Gravity Inversion Method Research Articles

Three-Dimensional Gravity Inversion Based on Attention Feature Fusion.

Three-dimensional gravity inversion is a process of obtaining the location, shape, and physical property parameters of underground anomaly sources using gravity anomaly data observed on the surface. In recent years, with the rapid development of data-driven methods, the application of deep learning (DL) to 3D gravity inversion has also attracted wide attention and achieved certain results. In this paper, based on the U-Net network, a three-dimensional gravity inversion method using an attention feature fusion mechanism is proposed. Using U-Net as the basic framework, the coarse-grained semantic features and fine-grained semantic features in the encoder and decoder are connected by long hops, and the global and local semantic features are aggregated through the attention feature fusion module, which avoids feature loss in the network training process. Compared with the inversion results of the U-Net network, the proposed method has a higher vertical resolution and effectively alleviates the influence of the skin effect on three-dimensional gravity inversion. Ablation experiments show that the attention feature fusion module is the key to improving the vertical resolution and prediction accuracy of inversion results. Noise experiments show that the inversion network in this study has a strong anti-noise ability and good generalization performance. The experimental results of the inversion network used in the prediction of the SAN Nicolas deposit in Mexico show that the inversion network can clearly predict the basic location and general shape of the sulfur deposit, and the results are in good agreement with the known geological data.

Recovering 3D salt dome by gravity data inversion using ResU-Net++

In geophysical research, gravity-based inversion is essential for identifying geologic anomalies, mapping rock structures, and extracting resources such as oil and minerals. However, traditional gravity inversion methods face challenges, such as the volumetric effects of gravity fields and the management of large complex matrices. Unsupervised learning techniques often struggle with overfitting and interpreting gravity data. This study explores the application of various U-Net-based network architectures in gravity inversion, each offering distinct challenges and advantages. Nested U-Net, although effective, requires a high parameter count, leading to extended training periods. The recurrent residual U-Net’s implicit attention mechanism restricts its dynamic adaptability, whereas the attention U-Net’s lack of residual connections raises concerns about gradient issues. This research comprehensively analyzes the training processes, core functionalities, and module distribution of these networks, including the residual U-Net++. Our synthetic studies compare these networks with traditional focused regularized gravity inversion for reconstructing density anomalies. The results demonstrate that the nested U-Net closely approximates the actual model despite some redundancy. The recurrent residual U-Net indicates an improved alignment with minimal redundancies, and the attention U-Net is effective in density prediction but encounters difficulties in areas of low density. Notably, the residual U-Net++ excels in inversion modeling, achieving the lowest misfit percentage and accurately replicating density values. In practical applications, the residual U-Net++ impressively reconstructs the F2 salt diapir in the Nordkapp Basin with well-defined boundaries that closely match seismic data interpretations. These results underscore the capabilities of the residual U-Net++ in geophysical data analysis, structural reconstruction, and inversion, demonstrating its effectiveness in simulated settings and real-world scenarios.

Three‐Dimensional Density Distribution and Seismic Activity along the Guxiang–Tongmai Segment of the Jiali Fault, Tibet

AbstractThe Guxiang–Tongmai segment of the Jiali fault is situated northeast of the Namche Barwa Syntaxis in northeastern Tibet. It is one of the most active strike‐slip faults near the syntaxis and plays a pivotal role in the examination of seismic activity within the eastern Himalayan Syntaxis. New study in the research region has yielded a 1:200000 gravity dataset covering an area 1500 km2. Using wavelet transform multiscale decomposition, scratch analysis techniques, and 3D gravity inversion methods, gravity anomalies, fault distributions, and density structures were determined across various scales. Through the integration of our new gravity data with other geophysical and geological information, our findings demonstrate substantial variations in the overall crustal density within the region, with the fault distribution closely linked to these density fluctuations. Disparities in stratigraphic density are important causes of variations in the capacity of geological formations to endure regional tectonic stress. Earthquakes are predominantly concentrated within the density transition zone and are primarily situated in regions of elevated density. The hanging wall stress within the Guxiang–Tongmai segment of the Jiali fault exhibits a notable concentration, marked by pronounced anisotropy, and is positioned within the density differential zone, which is prone to earthquakes.

A Deep Learning Gravity Inversion Method Based on a Self-Constrained Network and Its Application

Gravity inversion can be used to obtain the spatial structure and physical properties of subsurface anomalies through gravity observation data. With the continuous development of machine learning, geophysical inversion methods based on deep learning have achieved good results. Geophysical inversion methods based on deep learning often employ large-scale data sets to obtain inversion networks with strong generalization. They are widely used but face a problem of lacking information constraints. Therefore, a self-constrained network is proposed to optimize the inversion results, composed of two networks with similar structures but different functions. At the same time, a fine-tuning strategy is also introduced. On the basis of data-driven deep learning, we further optimized the results by controlling the self-constrained network and optimizing fine-tuning strategy. The results of model testing show that the method proposed in this study can effectively improve inversion precision and obtain more reliable and accurate inversion results. Finally, the method is applied to the field data of Gonghe Basin, Qinghai Province, and the 3D inversion results are used to effectively delineate the geothermal storage area.

Binary structure constrained gravity inversion based on seismic first arrival travel time data

Gravity exploration method is one of the important methods for deep mineral resource exploration, but gravity data inversion has limited resolution ability in the vertical direction. In order to improve the vertical resolution of gravity data inversion, we propose a binary structure constrained gravity inversion method based on seismic first arrival travel time data. This method effectively reconstructs a density model with high vertical resolution by transferring the structural information of a high-resolution velocity model reconstructed by seismic data inversion to gravity data inversion through the binary structure constrained technique. This strategy eliminates the need to integrate both gravity and seismic methods into a single inversion framework, avoiding both the difference in convergence speeds between the two methods, as well as getting rid of the complexity associated with calculating structural coupling terms. Theoretical simulations show that the fuzzy c-means cluster analysis technique can accurately extract the target region of the velocity model reconstructed by seismic data inversion. Under the constraint of seismic structural information, the resolution of reconstructed density model is much higher than that of separate gravity data inversion, which proves that high resolution seismic information can improve the vertical resolution of gravity data inversion. Compared with the traditional cross-gradient joint inversion, the binary structure constrained gravity inversion method can further improve the resolution of the density model, especially in the reconstruction of the anomaly interface, which verifies that the method has certain effectiveness.

Improved Gravity Inversion Method Based on Deep Learning with Physical Constraint and Its Application to the Airborne Gravity Data in East Antarctica

This paper aims to solve the limitations of traditional gravity physical property inversion methods such as insufficient depth resolution and difficulties in parameter selection, by proposing an improved 3D gravity inversion method based on deep learning. The deep learning network model is established using the fully convolutional U-net network. To enhance the generalization ability of the sample set, the large-scale training set and test set are generated by the random walk, based on the forward theory. Founded on the traditional loss function’s definition, this paper introduces an improvement incorporating a physical constraint to measure the degree of data fitting between the predicted and the real gravity data. This improvement significantly boosted the accuracy of the deep learning inversion method, as verified through both a single model and an intricate combination model. Finally, we applied this improved inversion method to the gravity data from the Gamburtsev Subglacial Mountains in the interior of East Antarctica, obtaining a comprehensive 3D crustal density structure. The results provide new evidence for the presence of a dense crustal root situated beneath the central Gamburtsev Province near the Gamburtsev Suture.

Density structure of the upper and middle crust in the northeast Dabie Orogen revealed by terrestrial gravity surveys

Moderate to strong earthquakes have occurred frequently in the northeast Dabie Orogen recently. From 2014 to 2017, the Guanmiao Earthquake Swarm (GES), with a maximum earthquake magnitude of M3.9, and the Quanjun Earthquake Swarm (QES), with a maximum earthquake magnitude of M3.7, occurred successively in the area near southeast Jinzhai County, where two main Mesozoic E–W‐striking boundary faults, including the Xiaotian–Mozitan and Xinyang–Shucheng faults, are cut by the Cenozoic NNE‐/NE‐trending dextral strike‐slip faulting system. These earthquake swarms occurred within areas of human activities and have the potential to cause more violent geological hazards. However, the tectonic geneses of the earthquake swarms are still unknown due to a lack of sufficient geophysical evidence. Based on terrestrial high‐resolution Bouguer gravity anomaly data, the density structure of the northeast Dabie Mountains is inverted using a 3D linear gravity inversion method. As a result, the occurrence and cutting depth of the reactivated faults near the earthquake swarms are defined, suggesting that the Shangloufang–Xialoufang Fault (F11) may be the seismogenic fault of the GES. The genesis of the QES is possibly associated with the fault termination of the Yingshan–Quanjun strike‐slip fault (F10). More broadly, F10 is one of the major synthetic faults of the NNE‐/NE‐trending dextral strike‐slip faulting system between the Tanlu and Shangcheng–Macheng (F2) faults, which bound the East Dabie Block together. The synthetic and antithetic faults fully cover the Beihuaiyang belt and North Dabie unit topography. These intraplate strike‐slip faults formed to accommodate vertical and lateral movements of the Dabie Mountains, driven by the oblique subduction of the Pacific Plate, were likely responsible for generating earthquakes in both Huoshan and Jinzhai.

A Novel Approach for Bathymetry Estimation through Bayesian Gravity Inversion

The bathymetry is the most superficial layer of the Earth’s crust on which it is possible to perform direct measurements. However, it is also well known that water covers more than 70% of the Earth’s surface, so an enormous expenditure of acquisition campaigns should be performed to produce a high-resolution map of this layer. Currently exploiting mainly commercial navigation routes, the sea floor coverage with shipborne sounding is only at 11%, and the remaining part is currently modeled by classical interpolation techniques or satellite-based gravity inversion methods. In the present work, a new method to refine bathymetry modeling based on the exploitation of global gravity field models is presented. In the proposed solution, once modeled and removed from the observed gravity field, the gravitational signals related to the deepest structures, a 3D Bayesian inversion algorithm is used to improve the actual knowledge of bathymetry. The proposed inversion method also enables limiting the solution to shipborne sounding measurements in such a way as to improve the seafloor grid where no local, high-quality information is available. Two test cases are discussed in the Mediterranean Sea region. Promising results are presented, opening the possibility of applying an analogous method to refine the bathymetry modeling at larger scales up to the global one.

An Object‐Oriented Bayesian Gravity Inversion Scheme for Inferring Density Anomalies in Planetary Interiors

AbstractGravity inversions have contributed greatly to our knowledge of the interior of planetary bodies and the processes that shaped them. However, previous global gravity inversion methods neglect the inference of mantle density anomalies when using techniques to decrease the non‐uniqueness of the inversion. In this work, we present a novel global gravity inversion algorithm, named THeBOOGIe, suited to inferring global‐scale density anomalies within the crust and mantle of planetary bodies. The algorithm embraces the nonuniqueness inherent in gravity inversions by not prescribing at the outset a density interface or depth range of interest. Instead, the method combines a Bayesian approach with a flexible incorporation of prior geological or geophysical information to infer density anomalies at any depth. A validation test using synthetic lunar‐like gravity data shows that THeBOOGIe can constrain the lateral location of crustal density anomalies but tends to overestimate their thicknesses. Importantly, THeBOOGIe can detect deep mantle density anomalies and quantify the level of confidence in the inferred density models. Our results show that THeBOOGIe can provide complementary information to one‐dimensional seismic models of the interior of the terrestrial planets and the Moon by constraining density anomalies that are not spherically symmetric. Additionally, THeBOOGIe is specially suited to constraining the interior of partially differentiated bodies where these large‐scale density anomalies are more likely to exist. Finally, thanks to the flexible use of priors, THeBOOGIe is an essential tool to understand the interior of planetary bodies lacking additional constraints.

Papua New Guinea Moho inversion based on XGM 2019e gravity field model

The construction of the high-resolution Moho depth model is significant for studying the characteristics of the complex tectonic movement (seafloor spreading, plate subduction phenomena) in Papua New Guinea. We calculate the region’s Moho relief and lithosphere thinning factor using the XGM 2019e gravity field model and nonlinear fast gravity inversion method under the GEMMA Moho depth model’s constraint considering the influence of lithosphere thermal gravity anomaly. The calculation result shows that the Moho depth is between 6—34 km, forming two large depressions in Woodlark Basin (WB) and Solomon Sea Plate (SSP) with deep scattered islands. In addition, the findings suggest that Significant differences exist in the shape and tectonic movement intensity of the North and South oceanic crust at the WB. Nevertheless, the lithosphere extends evenly in Manus Basin (MB). WB collided with the Solomon Islands at a higher angle than the SSP subducted under Bismarck Sea Plate (BSP); strong earthquakes may frequently occur on both sides and in deeper positions at West New Britain Trench in the future.

Deep learning to estimate the basement depth by gravity data using a feedforward neural network

We have developed a deep-learning method based on the neural network of the feedforward type to estimate the depth to the basement from potential fields. The data used to train and test the network are related to the Bishop synthetic model. A trial-and-error approach was used to find the hyperparameters that have the best compromise between performance and computation time. The training was organized by associating the depth values of the basement to the data through a moving window, running along profiles in the north–south and east–west directions. In this way, we generated a set of approximately 296,980 examples. We verified the robustness of the trained net by carrying out a test related to another synthetic model, extracted from the Himalaya digital elevation model. The inherent ambiguity of the problem led us to test two hypotheses for the estimation of the basement depth, the first related to a priori information on the density contrast and the shallowest depth and the second assuming the knowledge of the depth at least at two points, but not that of the density contrast. In these cases, our data-driven approach yielded interesting results leading to estimate the maximum depth in the first case and the density contrast in the second one. We finally applied the method to the isostatic anomaly of the Yucca Flat sedimentary basin, Nevada. The results are consistent with previous interpretations of the area, which were based on gravity inversion methods.

Gravity inversion constrained by OBS receiver function reveals crustal structure in Ryukyu Trench

The Ryukyu Trench is located in the northern Philippine Sea. The subduction of the Philippine Sea Plate to the Eurasia Plate along the Ryukyu Trench in the NNW direction leads to extremely complex tectonic processes such as subduction, collision, accretion, and back-arc expansion. It is of great significance to obtain the crustal structure of the Ryukyu Trench for understanding the crustal deformation characteristics, subduction direction and the scale of the Philippine Sea Plate. The ocean bottom seismometer (OBS) could provide important information on the deep structure of the oceanic area, and the wide coverage of gravity anomaly can provide more constraints for the regional crustal structure. In this study, we put the time-delay term of the sedimentary layer into the H-κ stacking formula, which eliminates the influence of the sedimentary layer in traditional H-κ stacking. Based on the accurate crustal thickness at OBS locations, a gravity inversion method is proposed to solve the problem of non-uniqueness in gravity data and limited distribution of OBSs. By using this method, we obtain a crustal structure with higher resolution than Crust1.0 model in Ryukyu Trench. The results show that the crustal thickness in the Ryukyu Trench region thickens along the NNW subduction direction, revealing that the Philippine Plate’s subduction direction towards the Eurasian Plate is in the NNW direction.

3D gravity inversion based on mixed-norm regularization in spherical coordinates with application to the lunar Moscoviense Basin

Three-dimensional gravity inversion has been widely used to infer density structures and tectonic movements of the earth and Moon. However, two problems (the nonuniqueness and low depth resolution) of current gravity inversion methods still exist and are not completely resolved, which affect the reliability of the inversion results and the corresponding geologic interpretation. To improve the depth resolution of the 3D gravity inversion, we propose an efficient inversion method in spherical coordinates based on a mixed smooth and focused regularization with depth-weighting functions. In the inversion, we also use the kernel matrix equivalence strategy and the fast kernel-vector multiplication method based on a fast Fourier transform in each iteration to increase computational efficiency. Two synthetic inversion examples indicate that the proposed method can recover more complex density structures compared with the often used smooth-constraint inversion approach. Finally, the proposed inversion approach is applied to the latest lunar gravitational field model GL1500E to study the 3D density structures of the Moscoviense Basin. The inverted results indicate that the density structure with high-positive anomalies is principally distributed at depths ranging from 5 to 70 km, forming a giant asymmetrical high-density structure inclining from the southwest to the northeast. We may conclude that the Moscoviense Basin was formed by the double impact, where the second collision occurred in the southwest of the basin center of the first collision.

Gravity inversion with a binary structure constraint imposed by magnetotelluric data and its application to a Carlin-type gold deposit

With characteristics of low cost and high efficiency, the gravity method is one of the most important means for the deep exploration of mineral resources. However, due to its inherent physical properties, its inversion results provide a limited vertical resolution. To reduce the uncertainty of gravity inversion, it is necessary to impose constraints from other geophysical methods, drilling, or geologic models. Based on the high vertical resolution of the multifrequency magnetotelluric (MT) data, we have developed a novel 2D gravity inversion method with a binary structure constraint imposed by MT data. The guided model is the density model reconstructed by the cross-gradient joint inversion of MT and gravity data, and the target and background regions of the guided model are divided using a fuzzy c-means clustering algorithm. The obtained binary target-background model is used as a structural constraint of the gravity inversion. The gravity inversion changes the density values of the target region rather than the background region, which can significantly reduce the dimensions of the inversion solution equation. The experimental results demonstrate that, even if the resistivity model and the density model indicate an inconsistent structure, the binary structure-constrained gravity inversion can reconstruct the density model with a higher degree of resolution than the traditional gravity inversion and cross-gradient joint inversion. Finally, we apply this algorithm to density modeling for the exploration of Carlin-type gold deposits in the southeast of the Jilin province, China, where the image determines the distribution of deep Paleoproterozoic Formation and high-density deposits, providing important technical support for the exploration of Carlin-type gold deposits.

Fast forward approximation and multitask inversion of gravity anomaly based on UNet3+

SUMMARYGravity inversion is a process that obtains the spatial structure and physical properties of underground anomalies using surface collected gravity anomaly data. In recent years, the rapid development of deep learning (DL) has enabled the achievement of good results for gravity inversion methods based on DL. These methods aim to learn the mapping between geological models and gravity anomaly data by training a neural network with geological models as labels. However, using DL inversion requires generating a large amount of training data for each geological target and involves the forward calculation of the generated models, which inevitably consumes a large amount of time and storage space. To address this issue, we propose using a neural network to approximate the expensive forward computation with a fast evaluation alternative. After training, the network can reproduce gravity anomalies at any observation point. To evaluate the effectiveness of the forward model, we use the gravity anomalies predicted by the forward network for inversion network training. Additionally, to mitigate the problem of poor generalization of existing DL inversions, we propose using multitask learning. By learning multiple related tasks simultaneously, the generalization ability of the model improves, thus enhancing the performance of the main task. In this paper, a multitask UNet3+ network is proposed to realize anomaly bodies localization and density contrasts reconstruction simultaneously. Test results on the synthetic data set demonstrate that the gravity anomalies predicted by the forward network can be successfully inverted, and the multitask approach can predict subsurface geology more accurately than the single-task. To further illustrate the effectiveness of the algorithm, we apply this method to the inversion of the San Nicolas deposit in central Mexico.

Gravity inversion method using L0-norm constraint with auto-adaptive regularization and combined stopping criteria

Abstract. We present a gravity inversion method that can produce compact and sharp images to assist the modeling of non-smooth geologic features. The proposed iterative inversion approach makes use of L0-norm-stabilizing functional, hard and physical parameter inequality constraints and a depth-weighting function. The method incorporates an auto-adaptive regularization technique, which automatically determines a suitable regularization parameter and error-weighting function that helps to improve both the stability and convergence of the method. The auto-adaptive regularization and error-weighting matrix are not dependent on the known noise level. Because of that, the method yields reasonable results even if the noise level of the data is not known properly. The utilization of an effectively combined stopping rule to terminate the inversion process is another improvement that is introduced in this work. The capacity and the efficiency of the new inversion method were tested by inverting randomly chosen synthetic and measured data. The synthetic test models consist of multiple causative blocky bodies, with different geometries and density distributions that are vertically and horizontally distributed adjacent to each other. Inversion results of the synthetic data show that the developed method can recover models that adequately match the real geometry, location and densities of the synthetic causative bodies. Furthermore, the testing of the improved approach using published real gravity data confirmed the potential and practicality of the method in producing compact and sharp inverse images of the subsurface.

Structural study of the transition zone between the Benue and Lake Chad Basins (Central Africa) using gravity data

This work is a contribution to the structural knowledge of the transition zone between the Benue and Lake Chad basins in Central Africa. To achieve this aim, gravity data analysis techniques such as polynomial separation, upward continuation, horizontal gradient and 3D gravity inversion method have been applied to the gravity data of this zone. The separate and upward-continue maps show significant anomalies. The new structural map of the study area presents 24 lineaments of N-S, NNW-SSE and SE-NW directions. The depth configuration map obtained reveals that the maximum depth of the basement in the study area is approximately 2.2 km. The results of this study show that despite the barriers that separate the two sedimentary basins there is a possibility of having a communication channel between the two basins to the West of the study area. This channel could pass between the localities of Garoua, Belel, Figuil and Bourrha.

Deep Learning for 3-D Inversion of Gravity Data

Three-dimensional (3-D) gravity inversion obtains the density distribution of subsurface geological bodies through observed gravity anomalies. Recently, data-driven methods based on deep neural networks (DNNs) have received considerable attention for geophysical inverse problems. They proved to be superior to physics-driven methods that suffer from nonuniqueness issues and high computational costs. Several deep-learning inversion strategies have been developed for geophysical modeling and are mainly applicable for two-dimensional (2-D) subsurface imaging. Despite their effectiveness, deep-learning inversions suffer from appropriate generalization to new case scenarios. In this study, a novel 3-D gravity inversion method based on encoder–decoder neural networks is proposed. The network has a gravity field encoder for 2-D gravity field feature extraction, a dimension transformation module for feature space transformation, and a density structure decoder for 3-D density structure reconstruction. A highly random dataset is constructed to enlarge the feature distribution space of the samples and perform hyper-parameter experiments to improve the accuracy and generalisability of the network. Numerical examples using synthetic gravity data show that the accuracy of the network can reach 97% in the entire area and 81.5% in the area of density structures while reducing the computational time by 20 times. In the experiments on real data of the Vinton salt dome, the results are in good agreement with the known geological information. Our method significantly improves the inversion accuracy and generalisability of 3-D gravity inversion and can be applied in real case scenarios with less computational time.

Analysis on the Characteristics of Crustal Structure and Seismotectonic Environment in Zigui Basin, Three Gorges

The Zigui Basin in the Three Gorges area is a syncline running in the north-south axial direction; the sediments in the basin are mainly late Triassic-late Jurassic sandy and argillaceous rocks. Since the Three Gorges Project began undergoing impoundment in May 2003, nearly 20,000 mini-earthquakes have occurred in the Zigui–Badong region, including five earthquakes with magnitudes greater than Ms 5.0. Herein, a 3D gravity inversion method was introduced to investigate the density structure of the Zigui Basin and its adjacent areas. A comprehensive analysis of the geological structure of the area was carried out, based on focal mechanism solutions of six moderate–strong earthquakes in the area. The Zigui Basin is a low–density area from the periphery, and the sediment in the east is thicker but less dense than in the west. The shallow part of the Zigui Basin is a weak bottom layer prone to slippage, and the deep part (5–10 km) could comprise lithological strata such as limestone, sandstone, and shale, which easily undergo dissolution by leaking reservoir water. Under the action of external forces such as long-term infiltration and unloading of reservoir water, fissures will expand and squeeze then earthquakes are likely induced in the deep strata. Furthermore, new buried faults in the western and southeastern edges of the core area of the Zigui Basin could also trigger an earthquake under long–term pressurization and reservoir water penetration.

Deep learning inversion of gravity data for detection of CO2 plumes in overlying aquifers

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 CO2 distribution along a vertical cross-section due to CO2 leakage through a wellbore within a deep CO2 storage reservoir. We used synthetic data to model two types of CO2 leakage scenarios: one CO2 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 CO2 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 CO2 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 CO2 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 CO2 distribution for risk management and mitigation.