dimensional, primitive equation model containing the essential moist physics for simulating and forecasting mesoscale convective processes in the atmosphere. The modeling system is currently implemented at the Applied Meteorology Unit, Kennedy Space Center. Two procedures involving the synthetic relative humidity to define the model initial moisture fields are considered. It is proposed to perform several short-range (approximately 6 hours) comparative coarse-mesh simulation experiments with and without the synthetic data. They are aimed at revealing the model sensitivities should allow us both to refine the specification of the observational requirements, and to develop more accurate and efficient objective analysis schemes. The goal is to advance the MASS (Mesoscal Atmospheric Simulation System) modeling expertise so that the model output can provide reliable guidance for thunderstorm forecasting.

Chang, Chia-Bo↗
DOE OSTI2023

Accelerating full-waveform inversion using source stacking: synthetic experiments at the global scale in a realistic 3-D earth model

SUMMARY The spectral element method is currently the method of choice for computing accurate synthetic seismic wavefields in realistic 3-D earth models at the global scale. However, it requires significantly more computational time, compared to normal mode-based approximate methods. Source stacking, whereby multiple earthquake sources are aligned on their origin time and simultaneously triggered, can reduce the computational costs by several orders of magnitude. We present the results of synthetic tests performed on a realistic radially anisotropic 3-D model, slightly modified from model SEMUCB-WM1 with three component synthetic waveform ‘data’ for a duration of 10 000 s, and filtered at periods longer than 60 s, for a set of 273 events and 515 stations. We consider two definitions of the misfit function, one based on the stacked records at individual stations and another based on station-pair cross-correlations of the stacked records. The inverse step is performed using a Gauss–Newton approach where the gradient and Hessian are computed using normal mode perturbation theory. We investigate the retrieval of radially anisotropic long wavelength structure in the upper mantle in the depth range 100–800 km, after fixing the crust and uppermost mantle structure constrained by fundamental mode Love and Rayleigh wave dispersion data. The results show good performance using both definitions of the misfit function, even in the presence of realistic noise, with degraded amplitudes of lateral variations in the anisotropic parameter ξ. Interestingly, we show that we can retrieve the long wavelength structure in the upper mantle, when considering one or the other of three portions of the cross-correlation time series, corresponding to where we expect the energy from surface wave overtone, fundamental mode or a mixture of the two to be dominant, respectively. We also considered the issue of missing data, by randomly removing a successively larger proportion of the available synthetic data. We replace the missing data by synthetics computed in the current 3-D model using normal mode perturbation theory. The inversion results degrade with the proportion of missing data, especially for ξ, and we find that a data availability of 45 per cent or more leads to acceptable results. We also present a strategy for grouping events and stations to minimize the number of missing data in each group. This leads to an increased number of computations but can be significantly more efficient than conventional single-event-at-a-time inversion. We apply the grouping strategy to a real picking scenario, and show promising resolution capability despite the use of fewer waveforms and uneven ray path distribution. Source stacking approach can be used to rapidly obtain a starting 3-D model for more conventional full-waveform inversion at higher resolution, and to investigate assumptions made in the inversion, such as trade-offs between isotropic, anisotropic or anelastic structure, different model parametrizations or how crustal structure is accounted for.

Geochemistry & Geophysics↗
DOE OSTI2021

Subsurface Characterization and Machine Learning Predictions at Brady Hot Springs Results

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells - increasing or decreasing the fluid flow rates across the wells - and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. Data and supporting literature from a study describing a new approach combining reservoir modeling and machine learning to produce models that enable strategies for the mitigation of decreased heat and power production rates over time for geothermal power plants. The computational approach used enables translation of sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy and discovery of optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an "open-source" reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 hours, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 seconds. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs. Includes a synthetic, yet realistic, model of a geothermal reservoir, referred to as open-source reservoir (OSR). OSR is a 10-well (4 injection wells and 6 production wells) system that resembles Brady Hot Springs (a commercially operational geothermal field in Nevada, USA) at a high level but has a number of sufficiently modified characteristics (which renders any possible similarity between specific characteristics like temperatures and pressures as purely random). We study OSR through CMG simulations with a wide range of flow allocation scenarios. Includes a dataset with 101 simulated scenarios that cover the period of time between 2020 and 2040 and a link to the published paper about this project, where we focus on the Machine Learning work for predicting OSR's energy production based on the simulation data, as well as a link to the GitHub repository where we have published the code we have developed (please refer to the repository's readme file to see instructions on how to run the code). Additional links are included to associated work led by the USGS to identify geologic factors associated with well productivity in geothermal fields. Below are the high-level steps for applying the same modeling + ML process to other geothermal reservoirs: 1. Develop a geologic model of the geothermal field. The location of faults, upflow zones, aquifers, etc. need to be accounted for as accurately as possible 2. The geologic model needs to be converted to a reservoir model that can be used in a reservoir simulator, such as, for instance, CMG STARS, TETRAD, or FALCON 3. Using native state modeling, the initial temperature and pressure distributions are evaluated, and they become the initial conditions for dynamic reservoir simulations 4....

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Data Driven Online Learning of Power System Dynamics

With the advancement of sensing and communication in power networks, high-frequency real-time data from a power network can be used as a resource to develop better monitoring capabilities. In this work, a systematic approach based on data-driven operator theoretic methods involving Koopman operator is proposed for the online identification of power system dynamics. In particular, a new algorithm is provided, which unlike any previously existing algorithms, updates the Koopman operator iteratively as new data points are acquired. The proposed algorithm has three advantages: a) allows for real-time monitoring of the power system dynamics b) linear power system dynamics (this linear system is usually in a higher dimensional feature space and is not same as linearization of the underlying nonlinear dynamics) and c) computationally fast and less intensive when compared to the popular Extended Dynamic Mode Decomposition (EDMD) algorithm. The efficiency of the proposed algorithm is illustrated on an IEEE 9 bus system using synthetic data from the nonlinear model and on IEEE 39 bus system using synthetic data from the linearized model.

Sinha, Subhrajit↗
DOE OSTI2021

Deep learning inversion of gravity data for detection of CO 2 plumes in overlying aquifers

In this work, we developed an effective U-Net based deep learning (DL) model for inversion of surface gravity data on a rectangular grid to predict 2-D high-resolution subsurface CO 2 distribution along a vertical cross-section due to CO 2 leakage through a wellbore within a deep CO 2 storage reservoir. We used synthetic data to model two types of CO 2 leakage scenarios: one CO 2 plume in a shallow aquifer (single plume case), and two plumes present at different depths (double plume case). The 3-D synthetic plume samples were created by sampling among predetermined CO 2 plume depths, saturations, and volumes. The corresponding surface gravity data on a rectangular grid were generated by a 3-D forward model. The U-Net model detected 72% of single-plume samples, and one or both plumes in 75% of double-plume samples. Most of the undetected single plumes have small gravity field strengths below the typical noise level of 5 μGal. This model generated reproducible, reliable predictions with acceptable errors and demonstrated improved spatial resolution over the conventional least-squares inversion. In contrast to the conventional least-squares inversion, which often overestimates the size of its target and underestimates its density, this U-Net model accurately delineated the boundary of a target. Furthermore, this DL inversion detected deep, small, or low saturation CO 2 plumes that are often more difficult to resolve with conventional gravity inversion methods. We note the limitations of this feasibility study, including the use of synthetic data with regular CO 2 plume shapes, and the prediction of a 2-D plume cross-section rather than the full 3-D plume, as well, we recognize the lower detection fraction for double-plume scenarios. Nevertheless, this study demonstrates that DL gravity inversion is a promising and potentially superior method to conventional least-squares inversion. Our U-Net based deep learning inversion approach may be adapted for inversion of other types of geophysical data. DL inversion can facilitate near real-time monitoring of geologic carbon sequestration to provide site operators with prompt information about subsurface CO 2 distribution for risk management and mitigation.

58 GEOSCIENCES↗