Gas Reservoirs Research Articles

A novel model of kinetics and thermodynamics for shale gas adsorption–diffusion

The study of adsorption–diffusion kinetics in shale gas reservoirs is crucial for predicting reserves and assessing production. Although some scholars have proposed adsorption–diffusion kinetics models, there are few models and interpretation methods that systematically consider Arrhenius’s thermodynamics parameters and actual adsorption gas concentration. In this study, we propose a novel model for analyzing the kinetics processes of adsorbed gas and free gas in shale. The analysis of adsorbed gas kinetics experimental data indicates a negative correlation between temperature and the adsorption–diffusion equilibrium time. Sensitivity analysis of the parameters reveals that three parameters (the diffusion activation energy, adsorption activation energy, and desorption pre-exponential factor) are positively correlated with adsorption–diffusion equilibrium time, whereas the other three parameters (the diffusion pre-exponential factor, adsorption pre-exponential factor, and desorption activation energy) are negatively correlated. Furthermore, we find that higher temperatures lead to lower concentrations of free gas at equilibrium state. Larger radius positions in spherical particles tend to reach adsorption–diffusion equilibrium earlier. Compared to the traditional diffusion kinetics model, the proposed novel model exhibits a significant lag effect in the calculated equilibrium time and more accurately describes the gas adsorption-diffusion kinetics equilibrium process.

Calculation and application of elastic modulus of mineral components in tight sandstone based on adaptive method

Abstract For the petrophysics modelling of tight sandstones, the elastic modulus of their sandstone and mudstone components are often substituted with those of quartz and clay, which affects model accuracy. To solve this problem, we innovate an adaptive approach for modelling the rock physics characteristics of tight sandstone. First, based on the relationship between P- and S-wave velocities from well logs and the elastic modulus of the rocks, the equivalent elastic modulus of tight sandstone under saturated conditions is calculated. Next, The Lee model and the Gassmann equation were jointly used to determine the equivalent elasticity modulus of tight sandstone matrix. The upper and lower limits of the equivalent elasticity modulus for mudstone and sandstone are established using the mudstone content curve, the least squares method and the Voigt–Reuss–Hill (V-R-H) model. We used the random-walk algorithm to accurately calculate the equivalent elastic modulus of the sandstone and mudstone components. Finally, using the accurately obtained elastic modulus of sandstone and mudstone, the equivalent elastic modulus of the matrix is calculated. The Kuster–Toksöz (K-T) model is subsequently applied to compute the dry frame bulk modulus and shear modulus of the rock. Following this, the Brie model is used to calculate the elastic modulus of the mixed fluid, thereby completing the construction of the rock physics model for the study area. The results demonstrate that our improved petrophysics model can predict the S-wave velocity curve with ≤ 15% errors relative to the true curve. When sweet spot prediction was performed using reservoir-sensitive parameter (Vp/Vs) derived from the petrophysics template, the agreement between the predictions and well-log data was 80%. Thus, our petrophysics modelling method can be used to predict tight gas reservoirs effectively and will aid efforts to improve petroleum exploration works in the study area.

Influence of reservoir water saturation on coalbed methane development: Based on multi-field coupling numerical simulation

Water in coal reservoirs serves as both the driving force of reservoir fluid and the resistance to coalbed methane (CBM) migration. However, the impact and control mechanism of water saturation on CBM development in the field have not been revealed yet. The evolution of reservoir dynamics and gas production rate under various initial water saturation conditions is simulated based on the COMSOL multiphysics numerical simulation software. The simulation results show that the reduction of initial water saturation can significantly enhance the effective permeability of the reservoir gas phase, which can be increased by up to 4764%. This increases the rate of gas production, which is the main mechanism for controlling production by water saturation in the reservoir. For high water saturation reservoirs, the positive effect of inter-well interference should be reasonably utilized, and high well network density should be used to rapidly increase gas-effective permeability. For low water saturation reservoirs, the negative effect of inter-well interference should be avoided, and low well network density should be used to increase the control of single well reserves.

Numerical simulation on multi-well fracturing considering multiple thin layers in vertical direction

Multiwell fracturing is a key technology for developing shale gas and shale oil reservoirs. In this study, a multiple planar 3D (PL3D) fracture simulator that can capture multiple thin layers was developed to examine the propagation of multiple fractures during multicluster fracturing in multiple horizontal wells. The simulator considers multiple thin layers in the vertical direction. The results of the model are validated against the analytical solution of a single radial fracture and the implicit level set algorithm (ILSA). Using the simulator, a series of numerical simulations based on the field case are performed to investigate the fracture propagation mechanism of multiwell fracturing. The completion sequence, well placement pattern, well spacing, and cluster spacing are investigated to optimize the treatment parameters. The effective fracture area is used to quantitatively describe the stimulation effect. The adaptability of the completion sequence and well placement pattern is also analysed from the perspective of “frac hits”. The results show that the completion sequence has a critical influence on the stimulation effect and fracture geometry. From the perspective of avoiding “frac-hit” fractures, fracturing the low-stress layer can form an “artificial stress barrier”, which slightly protects the well from interference from other fractures. The staggered well pattern is better than the stacked well pattern. Compared with the stacked pattern, the staggered pattern can reduce the overlap area of fractures by 80 %, which greatly reduces the probability of “frac-hits”. With increasing well spacing from 200 m to 500 m, the fracture area increases by 25 %, and the degree of uneven stimulation between the two pay zones also increases by 6 %. Considering that a small well spacing is prone to “frac hits”, a large well spacing leads to an unstimulated area between two wells, and a 350 m well spacing is optimal. The effective fracture area decreases slightly with increasing perforation cluster spacing, but the fracture geometry becomes much more regular. The results can be helpful for the field design of multiwell fracturing.

Measuring the 34S and 33S Isotopic Ratios of Volatile Sulfur during Planet Formation

Stable isotopic ratios constitute powerful tools for unraveling the thermal and irradiation history of volatiles. In particular, we can use our knowledge of the isotopic fractionation processes active during the various stages of star, disk, and planet formation to infer the origins of different volatiles with measured isotopic patterns in our own solar system. Observations of planet-forming disks with the Atacama Large Millimeter/submillimeter Array (ALMA) now readily detect the heavier isotopologues of C, O, and N, while the isotopologue abundances and isotopic fractionation mechanisms of sulfur species are less well understood. Using ALMA observations of the SO and SO2 isotopologues in the nearby, molecule-rich disk around the young star Oph-IRS 48 we present the first constraints on the combined 32S/34S and 32S/33S isotope ratios in a planet-forming disk. Given that these isotopologues likely originate in relatively warm gas (>50 K), like most other Oph-IRS 48 volatiles, SO is depleted in heavy sulfur, while SO2 is enriched compared to solar system values. However, we cannot completely rule out a cooler gas reservoir, which would put the SO sulfur ratios more in line with comets and other solar system bodies. We also constrain the S18O/SO ratio and find the limit to be consistent with solar system values given a temperature of 60 K. Together these observations show that we should not assume solar isotopic values for disk sulfur reservoirs, but additional observations are needed to determine the chemical origin of the abundant SO in this disk, inform on what isotopic fractionation mechanism(s) are at play, and aid in unraveling the history of the sulfur budget during the different stages of planet formation.

Determination and Application of Stress States Based on Finite Element Techniques: A Case Study of the Longmaxi Formation in the Luzhou Block, Sichuan Basin.

Knowledge of the present-day in situ stress field (PIS) has important theoretical and practical significance for shale gas exploration and development. The Wufeng-Longmaxi Formation in the Luzhou Block serves as the main reservoir of marine shale production in southern China. However, there is no clear understanding of PIS in the Luzhou area, which leads to a series of production problems. To investigate the PIS of deep shale reservoirs in Luzhou, experimental and finite element methods (FEMs) were used. Data obtained from imaging logging data, well deviation data, multipole array acoustic logging (XMAC), and world stress map were used to determine the orientation of the horizontal maximum principal stress (S Hmax). Additionally, acoustic emission experiments were employed to determine the magnitude of three principal stresses. Based on FEM, with the stress of a single well as a constraint, a three-dimensional (3D) stress field model was developed. The results show that the orientation of S Hmax varies from 90 to 120 °E. Further, there are significant differences in stress regimes across the region, with strike-slip/reverse faulting stress regime (S Hmax > S v ≈ S hmin) in the northern region and strike-slip stress regime in the southern region (S Hmax > S v > S hmin). In addition, geomechanical evaluations of wellbore stability and natural activation of fractures were performed. The Luzhou Block mainly develops two groups of natural fractures (NE-SW trending and NW-SE trending), with NW-SE trending being the dominant fracture development orientation. During the fracturing operation, a pore pressure increment larger than 50 MPa is conducive to maintaining a high opening ratio of the reservoir and improving the gas production efficiency. Horizontal wells drilled in the direction of maximum horizontal principal stress in the Wufeng-Longmaxi Formation reduce the probability of wellbore instability. The research results provide a reference for the effective development of deep shale gas reservoirs in southern Sichuan.

Integrated study of hydraulic/CO2 fracturing and production coupled with a THM-D process in ultra-shallow shale reservoirs

To explore fracturing technology for vertical wells in ultra-shallow shale gas reservoirs, a coupled thermo-hydro-mechanical-damage (THM-D) fracturing and production integration model is established in this study. In addition, a new coupled hydro-mechanical damage model is established to calculate fracture evolution. These two models are validated through theoretical models and field data, respectively. Based on these models, the quality of fracturing under different geological parameters, fracturing parameters, and fracturing technology is compared and analyzed. The results show that the distribution of natural fractures significantly influences fracturing and production. In addition, due to the high leak-off in the ultra-shallow shale reservoir, the total fracture length and cumulative production after 720 days of carbon dioxide fracturing are only 70.35% and 77.26% of the values achieved by hydraulic fracturing, respectively. Therefore, it is necessary to consider reducing carbon dioxide leak-off in the design of carbon dioxide fracturing in ultra-shallow shale reservoirs. Fracturing efficiency also should be considered when designing fracturing time. When the injection rate is 5 m3/min, the efficiency drops sharply if the fracturing time exceeds 67.45 min. The production of hydraulic fracturing and carbon dioxide fractured wells has also been studied when fracturing methods without proppant are used. This study found that a satisfactory production rate can also be achieved in ultra-shallow shale gas reservoirs when fracturing without proppant.

A novel high-z submm galaxy efficient line survey in ALMA Bands 3 through 8 – an ANGELS pilot

ABSTRACT We use the Atacama Large sub/Millimetre Array (ALMA) to efficiently observe spectral lines across Bands 3, 4, 5, 6, 7, and 8 at high-resolution (0.5–0.1 arcsec) for 16 bright southern Herschel sources at $1.5 \lt z \lt 4.2$. With only six and a half hours of observations, we reveal 66 spectral lines in 17 galaxies. These observations detect emission from CO (3−2) to CO(18−17), as well as atomic ([C i](1−0), (2−1), [O i] 145 $\mu$m and [N ii] 205 $\mu$m) lines. Additional molecular lines are seen in emission (${\rm H_2O}$ and ${\rm H_2O^+}$) and absorption (OH$^+$ and CH$^+$). The morphologies based on dust continuum ranges from extended sources to strong lensed galaxies with magnifications between 2 and 30. CO line transitions indicate a diverse set of excitation conditions with a fraction of the sources ($\sim 35$ per cent) showcasing dense, warm gas. The resolved gas to star formation surface densities vary strongly per source, and suggest that the observed diversity of dusty star-forming galaxies could be a combination of lensed, compact dusty starbursts and extended, potentially merging galaxies. The predicted gas depletion time-scales are consistent with 100 Myr to 1 Gyr, but require efficient fuelling from the extended gas reservoirs onto the more central starbursts, in line with the Doppler-shifted absorption lines that indicate inflowing gas for two out of six sources. This pilot paper explores a successful new method of observing spectral lines in large samples of galaxies, supports future studies of larger samples, and finds that the efficiency of this new observational method will be further improved with the planned ALMA Wideband Sensitivity Upgrade.

Amalgamating LMR, EEI and AVO Analysis to Monitor the Characteristics of Pliocene Gas Reservoir: A Case Study Offshore, East Nile Delta, Egypt

Amalgamating LMR, EEI and AVO Analysis to Monitor the Characteristics of Pliocene Gas Reservoir: A Case Study Offshore, East Nile Delta, Egypt

Analysis of the impact of geological and engineering parameters on productivity in tight oil reservoirs

AbstractTight oil resources are abundant, but the factors affecting production capacity are complex. In this paper, focusing on tight oil reservoirs, three research works were conducted. First, using the numerical simulation software, a numerical model of tight oil reservoirs was established. Second, the influence of geological parameters such as porosity and permeability on oil production were analyzed. Third, the influence of rock compression coefficient and injection fluid on tight oil production were analyzed. Results show that: (a) When the porosity is 0.05, the cumulative oil production in the first 6 years is the highest, while in the later stage of the simulation, the cumulative oil production with a porosity of 0.1 is the highest. (b) The higher the permeability, the greater the cumulative oil production. The cumulative oil production under different permeability conditions are 1392.044, 2178.805, 2939.1704, and 4038.0878 m3, respectively. (c) Under tight reservoir conditions, the impact of different rock compression coefficients on the daily oil production of oil and gas reservoirs is not very significant. (d) The recovery effect is optimal when using the N2 injection scheme. The effectiveness of the CH4 scheme is second, and there is a certain gap compared to the N2 scheme. The development plan of injecting water has the worst effect. However, compared to the depletion development model, the cumulative oil production by injecting N2, CO2, CH4, and water has all increased.

Electric Field Control of CO2 Distribution in Kerogen Slit of Depleted Shale Gas Reservoirs: Implications for CO2 Sequestration

Electric Field Control of CO₂ Distribution in Kerogen Slit of Depleted Shale Gas Reservoirs: Implications for CO₂ Sequestration

Modeling the effect of dispersion and attenuation for frequency-dependent amplitude variation with offset

As research in oil and gas exploration progresses, unconventional resources, such as shale gas, are increasingly becoming the focal point in the global pursuit of oil and gas resource. Shale gas reservoirs significantly differ from conventional sandstone reservoirs in aspects such as rock composition, pore type, occurrence mode, fluid, etc., thereby amplifying the challenges associated with geophysical modeling and the prediction of sweet spots. Since the formation and storage of shale gas are positively correlated with shale fracturing, a modeling approach based on Chapman theory is introduced to complete frequency-dependent petrophysical modeling. Additionally, the Frequency-dependent Amplitude Variation with Offset (FAVO) technique can estimate velocity dispersion by using the reflection coefficient information related to incidence angle and frequency. This method can more effectively identify fluids within shale reservoir. However, current FAVO forward modeling only considers the velocity dispersion and attenuation at the interface, neglecting the attenuation dispersion effects during interlayer propagation. To this end, we utilize Chapman-based petrophysical modeling as a foundation and conduct seismic forward modeling studies employing the compound matrix method. Through experimental analysis, we meticulously examine the attenuation dispersion effects at interfaces and within layers. Finally, we conduct FAVO simulations that vividly delineate the interplay between reservoir parameters and seismic responses.

Numerical simulation of shale gas reservoir based on ILU-GMRES method

ABSTRACT The numerical simulation of shale gas reservoirs requires transforming mathematical models into large linear equation systems, and solving large linear equation systems requires a lot of time. A novel ILU-GMRES method for solving large linear equations is presented, which treats the sub matrix discretized at nodes as the basic elements of the coefficient matrix. By combining the incomplete LU decomposition method (ILU) with the generalized minimum residue method (GMRES), the discretized large linear equations are iteratively solved. A comparison was made between the new method and other methods for calculating the actual shale gas reservoir model. The results reveal that the new method has a faster calculation speed in solving linear equation systems. The calculation time of the novel ILU-GMRES method is 1029s, the calculation time of the generalized minimum residual method (GMRES) method is 2709s, the calculation time of the Gauss–Seidel method (GS) is 3786s, and the calculation time of the successive over relaxation method (SOR) method is 3386s, the calculation time of the preprocessing conjugate gradient method (PCG) is 3115s. The calculation speed of the novel method is almost 2.6 times faster than the GMRES method, the novel method is more effective in the numerical simulation of shale gas.

Study on the Impact of Porous Media on Condensate Gas Depletion: A Case Study of Reservoir in Xihu Sag.

During the depletion and pressure reduction process in condensate gas reservoirs, the precipitation of condensate oil transforms the single-phase gas flow into a two-phase gas-liquid flow, significantly reducing the permeability. Currently, microscopic studies of the phase behavior of condensate gas in porous media mainly focus on observing and describing the occurrence of condensate oil, lacking quantitative calculations and direct observations of condensate oil throughout the entire depletion cycle. This paper uses a microvisualization method to simulate the depletion process of condensate gas reservoirs. Condensate gases with oil contents of 175.3 and 505.5 g/cm3 were prepared by mixing methane, ethane, hexane, and decane in specific proportions. Pore structures were extracted from thin sections of real core casts, and microfluidic chips with a minimum pore diameter of 20 μm and an areal porosity of 20.75% were fabricated by using a chemical wet etching method. Subsequently, microfluidic condensate gas depletion experiments were conducted with chip images recorded during the depletion process. Grayscale analysis of the depletion images was performed using ImageJ software to quantitatively calculate condensate oil saturation and recovery rates, analyzing the effects of different condensate oil contents on condensate gas depletion, and comparing the differences between depletion in porous media and in a PVT cell. The conclusions drawn are as follows: the dew points of high and low in the porous media are 3.15% and 1.85% higher than those in the PVT cell, respectively. In the early stages of depletion, condensate oil saturation in porous media is higher than that in the PVT cell, while in the middle to late stages, condensate oil saturation in porous media is lower than that in the PVT cell. The condensate oil recovery rate in porous media is significantly higher than the depletion recovery rate in the PVT cell. Condensate oil tends to precipitate and disperse at blind ends and corners, while it easily forms patches in mainstream large pores.

Improved Fracture Permeability Evaluation Model for Granite Reservoirs in Marine Environments: A Case Study from the South China Sea

Permeability is a crucial parameter in the exploration and development of oil and gas reservoirs, particularly in unconventional ones, where fractures significantly influence storage capacity and fluid flow. This study investigates the fracture permeability of granite reservoirs in the South China Sea, introducing an enhanced evaluation model for planar fracture permeability based on Darcy’s law and Poiseuille’s law. The model incorporates factors such as fracture heterogeneity, tortuosity, angle, and aperture to improve permeability assessments. Building on a single-fracture model, this research integrates mass transfer equations and trigonometric functions to assess intersecting fractures’ permeability. Numerical simulations explore how tortuosity, angle, and aperture affect individual fracture permeability and the influence of relative positioning in intersecting fractures. The model makes key assumptions, including minimal consideration of horizontal stress and the assumption of unidirectional laminar flow in cross-fractures. Granite outcrop samples were systematically collected, followed by full-diameter core drilling. A range of planar models with varying fracture apertures were designed, and permeability measurements were conducted using the AU-TOSCAN-II multifunctional core scanner with a steady-state gas injection method. The results showed consistency between the improved model and experimental findings regarding the effects of fracture aperture and angle on permeability, confirming the model’s accuracy in reflecting the fractures’ influence on reservoir flow capacity. For intersecting fractures, a comparative analysis of core X-ray computed tomography (X-CT) scanning results and experimental outcomes highlighted discrepancies between actual permeability measurements and theoretical simulations based on tortuosity and aperture variations. Limitations exist, particularly for cross-fractures, where quantifying complexity is challenging, leading to potential discrepancies between simulation and experimental results. Further comparisons between core experiments and logging responses are necessary for model refinement. In response to the challenges associated with evaluating absolute permeability in fractured reservoirs, this study presents a novel theoretical assessment model that considers both single and intersecting fractures. The model’s validity is demonstrated through actual core experiments, confirming the effectiveness of the single-fracture model while highlighting the need for further refinement of the dual-fracture model. The findings provide scientific support for the exploration and development of granite reservoirs in the South China Sea and establish a foundation for permeability predictions in other complex fractured reservoir systems, thereby advancing the field of fracture permeability assessment.

Perforation design coupled with heterogeneity during underground hydrogen storage in steeply dipping anticline aquifers

Hydrogen has been recognized as a crucial energy carrier to reduce greenhouse gas emissions. However, as it is not always possible to meet current energy demands, underground hydrogen storage (UHS) is required for energy supply and consumption. UHS is an emerging field of study with limited investigations regarding structural conditions and wellbore perforation design in steeply dipping anticline aquifers. This study investigates different perforation schemes with respect to UHS within steeply dipping anticline aquifers to find the most suitable injection/production design while examining small-scale reservoir heterogeneities. Several UHS improvement techniques are evaluated, including water and CO2 injection through flank wells during hydrogen production. The results indicate that the highest hydrogen production is achieved with a fully perforated H2 well located at the crest as it provides the maximum contact between the hydrogen and aquifer layers during H2 injection/production. In contrast, hydrogen production is diminished with increased heterogeneity, as higher heterogeneities raise the chance of H2 being trapped. To enhance UHS performance, first H2 initialization before UHS beginning was evaluated but the results showed that it does not enhance UHS performance in a steeply dipped anticline aquifers, as effectively as it does in gas reservoirs. Water injection from flank wells during H2 production cycles showed improvement in hydrogen withdrawal, while water production experienced a slight increase. CO2 injection from flank wells was evaluated to effectively increase H2 recovery as a cushion gas and to maintain hydrogen purity during production. According to results, hydrogen purity was not affected only in high heterogeneity, since more hydrogen gets trapped in the small-scale high heterogeneity level, which prevents the mixing zone from reaching the H2 well during production. While the method prevents hydrogen contamination in anticline aquifers due to the high dip angle coupled with high heterogeneity levels, it leads to a lower hydrogen recovery.

Using Refined Formation Water as Chemical Fertilizers: Implication of Oil and Gas Reservoir Wastewater Recycling for Agricultural Purposes

Using Refined Formation Water as Chemical Fertilizers: Implication of Oil and Gas Reservoir Wastewater Recycling for Agricultural Purposes

Analysis of the Impact of Clusters on Productivity of Multi-Fracturing Horizontal Well in Shale Gas

Shale gas reservoirs with nanoporous media have become one of the primary resources for natural gas development. The nanopore diameters of shale reservoirs range from 5 to 200 nm, with permeability ranging from 1 × 10−9 to 1 × 10−6 μm2. The natural gas production from shale gas reservoirs is low, necessitating the use of multi-stage hydraulic fracturing in horizontal wells. Segmented multi-cluster perforation fracturing is an effective method for shale gas extraction in these wells. The number of clusters significantly impacts the productivity of horizontal wells. Therefore, it is essential to analyze the impact of cluster numbers on fracture productivity in shale gas reservoir development. In this study, the equivalent flow resistance method was applied to establish a productivity model for multi-stage hydraulic fracturing horizontal wells in shale gas reservoirs considering diffusion and slip. An approximate analytical solution was obtained, and the effects of cluster length, diffusion coefficient, and fracture network permeability on productivity were analyzed. The results show that gas production gradually increases with the increase in the number of clusters and cluster length. However, as the number of clusters increases, the interference between clusters leads to a decrease in the productivity of individual clusters. As the fracture permeability, fracture network permeability, and diffusion coefficient increase, shale gas production also gradually increases. The permeability of the fracture network has the greatest impact on productivity. These research results are beneficial for the design of clusters in horizontal well fracturing and are of great importance for the development and production of shale gas reservoirs.

A bio‐reactive transport model for biomethanation in hydrogen underground storage sites

AbstractUnderground biomethanation, which relies on the subsurface microbial activity to convert hydrogen and carbon dioxide into methane, is a promising approach to support carbon capture, utilization, and storage technology. The process involves injecting hydrogen with captured CO2 into depleted oil and gas reservoirs or aquifers colonized by hydrogenotrophic methanogens that can convert these two substrates into methane. Despite the attractiveness of this technology, there are still uncertainties about the efficiency of the conversion process, particularly the impact of microbial parameters. To investigate the efficiency of the hydrogen conversion process, we relied on a bio‐reactive transport model that can mimic microbial growth and decay, consumption of substrates, and transport of reactants and products. It was found that the methane concentration peaks near the injection well when the hydrogen fraction is in the range of 75% to 80% of the injected gas composition. In addition, a noticeable hydrogen sulfide concentration can be produced due to sulfide ions in the brine. Using the Kozeny‐Carman relation, an attempt was made to correlate microbial growth with reduced porosity and permeability. It was then revealed that substrate consumption by microbes leads to a drastic increase in the microbial population in the subsurface, which can reduce the petrophysical properties of the reservoir, especially in the near wellbore area. The results obtained from a series of parametric analyses showed that the hydrogen concentration in the injected gas, pressure, well spacing, and injection rate are some of the most important parameters contributing to the biomethanation process. © 2024 Society of Chemical Industry and John Wiley & Sons, Ltd.

Improving the classification of rock samples with diffusion probabilistic machine learning

Machine learning is a powerful data-driven technology for regression and classification tasks in numerous branches of science and technology. With probabilistic machine learning, we can approximate the probability density function of a given digital data set, unlocking the sampling of new and realistic data. We implement probabilistic machine learning as a statistical-based data augmentation tool to effectively improve the performance of a classifier on scarce data sets. Limited data are the norm in most practical situations, as is the case with core samples retrieved from unconventional oil and gas reservoirs. Obtaining and properly labeling rock sample images is a manual and time-consuming task. This leads to scarce data sets that make the lithologic classification of rock samples challenging. We illustrate the technology on images taken from well cores from the Argentinean Neuquén and Austral basins, where by introducing generated samples in the training stage of a machine-learning classifier, we achieve a 5% higher accuracy with respect to the baseline obtained using the same number of samples from the original data set. We reach these results by proposing a lightweight workflow that can be run on very limited hardware. Our workflow is an alternative to classical data augmentation strategies for dealing with incomplete information, such as geometric transformations.