Permeability Prediction Model Research Articles

PREDICTION OF PERMEABILITY OF OIL AND GAS LAYERS USING ARTIFICIAL NEURAL NETWORKS

This article focuses on predicting the permeability of oil and gas reservoirs using artificial neural networks (ANN). By utilizing data sets from oil and gas wells, comprehensive preprocessing was conducted, including feature selection, scaling, and normalization to ensure the robustness of the models. The effectiveness of ANN in predicting the permeability of underground formations was evaluated using petrophysical data from wells in the Bukhara-Khiva oil and gas region. A precise permeability prediction model was created using key petrophysical parameters such as gamma rays (GR), resistivity (RT), sonic (DT), density (RHOB), and neutron porosity (NPHI). To enhance model performance, the dataset underwent complete preprocessing, including normalization and feature selection. The model's performance was assessed through MSE, R², and MAE metrics, demonstrating higher accuracy compared to traditional linear regression models. The results indicate that the ANN model provides highly accurate permeability predictions. The findings offer valuable insights for optimizing exploration and production strategies in the oil and gas industry, highlighting the superiority of machine learning and neural network models over traditional methods in subsurface resource evaluation.

Pore-throat structure, fractal characteristics and permeability prediction of tight sandstone: the Yanchang Formation, Southeast Ordos Basin

As a typical tight reservoir and an important site for unconventional hydrocarbon accumulation, the Chang 6 member of the Yanchang Formation is characterized by complex pore structures and strong heterogeneity. Analysing and characterizing the pore-throat structure is highly important for optimizing oil recovery processes. To clarify the nonhomogeneity and structural characteristics of the pore throats in the southeastern Ordos Basin, tight sandstone from the Chang 6 member was selected for analysis. Casting thin section (CTS), scanning electron microscopy (SEM), cathodoluminescence (CL), X-ray diffraction (XRD), and mercury intrusion capillary pressure (MICP) analyses were conducted. The results, revealed that intergranular pores, feldspar-dissolved pores, intergranular-dissolved pores, and microfractures were the predominant pore types found within the samples. By combining the results of MICP analysis with those of fractal theory, the pore–throat structure of each sample can be categorized into two types: large-scale and small-scale. Fractal theory was employed to characterize the complex and irregular pore–throat structure of the reservoir quantitatively. The average fractal dimension of large pores (D1) was 2.8094, whereas for small pores (D2), it was slightly lower than that of large pores, averaging 2.5325. These findings underscore that large-scale pore-throat structures are more complex and exhibit greater heterogeneity. Compared with those of large pores, the pore–throat structure parameters of small pores exhibit a more significant correlation with reservoir properties and fractal dimensions. Therefore, small pores are the primary contributors to the reservoir storage space and are key factors influencing the pore-throat structure of the Chang 6 tight sandstone. Based on the pore-throat radius and considering the influence of fractal characteristics on the pore structure, a nonlinear permeability prediction model was created using multiple regression analysis. Among these equations, the pore–throat radius corresponding to a mercury saturation of 40% (r40) emerged as the most effective predictor of permeability for tight sandstone. The investigation of micropore–throat structures in tight oil reservoirs holds practical significance for comprehending the distribution and accumulation of tight oil and guiding oil field development.

Developing a novel permeability prediction method for tight carbonate reservoirs using borehole electrical image logging

Predicting permeability accurately is crucial for effective hydrocarbon extraction, but the intricate pore structures of tight carbonates resulting from sedimentation, diagenesis, and tectonic activity present significant challenges. Based on borehole electrical image logging and fractal theory, we develop a method to calculate the fractal dimension of the porosity spectrum to characterize the complexity of the pore structure of the reservoir. Fractal features of the porosity spectra are studied, and fractal parameters are calculated, such as the left ([Formula: see text]), middle ([Formula: see text]), and right fractal dimensions ([Formula: see text]). A permeability prediction model is developed based on fractal parameters by investigating the linear relationship between fractal parameters and core permeability. The results indicate that [Formula: see text] and permeability have a coefficient of determination ([Formula: see text]) of 0.78, whereas [Formula: see text] between porosity and permeability is only 0.03. The [Formula: see text] and [Formula: see text] have little correlation with core permeability. The prediction results of the [Formula: see text]-based permeability model are in good agreement with the experimental data with Pearson product-moment correlation coefficient of 0.93 in the field applications. Our findings suggest that large pores primarily contribute to the permeability of tight carbonates because [Formula: see text] corresponds to the macroporous part of the porosity spectrum. This study enhances our understanding of the factors that influence permeability and provides a useful tool for predicting permeability in tight carbonate reservoirs.

Estimation of rock mass permeability using relaxation time and P‐wave velocity

AbstractDue to the inherent unpredictability of geological conditions, tunnelling operations are often at risk of encountering water inrushes. Such incidents can lead to construction delays, impose financial strains and pose significant safety threats to the workers involved. Water‐bearing geological formations are the main triggers for such incidents, with factors such as the positioning, water quantity and permeability distribution of these formations being key to predicting the occurrence and severity of water inrush disasters. By leveraging the complex interplay among relaxation time, P‐wave velocity and permeability within the rock's physical properties, a series of indoor tests were conducted on 40 artificial reef limestone cores to extract the necessary parameters. Through the analysis of the data, the comprehensive permeability prediction model was established, and the correlation coefficient was 0.9420 between the model's predictions and actual measurements. At the same time, through theoretical and mechanism analysis, the relationship between permeability and relaxation time and the relationship between permeability and P‐wave velocity were analysed. Finally, 10 natural reef limestone samples were used to verify the accuracy of the model. The prediction model enables an accurate evaluation of tunnel permeability, thus providing a scientific basis for the mitigation of tunnel water inrush hazards.

Permeability Characteristics of Improved Loess and Prediction Method for Permeability Coefficient

Due to its unique geotechnical properties, loess presents itself as a cost-effective and energy-efficient material for engineering construction, aiding in cost reduction and environmental sustainability. However, to meet engineering specifications, loess often requires enhancement. Evaluating its permeability properties holds significant importance for employing improved loess for construction materials in landfills and artificial water bodies. This study investigates the influence of dry densities, grain size characteristics, grain size distribution, and admixture contents and types on the permeability of improved loess, focusing on the Malan and Lishi loess. The falling head permeability test was conducted to analyze how each factor affects the permeability of the improved loess. The findings indicate that the permeability coefficient decreases with increased dry density and admixture content. Conversely, it demonstrates a linear increase with the average grain size (d50), restricted grain size (d60), and the product of the coefficient of uniformity and coefficient of curvature (Cu × Cc). The primary influencing factor is the type of admixture, followed by Cc and d60. Furthermore, this study developed a predictive model for permeability using a support vector machine (SVM), surpassing the predictive accuracy of linear regression and neural network models. The model provides a robust prediction for the permeability of superior loess material.

A Morphological Method for Predicting Permeability in Fractured Tight Sandstone Reservoirs Based on Electrical Imaging Logging Porosity Spectrum

Summary Permeability is a crucial parameter in formation evaluation, which reflects reservoir fluid mobility and directly influences subsequent development and production. In conventional to tight sandstone formations without fractures, numerous methods have been developed to predict permeability. However, permeability prediction accuracy based on the current method is low in fractured tight sandstone reservoirs due to the influence of heterogeneity, and little research is focused on permeability evaluation in such reservoirs. Conventional wireline and nuclear magnetic resonance (NMR) logging lose their role in fracture parameter evaluation, whereas electrical imaging logging is available for reflecting fracture information. Hence, we adopt electrical imaging logging, instead of conventional wireline and NMR logging, to predict permeability in fractured tight sandstone reservoirs. In this study, we propose a morphological method for permeability prediction using electrical imaging logging. Initially, we process the electrical imaging logging data to obtain the porosity spectra and determine the peak of the primary porosity spectrum. We then extract the mean and standard deviation of the primary porosity spectrum based on its distribution morphology. Meanwhile, we also use the normal distribution function to fit the primary porosity spectrum and accumulate the amplitudes of the original and fitted porosity spectra, respectively. When the cumulative amplitude of the fitted spectra stabilizes, the corresponding porosity indicates the boundary between primary and secondary pores. This boundary allows us to calculate the proportion of primary pores to total pores. Permeability in fractured tight sandstone formations is influenced by both primary and secondary pores, showing a strong correlation with the proportion of primary porosity. Finally, we establish a permeability prediction model based on total porosity and the proportion of matrix pores. The reliability of our established permeability evaluation model is confirmed by comparing the predicted permeabilities with core-derived results in the Triassic Chang 63 Member of the Jiyuan area in the Ordos Basin. In unfractured formations, the predicted permeability based on our raised model closely matches the results derived solely from total porosity. In fractured formations, however, the calculated permeability using our proposed model aligns more closely with the core-derived result, while predictions based on current and NMR models tend to underestimate permeability.

Study on the Mechanical Parameters and Permeability of Coal Reservoirs at Different Temperatures.

Deep coal reservoirs, as opposed to their shallower counterparts, exhibit characteristics of higher temperatures and pressures. These conditions affect the fracture structure and mechanical properties of coal, which in turn controls permeability. Substantial studies have been conducted to determine the effects of overburden pressure on permeability, but the correlation between the temperature and mechanical parameters/permeability of coal remains unclear. This study focused on low-rank bituminous coal from the southern edge of the Junggar Basin in Xinjiang. Using experiments conducted on seepage and mechanics at different depths (considering effective stress and temperature), the study investigated how temperature affects the mechanical parameters and permeability of coal column samples. A permeability prediction model was established incorporating temperature, mechanical parameters, and effective stress. The results show that from 20 to 80 °C, the elastic modulus of coal column samples decreases by 31.0%, and the Poisson ratio increases by 72.0%. Permeability decreases between 48.37 and 90.12% under different depths. The stress sensitivity coefficient under various temperature conditions decreased exponentially as the effective stress increased, and the temperature sensitivity coefficient under various effective stress conditions decreased with increasing temperature. The permeability was more sensitive to a temperature below 40 °C. In the permeability prediction model, the fracture compressibility coefficient is bifurcated into two coefficients, each controlled by temperature and effective stress. The permeability prediction error of the model was 12.7% under constant effective stress and 17.2% under varying effective stress and temperature conditions. The study could provide guidance for fracturing and coalbed methane production in deep coal reservoirs.

Knowledge Extraction via Machine Learning Guides a Topology‐Based Permeability Prediction Model

AbstractThe complexity and heterogeneity of pore structure present significant challenges in accurate permeability estimation. Commonly used empirical formulas neglect its microscopic and topological characteristics, thus lacking accuracy and adaptability. While machine learning (ML) and deep learning (DL) models demonstrate promising performance, but encounter challenges of data availability, computational cost, and model interpretability. The present study aims to develop a more robust and accurate permeability prediction model via knowledge extraction from ML model. We first establish an ML model between permeability and the geometry‐topology characteristics of porous media using Extreme Gradient Boosting (XGBoost) algorithm. The data set used to fit ML model is prepared from 458 samples of different types of porous media. Using the SHapley Additive exPlanations (SHAP) value, the influence of each feature on permeability prediction is quantified. It is found that the closeness centrality (topology feature), tortuosity, porosity (macroscopic features) and throat diameter, throat length, pore diameter (pore network features) are vital for permeability prediction. Guided by partial dependence calculation, the unknown function relationship between permeability and the top six important features is established. The novel permeability prediction model incorporating topology feature improves the prediction accuracy and demonstrates strong applicability across diverse data sets. This new model presents an optimal balance between simplicity and performance, rendering it a compelling alternative for permeability prediction in porous media. The research provides a novel referable framework of knowledge extraction via ML to reveal the important features and establish the potential relationship that can be extended and applied in other research fields.

An improved convolutional neural network for predicting porous media permeability from rock thin sections

Permeability prediction is a crucial aspect of investigating fluid flow capacity in porous media, and rapidly predicting the permeability of rock thin sections aids in reservoir assessment. In recent years, significant progress has been made regarding the use of deep learning for predicting porous media permeability, effectively overcoming the limitations associated with time-consuming conventional permeability determination methods. To address the issues of low prediction accuracy and insufficient generalization capability of previous permeability prediction models, this study proposes an improved convolutional neural network for porous media permeability and applies it to predict the permeability of rock thin sections. Given the difficulty of obtaining a large amount of rock thin section data, we synthetically generated 1000 binary images of porous media and calculated the corresponding permeability labels using computational fluid dynamics. These data were used as foundational data for training the model. The proposed model achieved accurate and efficient permeability prediction of porous media with a correlation of 0.9667 on testing set. Simultaneously, we employed class activation mapping technology to visualize the permeability prediction process of the neural network, thereby elucidating the working principles of the neural network during porous media permeability prediction. Subsequently, based on an optimally pretrained neural network, transfer learning was utilized to predict the permeability of rock thin sections, which achieved a correlation of 0.9032. Our study extends the rock thin section applications and provides technical support for reservoir evaluation.

Optimization and Application of XGBoost Logging Prediction Model for Porosity and Permeability Based on K-means Method

The prediction and distribution of reservoir porosity and permeability are of paramount importance for the exploration and development of regional oil and gas resources. In order to optimize the prediction methods of porosity and permeability and better guide gas field development, it is necessary to identify the most effective approaches. Therefore, based on the extreme gradient boosting (XGBoost) algorithm, laboratory test data of the porosity and permeability of cores from the southern margin of the Ordos Basin were selected as the target labels, conventional logging curves were used as the input feature variables, and the mean absolute error (MAE) and the coefficient of determination (R2) were used as the evaluation indicators. Following the selection of the optimal feature variables and optimization of the hyper-parameters, an XGBoost porosity and permeability prediction model was established. Subsequently, the innovative application of homogeneous clustering (K-means) data preprocessing was applied to enhance the XGBoost model’s performance. The results show that logarithmically preprocessed (LOG(PERM)) target labels enhanced the performance of the XGBoost permeability prediction model, with an increase of 0.26 in its test set R2. Furthermore, the application of K-means improved the performance of the XGBoost prediction model, with an increase of 0.15 in the R2 of the model and a decrease of 0.017 in the MAE. Finally, the POR_0/POR_1 grouped porosity model was selected as the final predictive model for porosity in the study area, and the Arctan(PERM)_0/Arctan(PER0M)_1 grouped model was selected as the final predictive model for permeability, which has better prediction accuracy than logging curves. The combination of K-means and the XGBoost modeling method provides a new approach and reference for the efficient and relatively accurate evaluation of porosity and permeability in the study area.

Prediction Model of Coal Gas Permeability Based on Improved DBO Optimized BP Neural Network.

Accurate measurement of coal gas permeability helps prevent coal gas safety accidents effectively. To predict permeability more accurately, we propose the IDBO-BPNN coal body gas permeability prediction model. This model combines the Improved Dung Beetle algorithm (IDBO) with the BP neural network (BPNN). First, the Sine chaotic mapping, Osprey optimization algorithm, and adaptive T-distribution dynamic selection strategy are integrated to enhance the DBO algorithm and improve its global search capability. Then, IDBO is utilized to optimize the weights and thresholds in BPNN to enhance its prediction accuracy and mitigate the risk of overfitting to some extent. Secondly, based on the influencing factors of gas permeability, effective stress, gas pressure, temperature, and compressive strength, they are chosen as the coupling indicators. The SPSS 27 software is used to analyze the correlation among the indicators using the Pearson correlation coefficient matrix. Additionally, the Kernel Principal Component Analysis (KPCA) is employed to extract the original data. Then, the original data is divided into principal component data for the model input. The prediction results of the IDBO-BPNN model are compared with those of the PSO-BPNN, PSO-LSSVM, PSO-SVM, MPA-BPNN, WOA-SVM, BES-SVM, and DPO-BPNN models. This comparison assesses the capability of KPCA to enhance the accuracy of model predictions and the performance of the IDBO-BPNN model. Finally, the IDBO-BPNN model is tested using data from a coal mine in Shanxi. The results indicate that the predicted outcome closely aligns with the actual value, confirming the reliability and stability of the model. Therefore, the IDBO-BPNN model is better suited for predicting coal gas permeability in academic research writing.

Description of Pore Structure of Carbonate Reservoirs Based on Fractal Dimension

The complexity and heterogeneity of pore structures in carbonate reservoirs pose significant challenges for accurately characterizing the influence of different pore micro-parameters on reservoir physical properties. Drawing upon the principles of fractal geometry theory applied to reservoir rocks, this study combines mercury intrusion porosimetry (MIP) and nuclear magnetic resonance (NMR) T2 spectrum methods to explore the relationship between the fractal dimension and micro-parameters of pore throats at various scales. Additionally, it clarifies how the fractal dimension of pores at different scales impacts reservoir physical properties. Moreover, a permeability prediction model that incorporates fractal dimensions is developed. The findings demonstrate that the fractal dimension effectively captures the complexity and multi-scale nature of reservoir microstructures, leading to higher reliability in predicting permeability when using the model incorporating the fractal dimension. It provides a theoretical basis for predicting the absolute permeability of fractured carbonate rocks in dual media.

Prediction of transverse permeability in representative volume elements with closely arranged fibers through the application of delaunay-triangulation and electrical-circuit analogy

The distribution of fibers in composite manufacturing significantly affects fiber bundle permeability, a crucial factor for resin impregnation and void formation, which determines final product quality. However, as the industry increasingly seeks composite materials characterized by high fiber volume fractions, the existing numerical analysis methodologies employed for predicting permeability require a considerable computational cost. In this study, the permeability prediction model was developed using a fluid domain simplification technique based on Delaunay triangulation. The inter-fiber flow was approximated using a lubrication model, and continuity was ensured using a circuit analogy. This model can explain stochastic permeability characteristics according to fiber distribution and accurately predicts the permeability regardless of the distance between fibers. Additionally, compared to existing computational fluid dynamics simulations, it achieved an incredible accuracy of 97.74% and reduced computational costs by an average of 1,700 times.

Prediction of permeability in a tight sandstone reservoir using a gated network stacking model driven by data and physical models

Introduction: Permeability is one of the most important parameters for reservoir evaluation. It is commonly measured in laboratories using underground core samples. However, it cannot describe the entire reservoir because of the limited number of cores. Therefore, petrophysicists use well logs to establish empirical equations to estimate permeability. This method has been widely used in conventional sandstone reservoirs, but it is not applicable to tight sandstone reservoirs with low porosity, extremely low permeability, and complex pore structures.Methods: Machine learning models can identify potential relationships between input features and sample labels, making them a good choice for establishing permeability prediction models. A stacking model is an ensemble learning method that aims to train a meta-learner to learn an optimal combination of expert models. However, the meta-learner does not evaluate or control the experts, making it difficult to interpret the contribution of each model. In this study, we design a gate network stacking (GNS) model, which is an algorithm that combines data and model-driven methods. First, an input log combination is selected for each expert model to ensure the best performance of the expert model and selfoptimization of the hyperparameters. Petrophysical constraints are then added to the inputs of the expert model and meta-learner, and weights are dynamically assigned to the output of the expert model. Finally, the overall performance of the model is evaluated iteratively to enhance its interpretability and robustness.Results and discussion: The GNS model is then used to predict the permeability of a tight sandstone reservoir in the Jurassic Ahe Formation in the Tarim Basin. The case study shows that the permeability predicted by the GNS model is more accurate than that of other ensemble models. This study provides a new approach for predicting the parameters of tight sandstone reservoirs.

A New Model for Predicting Permeability of Chang 7 Tight Sandstone Based on Fractal Characteristics from High-Pressure Mercury Injection

Accurately predicting permeability is important to elucidate the fluid mobility and development potential of tight reservoirs. However, for tight sandstones with the same porosity, permeability can change by nearly three orders of magnitude, which greatly increases the difficulty of permeability prediction. In this paper, we performed casting thin section, scanning electron microscopy and high-pressure mercury injection experiments to analyze the influence of pore structure parameters and fractal dimensions on the permeability of Chang 7 tight sandstones. Furthermore, the key parameters affecting the permeability were optimized, and a new permeability prediction model was established. The results show that the pore throat structure of Chang 7 tight sandstone exhibits three-stage fractal characteristics. Thus, the pore throat structure was divided into large pore throat, medium pore throat and small pore throat. The large pore throat reflects the microfracture system, whose fractal dimension was distributed above 2.99, indicating that the heterogeneity of the large pore throat was the strongest. The medium pore throat is dominated by the conventional pore throat system, and its fractal dimension ranged from 2.378 to 2.997. Small pore throats are mainly composed of the tree-shaped pore throat system, and its fractal dimension varied from 2.652 to 2.870. The medium pore throat volume and its fractal dimension were key factors affecting the permeability of Chang 7 tight sandstones. A new permeability prediction model was established based on the medium pore throat volume and its fractal dimension. Compared to other models, the prediction results of the new model are the best according to the analysis of root mean square value, average absolute percentage error and correlation coefficient. These results indicate that the permeability of tight sandstones can be accurately predicted using mesopore throat volume and fractal dimension.

A new nuclear magnetic resonance-based permeability model based on two pore structure characterization methods for complex pore structure rocks: Permeability assessment in Nanpu Sag, China

The nuclear magnetic resonance (NMR) estimate of permeability is a fundamental method that has numerous applications in reservoir engineering and petrophysics. To improve the accuracy of the NMR-based permeability model, many variables are introduced into NMR-based permeability prediction models due to geometric complexity and pore structure heterogeneity. In this paper, two pore structure characterization methods are investigated based on the Kozeny-Carman model and equivalent component model. Furthermore, an NMR-based permeability model accounting for the effect of pore structure is developed based on the analysis of the relationship between two pore structure parameters, and it is applied to practically predict permeability. Results indicate that the new model-calculated permeability has good agreement with experimental data; moreover, the adaptability of the new NMR-based permeability prediction model is highly improved through reducing undetermined variables, and key parameters can be measured directly using NMR. The new model provides a valuable scientific resource and assists in the evaluation of hydrocarbon-bearing reservoirs with complex pore structure, such as tight sandstone, shale, and carbonate rock.

Improved predictions of permeability properties in cement-based materials: A comparative study of pore size distribution-based models

Permeability is a fundamental physical property of a cement-based material and is closely related to its pore structure. This study developed an improved model for permeability prediction of cementitious materials with a function of the pore size distribution (PSD), in which PSD is simulated from single and compound lognormal distribution functions, respectively. The efficiency of the improved model is demonstrated by calculating permeability for mortars and pastes available in the literature. It is found that, first, for cementitious materials with unimodal PSD, the single lognormal distribution function is adequate to describe the pore structures. In contrast, for cementing mixtures presenting multimodal PSD, the compounded lognormal distribution function is highly recommended to cover a wide range of pore components. Second, the permeability model based on the compound PSD can predict well permeability to gas intrusion, whereas the single PSD-based model is applicable for calculating permeability via water intrusion. Furthermore, slippage effect and water saturation degree are introduced in the PSD-based model. Results prove that the corrected gas permeability model from the compound PSD performs well in estimating the gas permeability in unsaturated states. Finally, the compound PSD-based model is extended by considering varying porosities and relative humidities, which can be used to quantitively describe permeability when cementitious materials undergoing pore structure degradation induced by durability issues.

A pore network-based multiscale coupled model for rapid permeability prediction of tight sandstone gas

Tight sandstone has multiscale pore structures. Gas transport in tight sandstones involves several length scales and the complicated physics. Gas transport characteristics in tight sandstone can be represented by apparent gas permeability. Microstructure-based accurate and efficient calculation of gas permeability is challenging. By combining CT and SEM images along with statistical analysis, we present a novel pore network-based multiscale coupled model (MCPNM) to rapidly predict the apparent gas permeability. CT images are adopted to extract the large-scale pore network (LPNM) and the clay component, and SEM image is used to get the properties of small-scale pores. Upscaled model (UM) of small-scale pores is built via statistical analysis and then assigned to the clay domains. The LPNM and UM are coupled as MCPNM by the cross-scale connection structure with variable diameter. The pore spaces at several length scales and the flow characteristics in them are included in the MCPNM. We validate the MCPNM by comparing the calculated apparent gas permeability to the results of available multiscale pore network models and the experimental data. Compared with the available multiscale pore network models, MCPNM solves the accuracy/efficiency trade-off of tight gas permeability prediction. The effects of pressure, temperature, and gas type on gas permeability are studied. The MCPNM simplifies the permeability calculation process and can accurately and rapidly predict tight sandstone gas permeability.

Estimation of 3D Permeability from Pore Network Models Constructed Using 2D Thin-Section Images in Sandstone Reservoirs

Using thin-section images to estimate core permeability is an economical and less time-consuming method for reservoir evaluation, which is a goal that many petroleum developers aspire to achieve. Although three-dimensional (3D) pore volumes have been successfully applied to train permeability models, it is very expensive to carry out. In this regard, deriving permeability from two-dimensional (2D) images presents a novel approach in which data are fitted directly on the basis of pore-throat characteristics extracted from more cost-effective thin sections. This work proposes a Fluid–MLP workflow for estimating 3D permeability models. We employed DIA technology combined with artificial lithology and pore classification to calculate up to 110 characteristic parameters of the pore-throat structure on the basis of 2D rock cast thin sections. The MLP network was adopted to train the permeability prediction model, utilizing these 110 parameters as input. However, the accuracy of the conventional MLP network only reached 90%. We propose data preprocessing using fluid flow simulations to improve the training accuracy of the MLP network. The fluid flow simulations involve generating a pore network model based on the 2D pore size distribution, followed by employing the lattice Boltzmann method to estimate permeability. Subsequently, six key structural parameters, including permeability calculated by LBM, pore type, lithology, two-dimensional porosity, average pore–throat ratio, and average throat diameter, were fed into the MLP network for training to form a new Fluid–MLP workflow. Comparing the results predicted using this new Fluid–MLP workflow with those of the original MLP network, we found that the Fluid–MLP network exhibited superior predictive performance.

Ensemble Learning Based Sustainable Approach to Carbonate Reservoirs Permeability Prediction

Permeability is a crucial property that can be used to indicate whether a material can hold fluids or not. Predicting the permeability of carbonate reservoirs is always a challenging and expensive task while using traditional techniques. Traditional methods often demand a significant amount of time, resources, and manpower, which are sometimes beyond the limitations of under developing countries. However, predicting permeability with precision is crucial to characterize hydrocarbon deposits and explore oil and gas successfully. To contribute to this regard, the current study offers some permeability prediction models centered around ensemble machine learning techniques, e.g., the gradient boost (GB), random forest (RF), and a few others. In this regard, the prediction accuracy of these schemes has significantly been enhanced using feature selection and ensemble techniques. Importantly, the authors utilized actual industrial datasets in this study while evaluating the proposed models. These datasets were gathered from five different oil wells (OWL) in the Middle Eastern region when a petroleum exploration campaign was conducted. After carrying out exhaustive simulations on these datasets using ensemble learning schemes, with proper tuning of the hyperparameters, the resultant models achieved very promising results. Among the numerous tested models, the GB- and RF-based algorithms offered relatively better performance in terms of root means square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) while predicting permeability of the carbonate reservoirs. The study can potentially be helpful for the oil and gas industry in terms of permeability prediction in carbonate reservoirs.