Search

Abstract With the growing emphasis on environmental protection, many coal mines in northern China were closed. However, the cessation of pumping operations in those closed mines has caused a rise in groundwater levels, giving rise to various safety and environmental concerns. Understanding the patterns of water level recovery is vital for effectively managing abandoned mine sites and ensuring the uninterrupted production of adjacent coal mines. While the groundwater hazards in goaf areas have been extensively studied by scholars, there is a notable scarcity of research on water level recovery in closed coal mines. To address this knowledge gap, this study focuses on investigating the water level recovery patterns in abandoned mine sites, using the Zhaogezhuang Mine as a case study. Based on these research findings, we will conduct future studies of the impact of water level recovery on local communities, the ecological environment, and the geological environment.

Abstract The oil and gas industry relies on accurately predicting profitable clusters in subsurface formations for geophysical reservoir analysis. It is challenging to predict payable clusters in complicated geological settings like the Lower Indus Basin, Pakistan. In complex, high-dimensional heterogeneous geological settings, traditional statistical methods seldom provide correct results. Therefore, this paper introduces a robust unsupervised AI strategy designed to identify and classify profitable zones using self-organizing maps (SOM) and K-means clustering techniques. Results of SOM and K-means clustering provided the reservoir potentials of six depositional facies types (MBSD, DCSD, MBSMD, SSiCL, SMDFM, MBSh) based on cluster distributions. The depositional facies MBSD and DCSD exhibited high similarity and achieved a maximum effective porosity (PHIE) value of ≥ 15%, indicating good reservoir rock typing (RRT) features. The density-based spatial clustering of applications with noise (DBSCAN) showed minimum outliers through meta cluster attributes and confirmed the reliability of the generated cluster results. Shapley Additive Explanations (SHAP) model identified PHIE as the most significant parameter and was beneficial in identifying payable and non-payable clustering zones. Additionally, this strategy highlights the importance of unsupervised AI in managing profitable cluster distribution across various geological formations, going beyond simple reservoir characterization.

Abstract Geothermal energy is a sustainable energy source that meets the needs of the climate crisis and global warming caused by fossil fuel burning. Geothermal resources are found in complex geological settings, with faults and interconnected networks of fractures acting as pathways for fluid circulation. Identifying faults and fractures is an essential component of exploiting geothermal resources. However, accurately predicting fractures without high-resolution geophysical logs (e.g., image logs) and well-core samples is challenging. Soft computing techniques, such as machine learning, make it possible to map fracture networks at a finer resolution. This study employed four supervised machine learning techniques (multilayer perceptron (MLP), random forests (RF), extreme gradient boosting (XGBoost), and support vector regression (SVR)) to identify fractures in geothermal carbonate reservoirs in the sub-basins of East China. The models were trained and tested on a diverse well-logging dataset collected at the field scale. A comparison of the predicted results revealed that XGBoost with optimized hyperparameters and data division achieved the best performance than RF, MLP, and SVR with RMSE = 0.02 and R2 = 0.92. The Q-learning algorithm outperformed grid search, Bayesian, and ant colony optimizations. The blind well test demonstrates that it is possible to accurately identify fractures by applying machine learning algorithms to standard well logs. In addition, the comparative analysis indicates that XGBoost was able to handle the complex relationship between input parameters (e.g., DTP > RD > DEN > GR > CAL > RS > U > CNL) and fracture in geologically complex geothermal carbonate reservoirs. Furthermore, comparing the XGBoost model with previous studies proved superior in training and testing. This study suggests that XGBoost with Q-learning-based optimized hyperparameters and data division is a suitable algorithm for identifying fractures using well-log data to explore complex geothermal systems in carbonate rocks. Graphical abstract

Abstract For complex and multi-layered clastic oil reservoir formations, modeling lithofacies and petrophysical parameters is essential for reservoir characterization, history matching, and uncertainty quantification. This study introduces a real oilfield case study that conducted high-resolution geostatistical modeling of 3D lithofacies and petrophysical properties for rapid and reliable history matching of the Luhais oil reservoir in southern Iraq. For capturing the reservoir's tidal depositional setting using data collected from 47 wells, the lithofacies distribution (sand, shaly sand, and shale) of a 3D geomodel was constructed using sequential indicator simulation (SISIM). Based on the lithofacies modeling results, 50 sets of porosity and permeability distributions were generated using sequential Gaussian simulation (SGSIM) to provide insight into the spatial geological uncertainty and stochastic history matching. For each rock type, distinct variograms were created in the 0° azimuth direction, representing the shoreface line. The standard deviation between every pair of spatial realizations justified the number of variograms employed. An upscaled version of the geomodel, incorporating the lithofacies, permeability, and porosity, was used to construct a reservoir-flow model capable of providing rapid, accurate, and reliable production history matching, including well and field production rates.

The orthogonal experiments of similar materials were optimized and analyzed in order to accurately simulate the mechanical properties and the fracture evolution law of thick coal seam overlying strata during mining in this study. The experimental results indicated that similar materials using gypsum and calcium carbonate as cementing agents had a wide range of compressive strength (173.80 kPa–425.95 kPa) and were suitable for simulating various rock properties. Adding an appropriate amount of calcium carbonate can improve the brittleness and mechanical properties of similar materials using gypsum as cementing agents. The failure mode of similar materials transitioned from shear to tensile failure with the increase of the mass ratio of aggregate to cementing agents and the mass ratio of calcium carbonate to gypsum. Moreover, the compressive strength of similar materials rapidly decreased with an increase in the mass ratio of aggregate to cementing materials. And the compressive strength showed an increasing trend with the decrease of the mass ratio of calcium carbonate to gypsum. Moisture content had a significant impact on the density of similar materials, other parameters had small impacts. A thick coal seam mining experimental model was designed based on the experimental results of similar materials, which showed that Qianjiaying Mine may experience basic roof collapse when mining reached 58.1 m. The recommended periodic weighting pace for face pressure on the working face was approximately 15.0 m. Appropriate measures are necessary to adopt to prevent disasters after mining to a length of 58.1 m, followed by every 15.0 m of mining.

The safety of underground coal mining is threatened by coal spontaneous combustion, making it essential to develop effective inhibitors to prevent such incidents. To address this, a new in-situ gel has been proposed, which is formed in coal pores from a fire-prevention aqueous solution (FPAS) that reacts with atmospheric CO2. To determine the appropriate concentrations of polyvinyl alcohol (PVA) and sodium-metasilicate nonahydrate (SN) for FPAS, 24 groups of wire-mesh basket tests were conducted on Baiyinhua coal. The gelling mechanism and performance on fire inhibition of FPAS were then investigated using temperature-programmed tests, scanning electron microscopy, energy dispersive spectrometry, fourier transform infrared tests, thermogravimetric differential thermal analysis tests, and fire-extinguishing tests. The results indicate an inhibition rate of up to 43.3% and effective protection of active groups from oxidation. The in-situ gel demonstrated excellent fire-extinguishing properties. Additionally, the self-ignition temperatures of residual coals with varying thicknesses were estimated using the Frank-Kamenetskii theory. The combined method of CO2 injection and FPAS spraying is recommended for achieving better fire-prevention effectiveness in coal mine gob. The findings are expected to provide guidance on the application of FPAS to address thermal hazards in coal mines.

This study presents a method to develop a series of unique deliverability smart models for underground natural gas storage (UNGS) in different types of target formations. The natural gas supply loop is defined by periodic mismatches between demand and supply. Efficient and faster approaches for forecasting UNGS deliverability may not only assist stakeholders but also the competitive natural gas industry. Due to this fact, this article suggests a series of robust deliverability estimation models for 387 UNGS sites in depleted fields, aquifers, and salt domes based on rigorous machine learning (ML) techniques. To this end, the potential of three ML algorithms, including Gaussian Process Regression (GPR), Least Squares Support Vector Machine (LSSVM), and Extra Tree (ET), is employed. To assess and compare the proposed models, statistical parameters including coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and standard deviation (SD) were employed. Accordingly, in the case of depleted fields, the GPR, LSSVM, and ET paradigms show overall R2, RMSE, and MAE of 0.999999998, 4.75E−06, 0.00021, and 0.00021. For salt domes, the GPR, LSSVM, and ET models indicate overall R2, RMSE, and MAE of 0.987, 0.0046, and 0.11. Finally, for aquifers, the GPR, LSSVM, and ET algorithms represent overall R2, RMSE, and MAE of 0.999999997, 7.1094E−06, and 0.0002102. The prediction performance reveals that the GPR model is superior to the LSSVM and ET models. This study found that the proposed intelligent models could be utilized as a template for fast estimating the deliverability of UNGS in depleted fields, aquifers, and salt domes with high accuracy. In the end, the outcomes of this study contribute to a deeper understanding of the critical role of machine learning in resolving the difficulty of forecasting the UNSG on cleaner production and sustainable development strategies.

Understanding geological variance in a proved reservoir requires accurate as well as exact characterization of lithological facies. In the Kadanwari gas field, machine learning (ML) classification algorithms have been used to forecast facies on such an accessible dataset. The goal is to increase the reliability of facies categorization using a rigorous application of machine learning. In the current study to identify lithofacies, we have used the self-organizing map (SOM) and crossplot techniques. In the classification of the reservoir, recognition of lithofacies is the main piece of work. It is expensive to identify lithofacies with conventional methods from core data, and it is challenging to extend this application to non-cored wells. This research provides a less expensive method for the systematic and objective recognition of lithofacies through well-log data by Kohonen SOM. The SOMs are human-made neural networks that do not need surveillance and map the input space into groups in the structure as topology is arranged according to the input data changes. The results of SOM and crossplot indicates that the zone of interest is mainly composed of sandstone, shaly sandstone, shale with diminutive amount of carbonates. The cluster analysis approach has been utilized to categorize the reservoir rock groups in the Cretaceous reservoir for the Kadanwari gas field by analyzing the variance of reservoir properties data that are forecast by examining well log dimensions. Four groups of reservoirs were concluded, each of which was internally identical in petrophysical properties but distinct from the others. The reservoir mainly composed of sandstone is graded as excellent reservoir, while shale is graded as poor reservoir.

Future gas field development and prospect assessment depend on accurate reservoir parameter characterization. The understanding of the tight sand distribution of the Shanxi and Taiyuan Formations within the Hangjinqi area is ambiguous due to the presence of coal and mudstone lithofacies, high heterogeneity, and poor resolution of the seismic data. Thus, it is difficult to determine the reservoir’s thickness. To cope with this challenge, we have employed the advanced method of constrained sparse spike inversion (CSSI) utilizing 3D seismic and nine wells for the distinction of tight sandstone facies from the coal and mudstone facies. Results of petrophysical analysis of studied well J54 show that the coal and mudstone facies are dominant towards the T9c horizon, whereas tight sandstone facies are present towards the T9d horizon. The obtained findings show that the CSSI accurately identified the spatial distribution of sand-ratio in the zone of interest (ZOI) that lies between the T9c and T9d horizons. The acoustic impedance (AI) of coal shows the lowest AI values, whereas the tight sandstone shows the highest AI values. The tight sandstone facies shows moderate values of AI in the range of 8.5 × 106 kg/m2s to 1.20 × 107 kg/m2s. The impedance map of T9c suggested the presence of coal and mud facies, whereas the T9d impedance map suggest the presence of maximum tight sandstone facies. The sand-ratio map of T9d showed maximum reservoir thickness that ranges from 0.65-0-95, whereas the sand-ratio value mostly ranges from 0 to 0.5 on the T9c map. The maximum sand-ratio values on T9d show that the lower Shanxi Formation has good reservoir characteristics. Whereas, due to the presence of coal and mudstone in the Taiyuan Formation, the T9c map shows low values of sand-ratio. The maximum sand-ratio regions within the targeted T9c-T9d layers should be exploited for future gas explorations.

Precision porosity and facies determinations are critical in reducing drilling uncertainty and increasing hydrocarbon recoveries from heterogeneous sources. The porosity and facies distribution of the Taiyuan-Shanxi Formations (T9c-T9d), and Shihezi-1 Formation (T9d-T9e) within the Hangjinqi area are uncertain and no studies have covered the spatial distribution on a regional scale. The heterogeneous nature of coal, mudstone, and sandstone makes it challenging to comprehend the distribution of porosity and lithofacies. Also, the seismic resolution is not able to resolve the reservoir heterogeneity. Therefore, we have employed regional 3D seismic and well logs by utilizing the advanced acoustic impedance inversion to accomplish our study. Results of petrophysical analysis conducted on the well J32 showed that Shihezi-1 and Shanxi-1 Formations have potential gas-saturated zones. Crossplot analysis distinguished the lowest impedance coal from the highest impedance tight sandstone facies. The outcomes of the constrained sparse spike inversion (CSSI) reliably distinguished the coal facies from the channel-tight sandstone facies. The tight sandstone facies showed the highest impedance values as compared to coal and mudstone facies on the absolute acoustic impedance section. Impedance and porosity maps of T9d and T9e suggested the presence of a maximum porosity (8%–12% for T9d, and 5%–10% for T9e), and maximum distribution of tight sandstone facies, while T9c shows the lowest porosity (0%–6%) and lowest impedance values due to the presence of coal facies. Thick braided fluvial channels are evident on the T9d impedance and porosity maps, making it the most favorable horizon to produce the maximum gas. Whereas, T9c shows the least distribution of sandstone facies making it the least favorable. We propose that the zones of maximum porosity on the T9c, T9d, and T9e horizons can be exploited for future gas explorations.

This study involved an interpretation of wire-line logs in assessing the hydrocarbon capacity of the sandstone reservoir within the gas fields of Kadanwari, Sindh, Pakistan. Wire-line logs from four wells (KD-01, KD-03, KD-10 and KD-11) were used in our research and provided interpretation for thirteen reservoir zones. Reservoir analyses were done for effective porosity (ϕeff), shale content (Vsh), net pay thickness variations, water saturation, and hydrocarbon (Sw and Shc). Hydrocarbon-bearing zones consist of high values of resistivity, permeability, porosity, low water saturation content, and less shale content, indicating the presence of clean sand. The Thomas Stieber model findings show that in lower Goru sand, the laminated form of shale distribution persists. Sub-reservoirs’ petrophysical parameters were analyzed and ranked into a good sand reservoir quality (having ϕeff ∼0.11-0.44%), permeability (∼10.539-477.76 mD), hydrocarbon saturation (having Shc ∼0.59-0.86%), and water saturation (having Sw ∼0.18-0.45%). In the current research Indonesian model has been used to test for water saturation over a shaly-sand reservoir situated in a heterogeneous zone. It was observed that each well exhibited Sw at values lesser than 60%. This is indicative the selected zone has a hydrocarbon potential, and the hydrocarbons are of good quality. Isoparametric maps and crossplots of litho-saturation results reveal variations in the horizontal and vertical petrophysical parameters of the reservoir. The subsurface reservoir geographical distribution is visualized employing isoparametric maps. The fuel treasure in the southwestern section of the study area is enormous, as revealed by the petrophysical investigations, suggesting more well-drilling prospects in the gas fields of the lower Goru Formation situated in Kadanwari. Our research identified a quality hydrocarbon hotspot zone of immense economic value in Southern Kadanwari. In contrast, more research is needed regarding the northeastern section though our present findings suggest the northeastern section should be avoided because of excess shale and high-water concentrations.

Abstract Residual Oil Zones (ROZs) become potential formations for Carbon Capture, Utilization, and Storage (CCUS). Although the growing attention in ROZs, there is a lack of studies to propose the fast tool for evaluating the performance of a CO2 injection process. In this paper, we introduce the application of artificial neural network (ANN) for predicting the oil recovery and CO2 storage capacity in ROZs. The uncertainties parameters, including the geological factors and well operations, were used for generating the training database. Then, a total of 351 numerical samples were simulated and created the Cumulative oil production, Cumulative CO2 storage, and Cumulative CO2 retained. The results indicated that the developed ANN model had an excellent prediction performance with a high correlation coefficient (R2) was over 0.98 on comparing with objective values, and the total root mean square error of less than 2%. Also, the accuracy and stability of ANN models were validated for five real ROZs in the Permian Basin. The predictive results were an excellent agreement between ANN predictions and field report data. These results indicated that the ANN model could predict the CO2 storage and oil recovery with high accuracy, and it can be applied as a robust tool to determine the feasibility in the early stage of CCUS in ROZs. Finally, the prospective application of the developed ANN model was assessed by optimization CO2-EOR and storage projects. The developed ANN models reduced the computational time for the optimization process in ROZs.

Porous carbons as solid adsorbent materials possess effective porosity characteristics that are the most important factors for gas storage. The chemical activating routes facilitate hydrogen storage by adsorbing on the high surface area and microporous features of porous carbon-based adsorbents. The present research proposed to predict H2 storage using four nature-inspired algorithms applied in the random forest (RF) model. Various carbon-based adsorbents, chemical activating agents, ratios, micro-structural features, and operational parameters as input variables are applied in the ML model to predict H2 uptake (wt%). Particle swarm and gray wolf optimizations (PSO and GWO) in the RF model display accuracy in the train and test phases, with an R2 of ~0.98 and 0.91, respectively. Sensitivity analysis demonstrated the ranks for temperature, total pore volume, specific surface area, and micropore volume in first to fourth, with relevancy scores of 1 and 0.48. The feasibility of algorithms in training sizes 80 to 60% evaluated that RMSE and MAE achieved 0.6 to 1, and 0.38 to 0.52. This study contributes to the development of sustainable energy sources by providing a predictive model and insights into the design of porous carbon adsorbents for hydrogen storage. The use of nature-inspired algorithms in the model development process is also a novel approach that could be applied to other areas of materials science and engineering.

Abstract This study is intended to expand the scope of microbial enhanced oil recovery (MEOR) simulation studies from 1D to field scale focussing on fluid viscosity variation and heterogeneity that lacks in most MEOR studies. Hence, we developed a model that incorporates: (1) reservoir simulation of microbe-induced oil viscosity reduction and (2) field-scale simulation and robust geological uncertainty workflow considering the influence of well placement. Sequential Gaussian simulation, co-kriging and artificial neural network were used for the petrophysical modelling prior to field-scale modelling. As per this study, the water viscosity increased from 0.5 to 1.72 cP after the microbe growth and increased biomass/biofilm. Also, we investigated the effect of the various component compositions and reaction frequencies on the oil viscosity and possibly oil recovery. For instance, the fraction of the initial CO2 in the oil phase (originally in the reservoir) was varied from 0.000148 to 0.005 to promote the reactions, and more light components were produced. It can be observed that the viscosity of oil reduced considerably after 90 days of MEOR operation from an initial 7.1–7.07 cP and 6.40 cP, respectively. Also, assessing the pre- and post-MEOR oil production rate, we witnessed two main typical MEOR field responses: sweeping effect and radial colonization occurring at the start and tail end of the MEOR process, respectively. MEOR oil recovery factors varied from 28.2 to 44.9% OOIP for the various 200 realizations. Since the well placement was the same for all realizations, the difference in the permeability distribution amongst the realizations affected the microbes’ transport and subsequent interaction with nutrient during injection and transport.

Abstract Weathered and fractured crystalline basement is known as the important unconventional reservoir in the Cuu Long Basin. Naturally fractured reservoir plays a crucial role in oil exploration to contribute for hydrocarbon production in Vietnam. However, the complexity and heterogeneity of the fractures system in the basement reservoir are challenges for oil and gas production. They require the realistic simulation scenarios to estimate the hydrocarbon potential as well as field development plan of these reservoirs. Thus, this paper aims to propose the feasibility development scenarios to improve oil recovery factor for crystalline basement reservoir, X field, Cuu Long Basin, Vietnam. First, history matching process is validated for the model to fit the actual production data (reservoir pressure, pressure, water cut in each well) in order to approach closer the fluid flow behavior through the reservoir. The manual matching was selected to adjust the actual aquifer size and permeability distribution with limit simulation runs. Next, the highest reliability matching model which approximately reflects the actual fluid flow behavior can be used as the base case to forecast the future reservoir performance through the field development plan. The most potential scenario is to add six new infill production wells, two side track wells and two water injection wells. The forecasted results indicate that this scenario yields 8% more oil recovery factor compared to the natural drive with thirteen producers. This result suggests that the precise field development plan is to increase the efficiency of the production process by increasing the displacement parameters of residual oil and reservoir sweep efficiency by stimulation. The major contribution of this paper demonstrates the merits of the field development plan in fractured basement reservoir. The findings of this study can help better understand the fluid flow behavior using the production history profiles and field development scenarios of crystalline basement reservoir of Cuu Long Basin.

The forecasting and prediction of crude oil are necessary in enabling governments to compile their economic plans. Artificial neural networks (ANN) have been widely used in different forecasting and prediction applications, including in the oil industry. The dendritic neural regression (DNR) model is an ANNs that has showed promising performance in time-series prediction. The DNR has the capability to deal with the nonlinear characteristics of historical data for time-series forecasting applications. However, it faces certain limitations in training and configuring its parameters. To this end, we utilized the power of metaheuristic optimization algorithms to boost the training process and optimize its parameters. A comprehensive evaluation is presented in this study with six MH optimization algorithms used for this purpose: whale optimization algorithm (WOA), particle swarm optimization algorithm (PSO), genetic algorithm (GA), sine–cosine algorithm (SCA), differential evolution (DE), and harmony search algorithm (HS). We used oil-production datasets for historical records of crude oil production from seven real-world oilfields (from Tahe oilfields, in China), provided by a local partner. Extensive evaluation experiments were carried out using several performance measures to study the validity of the DNR with MH optimization methods in time-series applications. The findings of this study have confirmed the applicability of MH with DNR. The applications of MH methods improved the performance of the original DNR. We also concluded that the PSO and WOA achieved the best performance compared with other methods.

To achieve carbon dioxide (CO2) storage through enhanced oil recovery, accurate forecasting of CO2 subsurface storage and cumulative oil production is essential. This study develops hybrid predictive models for the determination of CO2 storage mass and cumulative oil production in unconventional reservoirs. It does so with two multi-layer perceptron neural networks (MLPNN) and a least-squares support vector machine (LSSVM), hybridized with grey wolf optimization (GWO) and/or particle swarm optimization (PSO). Large, simulated datasets were divided into training (70%) and testing (30%) groups, with normalization applied to both groups. Mahalanobis distance identifies/eliminates outliers in the training subset only. A non-dominated sorting genetic algorithm (NSGA-II) combined with LSSVM selected seven influential features from the nine available input parameters: reservoir depth, porosity, permeability, thickness, bottom-hole pressure, area, CO2 injection rate, residual oil saturation to gas flooding, and residual oil saturation to water flooding. Predictive models were developed and tested, with performance evaluated with an overfitting index (OFI), scoring analysis, and partial dependence plots (PDP), during training and independent testing to enhance model focus and effectiveness. The LSSVM-GWO model generated the lowest root mean square error (RMSE) values (0.4052 MMT for CO2 storage and 9.7392 MMbbl for cumulative oil production) in the training group. That trained model also exhibited excellent generalization and minimal overfitting when applied to the testing group (RMSE of 0.6224 MMT for CO2 storage and 12.5143 MMbbl for cumulative oil production). PDP analysis revealed that the input features "area" and "porosity" had the most influence on the LSSVM-GWO model's prediction performance. This paper presents a new hybrid modeling approach that achieves accurate forecasting of CO2 subsurface storage and cumulative oil production. It also establishes a new standard for such forecasting, which can lead to the development of more effective and sustainable solutions for oil recovery. [ABSTRACT FROM AUTHOR]

The study of gas transport in low-permeability rocks is both practical and of significant importance to produce tight rock reservoirs. The presence of nanopores in tight rocks results in distinctly different gas transport mechanisms from those found in conventional reservoirs. Traditional Darcy's law is inadequate for describing gas flow in this context. Instead, various modes of gas transport, such as continuum flow, slip flow, transition flow, and Knudsen diffusion for bulk gas, as well as surface diffusion and adsorption/desorption for adsorbed gas, coexist within these nanopores. This paper mainly focuses on studies of gas transport in nanopores that consider apparent permeability. To begin with, the pore structure characteristics and gas seepage mechanisms in shale are introduced. An overview of the three main methods for measuring apparent permeability including laboratory experiments, numerical simulations, and analytical techniques, is provided. Mathematical models describing gas transport within nanopores are emphasized as a foundational component of apparent permeability measurements. Furthermore, the factors that influence these models are discussed. Upon analyzing the existing models, it is evident that they are diverse and numerous. While these models typically encompass multiple mechanisms and influencing factors related to gas transportation, each model has its specific limitations. Therefore, there is a continued need for the development of more comprehensive and general models. This study offers the most detailed overview of gas transport mechanisms and mathematical models in low-permeability rocks, aiming to support the evaluation and exploitation of tight rock reservoirs. [ABSTRACT FROM AUTHOR]

Due to the dissimilarity among different producing layers, the influences of inter-layer interference on the production performance of a multi-layer gas reservoir are possible. However, systematic studies of inter-layer interference for tight gas reservoirs are really limited, especially for those reservoirs in the presence of water. In this work, five types of possible inter-layer interferences, including both absence and presence of water, are identified for commingled production of tight gas reservoirs. Subsequently, a series of reservoir-scale and pore-scale numerical simulations are conducted to quantify the degree of influence of each type of interference. Consistent field evidence from the Yan'an tight gas reservoir (Ordos Basin, China) is found to support the simulation results. Additionally, suggestions are proposed to mitigate the potential inter-layer interferences. The results indicate that, in the absence of water, commingled production is favorable in two situations: when there is a difference in physical properties and when there is a difference in the pressure system of each layer. For reservoirs with a multi-pressure system, the backflow phenomenon, which significantly influences the production performance, only occurs under extreme conditions (such as very low production rates or well shut-in periods). When water is introduced into the multi-layer system, inter-layer interference becomes nearly inevitable. Perforating both the gas-rich layer and water-rich layer for commingled production is not desirable, as it can trigger water invasion from the water-rich layer into the gas-rich layer. The gas-rich layer might also be interfered with by water from the neighboring unperforated water-rich layer, where the water might break the barrier (eg weak joint surface, cement in fractures) between the two layers and migrate into the gas-rich layer. Additionally, the gas-rich layer could possibly be interfered with by water that accumulates at the bottom of the wellbore due to gravitational differentiation during shut-in operations. [ABSTRACT FROM AUTHOR]

The Shear wave (S-wave) velocity is an essential parameter in reservoir characterization and evaluation, fluid identification, and prestack inversion. However, the cost of obtaining S-wave velocities directly from dipole acoustic logging is relatively high. At the same time, conventional data-driven S-wave velocity prediction methods exhibit several limitations, such as poor accuracy and generalization of empirical formulas, inadequate exploration of logging curve patterns of traditional fully connected neural networks, and gradient explosion and gradient vanishing problems of recurrent neural networks (RNNs). In this study, we present a reliable and low-cost deep learning (DL) approach for S-wave velocity prediction from real logging data to facilitate the solution of these problems. We designed a new network sensitive to depth sequence logging data using conventional neural networks. The new network is composed of one-dimensional (1D) convolutional, bidirectional long short-term memory (BiLSTM), attention, and fully connected layers. First, the network extracts the local features of the logging curves using a 1D convolutional layer, and then extracts the long-term sequence features of the logging curves using the BiLSTM layer, while adding an attention layer behind the BiLSTM network to further highlight the features that are more significant for S-wave velocity prediction and minimize the influence of other features to improve the accuracy of S-wave velocity prediction. Afterward, the nonlinear mapping relationship between logging data and S-wave velocity is established using several fully connected layers. We applied the new network to real field data and compared its performance with three traditional methods, including a long short-term memory (LSTM) network, a back-propagation neural network (BPNN), and an empirical formula. The performance of the four methods was quantified in terms of their coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). The new network exhibited better performance and generalization ability, with R² greater than 0.95 (0.9546, 0.9752, and 0.9680, respectively), RMSE less than 57 m/s (56.29, 23.18, and 30.17 m/s, respectively), and MAE less than 35 m/s (34.68, 16.49, and 21.47 m/s, respectively) for the three wells. The test results demonstrate the efficacy of the proposed approach, which has the potential to be widely applied in real areas where S-wave velocity logging data are not available. Furthermore, the findings of this study can help for a better understanding of the superiority of deep learning schemes and attention mechanisms for logging parameter prediction. [ABSTRACT FROM AUTHOR]