Reservoir Permeability Research Articles

Improved Relative Permeability Models Incorporating Water Film Effects in Low and Ultra-Low Permeability Reservoirs

Improved Relative Permeability Models Incorporating Water Film Effects in Low and Ultra-Low Permeability Reservoirs

Permeability Upscaling Conversion Based on Reservoir Classification

Deep and ultra-deep reservoirs are characterized by low porosity and permeability, pronounced heterogeneity, and complex pore structures, complicating permeability evaluations. Permeability, directly influencing the fluid production capacity of reservoirs, is a key parameter in comprehensive reservoir assessments. In the X Depression, low-porosity and low-permeability formations present highly discrete and variable core data points for porosity and permeability, rendering single-variable regression models ineffective. Consequently, accurately representing permeability in heterogeneous reservoirs proves challenging. In the following study, lithological and physical property data are integrated with mercury injection data to analyze pore structure types. The formation flow zone index (FZI) is utilized to differentiate reservoir types, and permeability is calculated based on core porosity–permeability relationships from logging data for each flow unit. Subsequently, the average permeability for each flow unit is computed according to reservoir classification, followed by a weighted average according to effective thickness. This approach transforms logging permeability into drill stem test permeability. Unlike traditional point-by-point averaging methods, this approach incorporates reservoir thickness and heterogeneity, making it more suitable for complex reservoir environments and resulting in more reasonable conversion outcomes.

Development of a new hydraulic electric index for rock typing in carbonate reservoirs

Rock typing techniques have relied on either electrical or hydraulic properties. The study introduces a novel approach for reservoir rock typing, the hydraulic-electric index (HEI), which combines the strengths of traditional electrical and hydraulic rock typing methods to characterize carbonate reservoirs more accurately. By normalizing the ratio of permeability and formation resistivity factor (K/FRF) with respect to porosity, the HEI method is applied to two datasets of carbonate core samples: dataset 1 consists of 112 carbonate core samples from the Tensleep formation in the Bighorn basin of Wyoming and Montana, and dataset 2 includes 81 carbonate core samples from the Asmari formation in the south-west of Iran. Statistical analysis confirms the effectiveness of the HEI in predicting permeability, with high determination coefficients for both datasets (resulting in determination coefficients (R2) of 0.965 and 0.904 for dataset 1 and dataset 2, respectively). The results classify the rock samples into distinct rock types, nine rock types for dataset 1 and four rock types for dataset 2, and demonstrate the HEI ability to capture the relationship between hydraulic conductivity and electrical resistivity in carbonate reservoir rocks. Applying the HEI method to the validation dataset yielded highly accurate permeability predictions, with average of determination coefficients of 0.883 and 0.859 for dataset 1 and dataset 2, respectively. Validation of the HEI method further confirms (20% of the dataset was set aside for validation, while the remaining 80% was used for the rock typing approach (5 folds)) its accuracy in predicting permeability, highlighting its robust predictive capacity for estimating permeability in carbonate reservoirs.

The Reservoir Injury Rules of Water Injection to an Ultralow Permeability Reservoir: Experimental Research Based on Core-NMR and Microfluidic Technology

The Reservoir Injury Rules of Water Injection to an Ultralow Permeability Reservoir: Experimental Research Based on Core-NMR and Microfluidic Technology

Optimization on self-assembled ultra-micro foam system for carbon dioxide flooding

Given the problem that the conventional foam injection and salt resistance are poor, the oil displacement effect is not obvious, and it is difficult to enhance oil recovery in the ultra-low permeability and high salinity reservoirs of Yanchang Oilfield, it is imperative to study a new foam flooding agent. Based on the surfactant’s self-assembled properties, foaming agent, stabilizer and complexing agent were screened in the absence of polymer and non-alkali. Three sets of self-assembly worm-like micelle systems were screened, and then a set of carbon dioxide foaming system was selected through comparative analysis: 0.50 wt% EAPMAC-12 + 0.20 wt% SDS + 0.09 wt% TEOA + 0.08 wt% EDTA. Under this condition, its viscosity, foaming volume, foam half-life and foam composite index are 18.8 mpa·s, 531 mL, 25 min and 9956 mL·min, respectively. Under the condition of the ratio of gas to liquid 3:1, the ultra-micro foam was obtained by gas–liquid co-injection in the sand pack, and the foam was round rather than the traditional pentagonal or hexagonal shape and the size was 5–31 um, indicating that the foam had good injection. Oil displacement experiment showed the average enhanced recovery rate was 12.84 % in ultra-low permeability cores, indicating that the foam had good oil displacement effect in ultra-low permeability reservoirs.

Evaluation of formation mobility inversion methods for formation testing while drilling

Formation mobility is a key parameter for characterizing reservoir permeability and predicting productivity. Formation mobility can be obtained in real-time by formation testing while drilling (FTWD), which is vital for improving the efficiency of oil and gas development and reducing production costs. In terms of FTWD, adopting an appropriate formation mobility inversion method is the key to accurately obtaining the mobility of the formation. The objective of this research is to evaluate the applicability and accuracy of formation mobility inversion methods in various coupled formations. Therefore, the mobility inversion methods for FTWD were reviewed in detail. Then, the process of finite element simulation of FTWD in various coupled formations, including uncoupled, hydro-mechanical coupled, thermal-hydro coupled, and thermal-hydro-mechanical coupled, was introduced. Based on the pressure response of FTWD generated by numerical simulation, four case studies of formation mobility inversion were performed using three different inversion methods, namely pressure drawdown (PDD), area integration (AI), and formation rate analysis (FRA). Finally, an evaluation was performed to assess the applicability of the inversion methods to different coupling formations, and the suggested method for each formation was provided. The results showed that the interpreted formation mobility based on the pressure response of FTWD is the apparent mobility near the wellbore, which can be influenced by the multi-physical coupling effect. The PDD method has a good applicability to high-mobility formations, a general applicability to low-mobility formations, and a poor applicability to tight formations. Both the AI and FRA methods can be used to invert formation mobility under different coupling conditions, and the accuracy of the FRA method is generally superior to that of the AI method. If the formation is in a coupled thermal-hydro-mechanical state, it is recommended to use the AI method, PDD method, and FRA method to invert the mobility for high-mobility, low-mobility, and tight formations, respectively. The results of this paper are beneficial for the accurate interpretation of formation mobility, which can promote the development of oil and gas resources.

Present-day stress regime, permeability, and fracture stimulations of coal reservoirs in the Qinshui Basin, northern China

Present-day stress regime, permeability, and fracture stimulations of coal reservoirs in the Qinshui Basin, northern China

Integrated modelling of CO2 plume geothermal energy systems in carbonate reservoirs: Technology, operations, economics and sustainability

The rising CO2 content in the atmosphere calls for urgent decarbonization efforts. Carbon capture and storage (CCS) have proven effective in storing large volumes of CO2 in geological reservoirs. Nevertheless, challenges persist in identifying sustainable energy sources and efficient storage sites, especially in carbonate reservoirs. This study aims to characterize the Miocene carbonate reservoir in the Jintan Megaplatform, for CO2 storage and geothermal energy utilization. By integrating advanced technologies such as CO2 Plume Geothermal (CPG) with 3D seismic techniques, borehole analysis and numerical modelling, the study reveals the distribution of critical reservoir characteristics, including architecture, heterogeneity, karstification, fractures, porosity, permeability, temperature and pressure that are paramount for CO2 plume and energy production. The reservoir is estimated to store over 31 Gt of CO2, produce 3.824 × 1018 J of geothermal energy and ⁓44.3 GW of power. This power output can be utilized for electrification of the CCS operations, industrial and municipals, potentially generating over $1.4 billion in revenue. A flow-through model has been proposed to improve energy efficiency, reservoir management, and risk mitigation. This study advances to achieving net-zero targets and the United Nations Sustainable Development Goals on clean energy, climate action and sustainable communities.

Impact of dissolution and precipitation on pore structure in CO2 sequestration within tight sandstone reservoirs

Complex physical and chemical reactions during CO2 sequestration alter the microscopic pore structure of geological formations, impacting sequestration stability. To investigate CO2 sequestration dynamics, comprehensive physical simulation experiments were conducted under varied pressures, coupled with assessments of changes in mineral composition, ion concentrations, pore morphology, permeability, and sequestration capacity before and after experimentation. Simultaneously, a method using NMR T2 spectra changes to measure pore volume shift and estimate CO2 sequestration is introduced. It quantifies CO2 needed for mineralization of soluble minerals. However, when CO2 dissolves in crude oil, the precipitation of asphaltene compounds impairs both seepage and storage capacities. Notably, the impact of dissolution and precipitation is closely associated with storage pressure, with a particularly pronounced influence on smaller pores. As pressure levels rise, the magnitude of pore alterations progressively increases. At a pressure threshold of 25 MPa, the rate of change in small pores due to dissolution reaches a maximum of 39.14%, while precipitation results in a change rate of −58.05% for small pores. The observed formation of dissolution pores and micro-cracks during dissolution, coupled with asphaltene precipitation, provides crucial insights for establishing CO2 sequestration parameters and optimizing strategies in low permeability reservoirs.

Mineral and fluid transformation of hydraulically fractured shale: case study of Caney Shale in Southern Oklahoma

This study explores the geochemical reactions that can cause permeability loss in hydraulically fractured reservoirs. The experiments involved the reaction of powdered-rock samples with produced brines in batch reactor system at temperature of 95 °C and atmospheric pressure for 7-days and 30-days respectively. Results show changes in mineralogy and chemistry of rock and fluid samples respectively, therefore confirming chemical reactions between the two during the experiments. The mineralogical changes of the rock included decreases of pyrite and feldspar content, whilst carbonate and illite content showed an initial stability and increase respectively before decreasing. Results from analyses of post-reaction fluids generally corroborate the results obtained from mineralogical analyses. Integrating the results obtained from both rocks and fluids reveal a complex trend of reactions between rock and fluid samples which is summarized as follows. Dissolution of pyrite by oxygenated fluid causes transient and localized acidity which triggers the dissolution of feldspar, carbonates, and other minerals susceptible to dissolution under acidic conditions. The dissolution of minerals releases high concentrations of ions, some of which subsequently precipitate secondary minerals. On the field scale, the formation of secondary minerals in the pores and flow paths of hydrocarbons can cause significant reduction in the permeability of the reservoir, which will culminate in rapid productivity decline. This study provides an understanding of the geochemical rock–fluid reactions that impact long term permeability of shale reservoirs.

The Main Controlling Factors of the Cambrian Ultra-Deep Dolomite Reservoir in the Tarim Basin

The genesis of deep-to-ultra-deep dolomite reservoirs in the Tarim Basin is crucial for exploration and development. The Cambrian subsalt dolomite reservoirs in the Tarim Basin are widely distributed, marking significant prospects for ultra-deep reservoir exploration. Based on big data methodologies, this study collects and analyzes porosity and permeability data of carbonate reservoirs in the western Tarim Basin, specifically targeting the Cambrian deep-oil and gas-reservoir research. Through an examination of the sedimentary evolution and distribution of carbonate–evaporite sequences, and considering sedimentary facies, stratigraphic sediment thickness, fault zone distribution, and source-reservoir assemblages as primary reference factors, the study explores the macro-distribution patterns of porosity and permeability, categorizing three favorable reservoir zones. The controlling factors for the development of Cambrian carbonate reservoirs on the western part of the Tarim Basin are analyzed from the perspectives of sedimentary and diagenetic periods. Factors such as tectonic activity, depositional environment, microbial activity, and pressure dissolution are analyzed to understand the main causes of differences in porosity and permeability distribution. Comprehensive analysis reveals that the porosity and permeability of the Series2 carbonate reservoirs are notably high, with extensive distribution areas, particularly in the Bachu–Tazhong and Keping regions. The geological pattern of “Three Paleo-uplifts and Two Depressions” facilitated the formation of inner-ramp and intra-platform shoals, creating conducive conditions for the emergence of high-porosity reservoirs. The characteristics of reservoir development are predominantly influenced by diagenetic and tectonic activities. The Miaolingian is chiefly affected by diagenesis, featuring high permeability but lower porosity and smaller distribution range; dolomitization, dissolution, and filling processes under a dry and hot paleoclimate significantly contribute to the formation and preservation of reservoir spaces. In the Furongian, the Keping and Bachu areas display elevated porosity and permeability levels, along with substantial sedimentary thickness. The conservation and development of porosity within thick dolomite sequences are mainly governed by high-energy-particulate shallow-shoal sedimentary facies and various dissolution actions during diagenesis, potentially indicating larger reserves.

Reservoir Permeability Prediction Based on Machine Learning

Reservoir Permeability Prediction Based on Machine Learning

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.

Experimental study of permeability characteristics of fracture-hosted hydrate-bearing clay sediments under triaxial shear

Reservoir permeability during the hydrate exploitation process is closely related to gas production. Fractures influence hydrate distribution and the evolution of reservoir permeability. Moreover, shear during exploitation can disturb the structure of sediments. Therefore, studying permeability and its evolution under shear in fracture-hosted hydrate-bearing sediments is significant for hydrate exploitation projects in the South China Sea. In this paper, standard sand and montmorillonite were mixed, and three different fracture angles were created to simulate sediment fracture. Consolidation, shear, and permeability measurements were employed to investigate mechanical and permeability properties. The results showed that the permeability of fracture-hosted hydrate-bearing sediments decreased and then increased with increasing hydrate saturation, both before and after consolidation. The compressibility of sediments played an important role in the permeability damage rate caused by consolidation and normalized permeability at the breaking point. Furthermore, fractures caused an undesired double peak and the disappearance of the permeability breaking point hysteresis relative to the stress breaking point. However, these effects were mitigated by increasing saturation. Lastly, the analysis of permeability sensitivity coefficients revealed that permeability was most sensitive to strain in the early shear stages. This study can guide methane hydrate exploitation in the South China Sea.

Key indicators of caprock sealing assessment with consideration of faults in potential CO2 geological storage sites in Subei Basin, China

Good caprock sealing is crucial for ensuring the long-term safety and security of carbon dioxide (CO2) geological storage. However, concealed faults within caprocks and reservoirs can impact the transport and accumulation of CO2 plumes. Due to the uncertainties associated with the geometric structure, physical properties, and combined relationships among reservoir, caprock and fault, accurately evaluating caprock sealing is challenging. To address the challenge of identifying key indicators for caprock sealing considering faults, this study focuses on the one potential CO2 geological storage field in the Subei Basin, China. First, this study establishes a hydraulic-mechanical (HM) coupled finite element model considering a combination of caprock, reservoir and fault. Then, 22 research indicators, including fault offset, fault dip, caprock thickness, burial depth, permeability and mechanical properties, are analysed to evaluate their influence on caprock sealing via the tornado analysis and response surface methods. Finally, key indicators are determined based on evaluation criteria, such as pore pressure increment (ΔPP) and Coulomb failure stress (CFS), in the fault plane. The research results indicate that fault dip, fault offset, fault permeability, burial depth, and reservoir permeability are key indicators. The caprock thickness, caprock permeability, and caprock Young's modulus significantly influence the caprock sealing capacity. The ΔPP and CFS increase with increasing fault dip and offset. When the fault dip exceeds 45°, the ΔPP and CFS reach maximum values at the interface between the reservoir and caprock. Fault permeability has a greater impact than reservoir permeability and caprock permeability. The research results may provide guidance for the evaluation of caprock sealing capacity for CO2 geological storage.

Numerical simulation of CO2-ECBM for deep coal reservoir with strong stress sensitivity

CH4 production rate of coalbed methane (CBM) well decreases rapidly during primary recovery in the deeply buried coal seam, resulting in a lot of CH4 residues. CO2 pour into deep coal seam with high stress sensitivity is available for enhancing CH4 recovery by improving permeability for reservoir fracture and displacing CH4 adsorbed in matrix. A coupled adsorp-hydro-thermo-mechanical (AHTM) model for deep methane development is established by considering the coupling relationships of non-isothermal and non-constant pressure competitive adsorption between CO2 and CH4, multi-phase flow, unsteady diffusion, heat transmission and in-situ stress variety. The model is verified by historical production and then used for CO2 enhanced CBM (CO2-ECBM) of deep coal reservoir in a sedimentary basin in Northwest China. The simulation results show that: (1) For primary recovery, permeability in coal reservoir drops rapidly with the development of CBM, which seriously restricts the production of CH4. The permeability of the reservoir decreases from 7.89 × 10−16 m2 to less than 1.50 × 10−16 m2, CH4 production rate in CBM well reduces to below 2000 m3/d, and the average total CH4 content of coal reservoir is reduced by 5.49 m3/t with the decrease of only 1.12 m3/t of average adsorbed CH4 in a production duration of 2000 d (2) With 10 MPa CO2 continuous injection into coal seam after 700d of primary, the permeability for reservoir and CH4 production rate increase while the total CH4 content and adsorption CH4 content in reservoir decrease compared with the primary recovery. (3) CO2 pouring into coal reservoir increases the CH4 production time and rate, which improves CH4 recovery of coal reservoir. And it increases by 23.36 %, 23.07 % and 22.46 % with shut-in thresholds of CH4 production rate of 1000 m3/d, 800 m3/d and 600 m3/d, respectively. The investigation is of great significance for the development of deep coalbed methane.

Multifractal characteristics on pore structure of Longmaxi shale using nuclear magnetic resonance (NMR)

The efficient exploration and extraction of shale gas is essential for China's energy structure as a replacement for natural gas. In this research, shale samples from the Longmaxi Formation in Changning, Sichuan Province were investigated for their pore structure. To achieve this, X-ray diffraction (XRD) and nuclear magnetic resonance (NMR) experiments were performed on the samples. Fractal theory was employed to characterize the pore structure and fractal features of the shale reservoirs. The fractal characteristics of reservoir rocks were correlated with physical parameters and mineral components to identify the controlling factors for the multifractal dimension. The results indicate the following: ① Quartz predominates in the mineral composition of shale in the study area, while clay minerals are the least abundant. ② The primary pore types observed in the samples are bound fluid pores, primarily controlled by mesopores (2 nm ≤ r ≤ 50 nm). ③ The calculated multifractal parameters show that the heterogeneous pore structure exhibits multifractal characteristics. ④ The low probability multifractal parameters Dmin-D0 and αmax-α0 were found to be negatively correlated with reservoir porosity, permeability, and clay mineral content, while the high probability multifractal parameters D0-Dmax and α0-αmin were found to be positively correlated with them. The comprehensive fractal characterization of reservoir rocks demonstrates the applicability of multifractal dimensions in characterizing the heterogeneity of shale reservoir pore structures, which holds potential promise for coal methane exploration.

A novel method to identify preferential flow paths by considering the time-varying effect of petrophysical parameters in ultra-high water-cut reservoirs

The continental clastic reservoirs mainly distributed in the eastern region of China are regarded as the “ballast stone” for ensuring national energy security. After long-term waterflooding, reservoir petrophysical parameters have changed drastically. When the ultra-high water-cut period is achieved, the preferential flow paths are widely distributed inside the reservoir, resulting in severe ineffective water circulation and high difficulty in inhibiting water cut rise and stabilizing oil production. Due to the slow calculation speed and low identification accuracy of the existing methods, it is crucial to propose a novel method to identify preferential flow paths by considering the time-varying impact of petrophysical parameters in ultra-high water-cut reservoirs. To tackle this issue, massive dynamic and static data are collected from typical water-drive reservoirs in the Daqing oilfield to analyze the dynamic characteristics of preferential flow wells and the time-variation laws of reservoir parameters. A rapid evaluation index system for preferential flow paths is thereafter established. By describing the time-variation of reservoir permeability and fluid apparent viscosity and introducing a dynamic flow resistance coefficient to infer the inter-well or inter-layer connectivity, a novel method with the time-varying effect of petrophysical parameters considered is developed to quickly identify preferential flow paths in ultra-high water-cut reservoirs. A critical criterion of preferential flow paths is further constructed. Finally, the proposed method is used to determine the spatial distribution of preferential flow paths in a typical block of the Daqing oilfield. Results demonstrate that, once a preferential flow path is formed, some distinct dynamic characteristics of injectors and producers will be exhibited. Based on the estimated dynamic flow resistance coefficient, the preferential flow paths are further classified into four types: non-preferential, primary preferential, intermediate preferential, and strong preferential flow paths. Using the proposed method, the identification accuracy of preferential flow paths exceeds 95%, and the identification speed is more than 10 times faster than the traditional methods.

The experimental study on multiple mechanisms of enhanced CBM recovery by autogenous nitrogen fracturing fluid

Hydraulic fracturing is a widely adopted technique for enhancing the permeability of coalbed methane (CBM) reservoirs, thus improving the recovery of CBM. Although previous studies have extensively explored the role of fracturing fluids in creating fractures and improving permeability, there remains a notable deficiency in the literature regarding the impact of these fluids on enhancing gas desorption and diffusion. This research employs an experimental investigation into a novel autogenous nitrogen (N2) fracturing fluid, demonstrating its significant potential for increasing CBM reservoir permeability and enhancing the desorption and diffusion of CBM. Through optimization experiments, the study initially determines the optimal proportions of sodium nitrite (NaNO2), ammonium chloride (NH4Cl), and an acidic activator to maximize the generation of N2. Kinetic experiments and subsequent analyses reveal that the autogenous N2 fracturing fluid releases a substantial amount of N2 and heat, with the reaction rate highly influenced by initial pressure and temperature conditions. Fracturing experiments on coal samples demonstrate that the release of N2 increases the fluid pressure within the pore spaces, initiating micro-fractures and enhancing permeability. Additionally, the increased pore pressure mitigates the water block effect and improves the gas diffusion. The heat and gas released during the reaction significantly facilitate the desorption of CBM within coals. This fracturing fluid offers a comprehensive approach for enhancing CBM recovery.

Carbonate reservoir characterization and permeability modeling using Machine Learning ـــ a study from Ras Fanar field, Gulf of Suez, Egypt

Predicting facies and petrophysical properties along and between wells is challenging in carbonate reservoir modeling. In the Nullipore carbonate reservoir, Ras Fanar field, depositional and long-term diagenetic processes result in a high degree of heterogeneity and complex distribution of facies, which in turn affect the reservoir quality. This provides a significant obstacle to building accurate geological models. This study integrates thin sections, routine core analyses, and well logging data to overcome such difficulties and model the Nullipore carbonate facies and permeability. The detailed petrographic analysis revealed the existence of seven microfacies in the reservoir, which are summed up into three facies associations (FAs), each of which represents a specific reservoir rock type (RRT): (1) supratidal FA, (2) intertidal FA, and (3) shallow subtidal FA. The three FAs were correlated with the gamma-ray logs to create facies logs for the studied wells, which were further populated via the Truncated Gaussian Simulation method. Cross-validation was used to evaluate the model's accuracy. The analysis of the available core data infers that the three RRTs are prospective and have a wide permeability distribution. However, RRT3 constitutes the best reservoir quality. The sedimentological analysis revealed that the long-term diagenetic events, involving the dolomitization of limestone and the dissolution of allochems have a major role in improving the pore connectivity and permeability of the reservoir. Fracture characterization discloses that fractures play a significant role in fluid storage and migration. Three Machine Learning (ML) models, including Adaptive boosting (AdaBoost), Gradient Boosting (GB), and Extreme Gradient Boosting (XGB), were developed to integrate the RRTs, porosity, and permeability to improve permeability prediction. Statistical analysis revealed that the XGB model outperforms other models and exhibits the highest prediction performance. The present study provides further insights into the characterization and modeling of facies and permeability of complex carbonate reservoirs. It can be applied in similar geological settings to better interpretation of depositional and diagenetic controls on reservoir quality assessment and aid in the field development plan.