Salt Bodies Research Articles

Theoretical and numerical studies on dissolution of horizontal salt body and pattern formation incorporated with a dynamic moving interface

The dissolution of a horizontal salt body is theoretically and numerically investigated by considering the coupled dynamics of the dissolution reaction and the diffusive and convective mass transfer at the salt surface. To take into account the nature of the recessing salt surface and the dissolution-driven convection, a dynamic moving boundary condition coupled with a dissolution reaction are employed By employing a newly derived moving interface condition and parameters, a theoretical analysis predicts the onset of gravitational instability, suggesting scaling relationships between parameters to describe the onset of instability (in transport-dominant (Damkholer number $Da \to \infty $ and Rayleigh number $Ra > {10^5}$ ), onset time ${\tau _d}\sim R{a^{ - 2/3}}$ and ${\tau _d}\sim (RaDa)^{1/4}$ for reaction-dominant regimes $(Da \to 0)$ ). The scaling relationships on dissolution (the average height change, $\Delta {h_{avg}}\sim \sqrt \tau $ for the diffusion-dominant regime and $\Delta {h_{avg}}\sim R{a^{0.79/3}}{\tau ^{0.86}}$ for the convection-dominant regime) are also suggested to explain the pattern formation. Under a convective mass transfer condition, the concentration gradient of the solute developed during the recession of the salt surface results in an adverse density gradient, which causes gravitational instability motion and finally determines the formation of a dissolution pattern. In addition, two-dimensional and three-dimensional numerical simulations visualize dissolution-driven convective flow fields, the recession of the liquid-solid interface and pattern formation on the dissolving interface. Theoretical and numerical analyses of the dissolution process suggest that the control of gravitational instability is important to prevent or enhance dissolution pattern formation. This systematic parameter study provides a deep understanding of the effect of gravitational instability on convection-driven dissolution in a horizontal geometry.

Salt reconstruction in full-waveform inversion using topology optimization techniques

SUMMARY With the increasing advances in the oil and gas industry, seismic imaging near or under salt structures has become an important point in deep-water exploration. Detailed velocity models of these areas are particularly interesting not only to characterize hydrocarbon reservoirs but also to identify potential sites for hydrogen and carbon dioxide storage in offshore salt caverns. Thus, we study the full-waveform inversion for the salt reconstruction in acoustic media with constant density considering the time-harmonic wave propagation in a finite element formulation using the topology optimization (TO) method. This problem is challenging due to the strong velocity contrast between salt bodies and the sedimentary background, in addition to the lack of low-frequency data and the inherent ill-posedness of the inverse problem. In this context, we incorporate techniques from the TO field, usually used in design applications, to overcome or reduce these known problems. We initially defined the squared slowness as a combination of two fields, one related to the salt shape and the other to the background. An interpolation rule based on the solid isotropic material with penalization method, combined with filtering and projection schemes, is used to find the shape of the salt bodies with increased sharpness interfaces. A Helmholtz-type filter is applied to modify the gradient aimed to regularize the problem and provide a more stable way for the salt shape to evolve during the inversion process. In particular, we demonstrate that the proposed approach may be relevant for reconstructing media with salt bodies when a suitable starting model is unavailable, and sharp interfaces are required. In addition, we present inversion results from synthetic data generated by a variable density model to demonstrate the approach capability when subjected to a reconstruction application.

Investigating seismic mode conversions from an ultra-high-velocity caprock by physical modelling, numerical simulations and a Gulf of Mexico salt proximity VSP survey

SUMMARY Salt structures are widely distributed in many basins worldwide and play an important role in understanding tectonic movements, offering underground storage and sealing hydrocarbon traps. In addition to the acknowledged difficulties in mapping complex salt structures through seismic methods, when an evaporitic layer, such as anhydrite, forms over salt, it can introduce strong multimode conversions that can couple with the primary compressional wavefields and generate artefacts in resulting acoustic images. From two well-log suites from the Gulf of Mexico, we identify thin evaporitic caprocks on top of their salt bodies and analyse their elastic properties. Through controlled experiments, including physical and numerical modelling with a vertical seismic profiling survey geometry, we observe significant shear-mode conversions at the top of the ultra-high-velocity caprock, which further result in a family of prominent S and P (converted from S wave) modes across the top of the salt region. Similarly, in a field survey, we identify evident converted S waves and a multimode P wave (converted S wave in the anhydrite layer, and P wave elsewhere) following the primary P transmission inside the salt body. While separating the converted Smodes at the receiver end is more unambiguous, the multimode P waves could behave very similarly to the primary Pmodes and are more difficult to suppress. Under the common acoustic assumption of seismic velocity model building and imaging, complex mode conversions on top of the salt are generally ignored. Through controlled experiments and a field survey, we analyse the pitfalls associated with this omission. We emphasize the importance of understanding the physics of wave partitioning in the presence of a thin ultra-high-velocity layer on the top of the salt.

Hydrogen sulphide (H2S) migration in groundwater of the Zechstein strata in the Legnica-Głogów Copper Basin and its vicinity, SW Poland

Hydrogen sulphide (H2S) occurs in groundwater in various lithostratigraphic units of the Zechstein Basin in the Legnica-Głogów Copper Basin (SW Poland). This region is located in the Fore-Sudetic Monocline within which, several tens of kilometres NE of the study area, at greater depths, natural gas fields with hydrogen sulphide (H2S) occur. The Main Dolomite (Ca2), in which H2S-containing natural gas has accumulated, is younger than the Zechstein Limestone (Ca1), which is actively mined. The Ca2 and Ca1 formations are separated by a thick anhydrite succession including a wedge-shaped salt body. Hydrochemical analyses of 18 groundwater samples taken from different horizons within the Zechstein strata showed spatial variability ofH2S and chloride concentrations. A conceptual model of groundwater flow with dissolved H2S in the Zechstein formations was developed. H2S migration is associated with groundwater flow between the Ca2 and Ca1 aquifers through fissures in the anhydrite strata that separate them. Hydraulic contact through fissures in the anhydrite layers is the result of long-term exploitation of the underground copper deposit. Groundwater flow between the layers is influenced by a large change in the piezometric pressure of the groundwater in the depression cone caused by mining drainage.

Application of Q-FWI-tomography and least-squares migration to improve seismic resolution in Tengiz oil field

Seismic image deterioration is a major problem for structures under complex overburdens. In areas under major faults and salt bodies, it is common to observe amplitude washout zones, poor structural definition, and relatively strong coherent and incoherent seismic noise. We developed a data-driven workflow of Q least-squares migration to mitigate these problems by enhancing the horizontal and vertical resolutions of seismic images. The workflow includes accurate velocity model building with joint full-waveform inversion and tomography to maximize the stacking power of P-wave primaries, Q tomography that balances weak-amplitude washout zones and minimizes swing noises, and least-squares migration with the aid of a constraint map that yields higher-resolution structural images. Its application on a wide-azimuth data set from the Tengiz oil field demonstrates the effective mitigation of fault shadow issues with an overall improvement of image quality. In addition, the uplift in focusing of diffracted energies shows promising improvements in enhancing seismic mega-amplitude events. Thus, the proposed method greatly increases the fidelity of seismic attribute analysis when compared with conventional vintage processing.

Enhancing salt model resolution and subsalt imaging with elastic FWI

Full-waveform inversion (FWI) has become the centerpiece of velocity model building (VMB) in seismic data processing in recent years. It has proven capable of significantly improving the velocity model and, thus, the migration image for different acquisition types and geologic settings, including complex environments such as salt. With the advent of FWI imaging, the scope of FWI applications has extended further from VMB into the imaging landscape. However, current FWI applications in the industry prevalently employ the acoustic approximation. One common problem of acoustic FWI (A-FWI) is the apparent salt halos at the salt-sediment interface in the resulting FWI velocity and FWI image, the presence of which hinders direct interpretation and imaging focusing around salt bodies. With synthetic and field data examples, we demonstrate that this salt halo is caused mainly by the large mismatch between the elastic recorded data and the acoustic modeled data, particularly at middle to long offsets. To overcome limitations imposed by acoustic assumptions, we developed an elastic FWI (E-FWI) algorithm that combines an elastic modeling engine with the time-lag cost function, which we call elastic time-lag FWI (E-TLFWI). With a more accurate modeling engine, E-TLFWI significantly reduces the salt halo observed in its acoustic counterpart. However, we also observe that the images migrated using the A-FWI and E-FWI velocity models remain similar overall, with some slight improvements around and beneath salt boundaries, particularly near steep salt flanks, as a result of the reduced salt halo. By contrast, FWI images derived from E-TLFWI show considerable benefits over those from acoustic time-lag FWI, such as improved event focusing, better structural continuity, and higher signal-to-noise ratio. The sharpened salt boundaries and enhanced quality of the FWI images reveal the significant value of E-FWI and provide the justification for its greatly increased cost.

Can elastic waveform inversion benefit from inverting multicomponent data?

Waveform inversion aims to retrieve high-resolution earth parameter volumes. Due to its high computational cost, acoustic approaches using low to mid seismic data frequencies are often applied in velocity model building. However, in the presence of large parameter contrasts, an elastic formulation should be preferred due to wave interferences that limit the applicability of phase- and kinematics-only approaches. The benefits of elastic waveform inversion have been demonstrated with inversion of hydrophone data in marine environments. Here, we extend the approach to inversion of the vertical geophone component. We propose a weighted cost function in the waveform inversion algorithm to jointly invert multicomponent data sets, and we compare the results to the inversion of single-component data. For this study, we use an ocean-bottom-node data set from the deepwater Gulf of Mexico around a salt dome. We show that slightly different velocity models, reverse time migration images, and angle gathers are retrieved when using hydrophone or vertical geophone data, further improving either the shallow or deeper sediments. The joint inversion combines the improvements brought by the single-component inversions. Though it doubles the cost, joint elastic waveform inversion of hydrophone and vertical geophone data can help velocity model building around salt bodies.

Estimation of Salt Intake in Normotensive and Hypertensive Children: The Role of Body Weight.

The connection between increased dietary salt intake and arterial hypertension has been recognized for a long time, even in children. This study aimed to investigate salt consumption in normotensive and hypertensive children and evaluate their dietary habits. A total of fifty participants were included in this cross-sectional study: twenty-five normotensive children and 25 children of both sexes with essential arterial hypertension from 12-17 years old. Subjects' body mass index, waist-to-hip ratio, body composition and arterial blood pressure were measured, and their daily salt intake was calculated from 24-h urine samples. Using the food frequency questionnaire (FFQ), the data on the average daily total energy and food intakes were collected and analyzed using a suitable program. Estimated daily salt intake was significantly higher in hypertensive compared to normotensive children, and this is positively associated with blood pressure and body mass index (BMI). Hypertensive children had significantly higher BMIs, which also positively correlated with blood pressure. Consistently, resting metabolic rate (kcal) is higher in hypertensive children compared to normotensive, and this is also associated with blood pressure. Reported energy intake is also enlarged in hypertensive compared to normotensive children and for both groups, levels are significantly higher than the recommended values. Our study results confirm the relationship between daily salt consumption, blood pressure and body weight. Sodium consumption related to blood pressure and body weight among children. Cardiovascular disease prevention should start in early childhood by reducing salt intake and preventing overweight/obesity since these are two of the most important modifiable risk factors for hypertension.

Three-Dimensional Initial Salt Body Building for Full-Waveform Inversion Assisted by Deep Learning

Salt bodies represent a significant challenge when performing full-waveform inversion (FWI) due to convergence issues when retrieving high-contrast geological structures. Recent advances in FWI promote the adoption of data regularization to address this problem. However, the model complexity where the bodies are enclosed tends to be the leading cause of unsatisfactory results. In recent years, the implementation of deep learning to tackle this issue has been proposed; however, these solutions generally rely on a direct mapping between the input (gathers) and output data (2D salt bodies) that are usually builtusing large datasets to become effective. In this study, we propose a simple and robust methodology for 3D initial salt body building assisted by deep learning. Two pre-trained models identify reflections associated with salt bodies on 3D shot gathersfrom the SEG/EAGE 3D salt model. Then, a 3D initial salt body is outlinedand built with RTM using only the deep learning-identified reflections. Finally, the 3D salt body is embedded into a background velocity model to conclude the initial model building for FWI. The accuracy of the initial model is tested by performing FWI, where observedand modeled data are compared, showing satisfactory results.

MDA GAN: Adversarial-Learning-Based 3-D Seismic Data Interpolation and Reconstruction for Complex Missing

The interpolation and reconstruction of missing traces is a crucial step in seismic data processing, moreover it is also a highly ill-posed problem, especially for complex cases such as high-ratio random discrete missing, continuous missing and missing in fault-rich or salt body surveys. These complex cases are rarely mentioned in current works. To cope with complex missing cases, we propose Multi-Dimensional Adversarial GAN (MDA GAN), a novel 3-D GAN framework. It keeps anisotropy and spatial continuity of the data after 3D complex missing reconstruction using three discriminators. The feature splicing module is designed and embedded in the generator to retain more information of the input data. The Tanh cross entropy (TCE) loss is derived, which provides the generator with the optimal reconstruction gradient to make the generated data smoother and continuous. We experimentally verified the effectiveness of the individual components of the study and then tested the method on multiple publicly available data. The method achieves reasonable reconstructions for up to 95% of random discrete missing and 100 traces of continuous missing. In fault and salt body enriched surveys, MDA GAN still yields promising results for complex cases. Experimentally it has been demonstrated that our method achieves better performance than other methods in both simple and complex cases. Moreover, our network does not require training weights for each survey, the same weights it uses are applied to multiple surveys, significantly reducing time and computational costs, and we make the model publicly available on https://github.com/douyimin/MDA_GAN.

The Role of Salt Tectonics in the Energy Transition: An Overview and Future Challenges

In this paper we examine the role salt tectonics can play in a number of key energy transition technologies, namely, energy storage as gas in salt caverns (e.g. hydrogen and compressed air), CO2 storage, and geothermal energy. For each of these technologies we explore: i) fundamental concepts and driving forces; ii) how and why the properties of salt are of importance; and iii) the key salt-related technical challenges, potential future research directions, and technical approaches needed for large-scale development. We highlight how salt-bearing basins offer vast potential for development throughout the energy transition including, but not limited to: i) the likely demand for thousands of new hydrogen storage caverns inside salt bodies by 2050; ii) a likely early focus for porous media CO2 storage sites in basins strongly influenced by salt tectonics; and iii) enhanced geothermal energy potential in and around salt bodies. Effective exploitation of these resources will require a deeper understanding of the internal composition, geometry, and evolution of salt structures and their surrounding sediments, and potentially the development of more predictive models of salt tectonic behaviour. Critically, we see the need to integrate learnings of salt tectonics gained in the academic, mining, solution mining, and oil and gas communities, and apply a fresh perspective to answer research questions of relevance to the energy transition. Developing this new understanding will help optimise design, reduce geotechnical risk, and improve efficiency for energy transition technologies, thus indicating a strong future demand for salt tectonic research.

Matrix deformation and fracture network in minibasins in a foreland fold and thrust belt: The Sivas Basin, Turkey

We use a multiscale study to investigate the strain record in the continental sandstones-filled minibasins of the Sivas Basin. Located on the central Anatolian Plateau, the Sivas basin is a foreland fold-and-thrust belt characterized in its central part by a wall and basin province in which two generations of Oligocene minibasins develop. We collected 399 oriented cores and 2504 fractures in the lower and middle members of the continental Karayün Formation from four minibasins (Emirhan, Karayün, Egribuçak and Ilkindi). Integrated analyses support several observations: (i) an early fracture set, striking NS, occurs in all minibasins. These fractures developed prior to macroscopic halokinetic structures formation (such as megaflap) and prior to minibasin tilting, during Layer Parallel Shortening (LPS). (ii) A preferential orientation of matrix texture, estimated using anisotropy of magnetic susceptibility, is related to the LPS direction only in the Emirhan minibasin. (iii) A second, younger, fracture set, oriented parallel to the tilting axes of the minibasins and to the thrust faults, developed prior to minibasin tilting or folding of minibasin edge structures (known as megaflaps, megahooks and composite halokinetic sequences). The existence of the carapace above raising salt bodies enables the propagation of the LPS deformation in response to regional shortening. However, once the carapace is broken due to the salt rise, there is no evidence of deformation at the meter and matrix scales in relation with FTB shortening affecting the wall and basin domain. The large bodies of evaporites preferentially accommodate compression in between minibasins through internal diapir squeezed. Salt bodies inhibit matrix and mesoscale deformation within the minibasins.

Integrating U-Nets Into a Multiscale Full-Waveform Inversion for Salt Body Building

Integrating U-Nets Into a Multiscale Full-Waveform Inversion for Salt Body Building

Low-frequency ambient ocean-bottom node surface-wave seismology: A Gulf of Mexico case history

Long-time marine seismic recordings are becoming more common with the increased use of ocean-bottom nodes (OBNs), which can measure ambient seismic energy at frequencies lower than the typical minimum values in active-source compressed air-gun surveys. Interferometric processing on long-time ambient multicomponent data allows for the extraction of low-frequency (sub-2.0 Hz) responses in virtual source gathers (VSGs). Using 40 days of continuous OBN recordings acquired on a large dense array during a field experiment in the Gulf of Mexico, we find that sub-2.0 Hz surface-wave energy in the computed VSGs is strongly coherent and exhibits an identifiable spatially varying character. In particular, after rotating the data components from a Cartesian geographic into a polar wave-vector reference frame, we find that radial VSGs (i.e., oriented along the vector connecting the virtual source and receiver) clearly indicate that surface-wave propagation is influenced by salt bodies as identified in a colocated active-source survey situated at a minimum of 0.7 km depth below the seafloor, an observation consistent with calculated 0.25–0.50 Hz surface-wave sensitivity kernels. This suggests that low-frequency ambient OBN surface-wave seismology could be important for estimating the long-wavelength elastic material properties (particularly S-wave velocity) and identifying the lateral boundaries of salt bodies without any prior knowledge of subsurface geology.

Tectonic evolution of the Triassic diapirs in the southern front of the Rif belt, Northern Morocco

Located at the front of the external Pre-Rif, northern Morocco, at the edge between the Rif cordillera and the Saiss neogen basin, Triassic diapirs constitute one of the main features of this area, occurring within the Meso-Cenozoic allochthonous formations. In order to understand their geological setting and evolution during the Meso-Cenozoic times, we carry out a geological study based on structural analysis and fracturing field investigations. The obtained results are completed by previous geophysical and seismic works. The rising salt bodies (halite, anhydrite and gypsum) in those diapirs was controlled by the two NW-SE and NE-SW system faults from the Mesozoic to the Quaternary. The contacts between the Triassic material and the Miocene sedimentary marls are discussed. Some mapped tectonic contacts, considered as thrusting faults are in fact stratigraphic limits, which are characterized by polygenic conglomerates. These arguments allow us to review the whole history of these salt walls and to discuss their current geometry.

Finding the right place in Mohr circle space: Geologic evidence and implications for applying a non-linear failure criterion to fractured rock

The ability to relate patterns of brittle rock failure to stress conditions permits geologists to better understand the nature of rock deformation in natural geologic settings. In the field of structural geology, the relationship between shear and normal stress at the time of rock failure, a critical element of any failure criterion, is most commonly assumed to be linear in compressive stress environments. However, derivation and utilization of linear and non-linear failure criteria have been debated and variably invoked in past laboratory, field, and modeling-based analyses. In a study of fractured Jurassic Moab Tongue Member sandstone (Entrada Formation) bordering Arches National Park (Utah), we have documented field evidence for a system of shear fractures whose character and kinematics are best explained by a non-linear failure criterion. This field setting is distinguished by lateral subjacent juxtaposition of a salt-wall diapir (to the northeast) and the fractured sandstone (to the southwest). The shear fracture system reveals conjugate dihedral angles that systematically decrease northeastward reflecting decreasing critical differential stress magnitudes along a non-linear failure criterion, driven by a reduction in mean normal stress closer to the salt-sediment interface. These stress conditions are most likely associated with the mechanical response of the adjacent salt body to tectonic loading. Augmented by experimental rock failure testing, we provide novel field-based evidence that a non-linear failure criterion is most applicable in this natural geologic environment. We also present a pathway to gain insight into paleostress magnitudes utilizing observed failure angles and a geomechanically constrained non-linear failure criterion.

From Salt‐Bearing Rifted Margins to Fold‐And‐Thrust Belts. Insights From Analog Modeling and Northern Calcareous Alps Case Study

AbstractAnalog modeling is used to study the role played by the inherited salt‐sediment architecture of a salt‐bearing rifted margin, developed by minibasin downbuilding and margin‐scale gliding, and then incorporated into a fold‐and‐thrust belt system influenced by surface processes. Inherited salt bodies localize contractional deformation at different scales and the salt‐sediment architecture determines structural styles of fold‐and‐thrust belts. In our analog models, a large‐transport thrust detached along allochthonous model salt (silicone polymer) accumulated in a former distal raft system. And the squeezing of salt walls, together with the tilting of minibasins, accounted for most of the shortening in a salt wall‐minibasin province. Shortening and surface processes promote the extrusion and erosion of about 75% of the original model salt. The role played by salt tectonics during the contraction of salt‐bearing rifted margins could be underestimated because of the low salt‐sediment ratio found in fold‐and‐thrust belts. Our modeling results are compared with and assist in the interpretation of a section along the Northern Calcareous Alps.

Quantifying uncertainty of salt body shapes recovered from gravity data using trans-dimensional Markov chain Monte Carlo sampling

SUMMARY Accurate delineation of salt body shapes is critical for hydrocarbon exploration. Various imaging methods based on seismic data have been developed. Due to the density contrast between salt and sedimentary rocks, gravity data have also been used as a de-risking tool to constrain the salt body shapes. However, quantifying uncertainties of the salt body shapes recovered from gravity data remains underexplored. Our goal is to understand and quantify how different constraints affect uncertainties of the salt body shapes reconstructed from gravity data. We adopt a trans-dimensional Markov chain Monte Carlo (MCMC) approach to explore the uncertainties. To address the computational challenges with MCMC sampling, we resort to two methods: sparse geometry parametrization and randomized parallel tempering. The first uses a set of simple geometries (e.g. ellipses) to approximate the complex shapes of salt bodies, greatly reducing the number of parameters to be sampled and making the MCMC approach computationally feasible. The second serves to further improve the acceptance ratio and computational efficiency. To quantify the uncertainties of the recovered salt body shapes, we design several scenarios to simulate different constraints on the top boundary of salt bodies from seismic imaging. We develop a new method to impose structural constraints on the top boundaries of salt bodies. This new method combines a set of fixed ellipses with randomly sampled ellipses through a concave hull. The results from different scenarios are compared to understand how uncertainties are reduced when stronger constraints are imposed. In addition, to make our uncertainty quantification results more relevant for practitioners, we propose to compute the salt probability models which show the spatial distribution of probabilities of salt materials at each cell. Finally, we investigate the effect of an uncertain salt density on the salt body reconstruction and the case of depth-varying densities in the sedimentary background. We apply our methods to the modified 2-D SEG-EAGE and Sigsbee salt models and quantify the uncertainties of the recovered salt body shapes in different scenarios. Our results highlight the importance of properly interpreting the uncertainty estimates in light of prior information and information content in the data.

Deep learning strategy for salt model building

Velocity models are crucial intermediate products generated in seismic data processing, and the model’s accuracy is essential for constructing quality seismic images. Conventional approaches to velocity-model building (VMB) use a family of inversion methods, among which are ray-based tomography and full-waveform inversion. These methods have been highly optimized throughout the years but are still heavily dependent on continuous human curation of the results, which leads to an overall high time cost, especially in areas with high structural complexity, such as those containing salt tectonics. We have investigated a deep learning (DL) approach that accurately defines salt geometries for VMB. We train our convolutional neural network on synthetic shot gather data, explore a manner of leveraging information through summation of shot data, and determine the influence that the choice of loss function has on the quality and aspect of predicted velocity models. Our residual U-Net model trained on data containing only randomly shaped salt bodies can estimate geologically complex salt geometries such as those in 2D SEG/EAGE salt model slices. Our results find that deeper encoder-decoder models with shortcut connections resolve velocity model structures better than shallower models. Moreover, network models trained with a composite loss function — combining mean absolute error and the multiscale structural similarity index — better delineate the contours of areas with high-velocity contrast and better recover regions with a uniform velocity trend than network models trained with conventional loss functions like the mean squared error. The residual U-Net and loss functions that we use are not task-specific and can be extended to other DL approaches to VMB.

Complete identification of complex salt geometries from inaccurate migrated subsurface offset gathers using deep learning

Delimiting salt inclusions from migrated images is a time-consuming activity that relies on highly human-curated analysis and is subject to interpretation errors or limitations of the methods available. We develop the use of migrated images produced from an inaccurate velocity model (with a reasonable approximation of sediment velocity, but without salt inclusions) to predict the correct salt inclusions shape using a convolutional neural network. Our approach relies on subsurface common-image gathers to focus the sediments’ reflections around the zero offset and to spread the energy of salt reflections over large offsets. Using synthetic data, we train a U-Net to use common-offset subsurface images as input channels and the correct salt masks as the output of a semantic segmentation problem. The network learns to predict the salt inclusions masks with high accuracy; moreover, it also performs well when applied to synthetic benchmark data sets that were not previously introduced. Our training process successfully tunes the U-Net to learn the shape of complex salt bodies from partially focused subsurface offset images.