Injection-production Parameters Research Articles

Global feature capture and spatially-aware neural networks for predicting CO2-flooding performance in heterogeneous low-permeable reservoirs

CO2-flooding can enhance crude oil recovery rates by reducing the viscosity of crude oil, improving the mobility ratio between crude oil and water, and leveraging the swelling effects of crude oil components. Furthermore, it facilitates the sequestration of greenhouse gases, leading to the realization of carbon capture, utilization, and storage (CCUS), which holds significant strategic importance for mitigating climate change, safeguarding ecological environments, and achieving sustainable development. Consequently, predicting CO2-flooding performance in heterogeneous low-permeability reservoirs holds crucial significance in sustainable energy production. However, the drawbacks of numerical simulation techniques, such as extensive computational resource consumption and prolonged simulation durations, have prompted extensive research into the utilization of artificial intelligence technologies. Prevalent approaches often treat the problem as a time series issue, which proves inadequate for reservoirs lacking historical production data. Furthermore, this methodology is unable to fully exploit the complex implicit relationships between various factors and the prediction target. Our study proposes a novel method for predicting the performance, which stands apart from previous approaches by not treating the problem as a time series issue, eliminating the need for historical production data for each prediction, and can predict various production variables such as gas production, oil production, water production, etc. in a universal manner. We combine enhanced MultiScale Non-local Neural Networks with ConvNet to handle sparse well network matrices with injection-production parameters. Additionally, we employ MultiScale convolutional networks with spatial attention mechanism to address formation permeability fields with spatial distribution features. Experimental results demonstrate the superiority of our approach in accuracy, achieving a prediction accuracy of over 97%. This research provides an innovative and flexible method, making significant contributions to the intelligentization and sustainable development of the petroleum industry, aligned with global efforts to both reduce carbon emissions and neutralize the existing ones.

A Review of the Utilization of CO2 as a Cushion Gas in Underground Natural Gas Storage

A cushion gas is an indispensable and the most expensive part of underground natural gas storage. Using CO2 injection to provide a cushion gas, not only can the investment in natural gas storage construction be reduced but the greenhouse effect can also be reduced. Currently, the related research about the mechanism and laws of CO2 as a cushion gas in gas storage is not sufficient. Consequently, the difference in the physical properties of CO2 and CH4, and the mixing factors between CO2 and natural gas, including the geological conditions and injection–production parameters, are comprehensively discussed. Additionally, the impact of CO2 as a cushion gas on the reservoir stability and gas storage capacity is also analyzed by comparing the current research findings. The difference in the viscosity, density, and compressibility factor between CO2 and CH4 ensures a low degree of mixing between CO2 and natural gas underground, thereby improving the recovery of CH4 in the operation process of gas storage. In the pressure range of 5 MPa–13 MPa and temperature range of 303.15 K–323.15 K, the density of CO2 increases five to eight times, while the density of natural gas only increases two to three times, and the viscosity of CO2 is more than 10 times that of CH4. The operation temperature and pressure in gas storage should be higher than the temperature and pressure in the supercritical conditions of CO2 because the diffusion ability between the gas molecules is increased in these conditions. However, the temperature and pressure have little effect on the mixing degree of CO2 and CH4 when the pressure is over the limited pressure of supercritical CO2. The CO2, with higher compressibility, can quickly replenish the energy of the gas storage facility and provide sufficient elastic energy during the natural gas production process. In addition, the physical properties of the reservoir also have a significant impact on the mixing and production of gases in gas storage facilities. The higher porosity reduces the migration speed of CO2 and CH4. However, the higher permeability promotes diffusion between gases, resulting in a higher degree of gas mixing. For a large inclination angle or thick reservoir structure, the mixed zone width of CO2 and CH4 is small under the action of gravity. An increase in the injection–production rate intensifies the mixing of CO2 and CH4. The injection of CO2 into reservoirs also induces the CO2–water–rock reactions, which improves the porosity and is beneficial in increasing the storage capacity of natural gas.

Research on Optimization of CCUS Injection Production Parameters in High-Temperature Reservoirs Based on Intelligent Optimization Algorithms

Research on Optimization of CCUS Injection Production Parameters in High-Temperature Reservoirs Based on Intelligent Optimization Algorithms

Optimization Simulation of Different Injection and Production Parameters of Enhanced Geothermal Systems

Enhanced Geothermal System (EGS), as a key technology for the extraction and utilization of geothermal energy in deep strata and high temperature rock mass, has a broad application prospect in the field of energy. In order to understand the sustainable utilization capacity of the enhanced geothermal system, explore the influence law of different factors on the heat production capacity of geothermal Wells, and design a reasonable geothermal energy development and utilization program. The influence of different injection and production parameters on thermal recovery performance was studied by numerical simulation, and the main influencing factors were analyzed by orthogonal experiment. The results show that water injection rate has the greatest effect on the injection-production parameters, followed by well spacing and water injection temperature, and fracture opening and fracture number have the least effect. The optimal parameter combination is water injection rate of 10kg/s, well spacing 500m, water injection temperature 40℃, crack opening 0.09mm and crack number 60.

Prediction of ORF for Optimized CO2 Flooding in Fractured Tight Oil Reservoirs via Machine Learning

Tight reservoirs characterized by complex physical properties pose significant challenges for extraction. CO2 flooding, as an EOR technique, offers both economic and environmental advantages. Accurate prediction of recovery rate plays a crucial role in the development of tight oil and gas reservoirs. But the recovery rate is influenced by a complex array of factors. Traditional methods are time-consuming and costly and cannot predict the recovery rate quickly and accurately, necessitating advanced multi-factor analysis-based prediction models. This study uses machine learning models to rapidly predict the recovery of CO2 flooding for tight oil reservoir development, establishes a numerical model for CO2 flooding for low-permeability tight reservoir development based on actual blocks, studies the effects of reservoir parameters, horizontal well parameters, and injection-production parameters on CO2 flooding recovery rate, and constructs a prediction model based on machine learning for the recovery. Using simulated datasets, three models, random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), were trained and tested for accuracy evaluation. Different levels of noise were added to the dataset and denoised, and the effects of data noise and denoising techniques on oil recovery factor prediction were studied. The results showed that the LightGBM model was superior to other models, with R2 values of 0.995, 0.961, 0.921, and 0.877 for predicting EOR for the original dataset, 5% noise dataset, 10% noise dataset, and 15% noise dataset, respectively. Finally, based on the optimized model, the key control factors for CO2 flooding for tight oil reservoirs to enhance oil recovery were analyzed. The novelty of this study is the development of a machine-learning-based method that can provide accurate and cost-effective ORF predictions for CO2 flooding for tight oil reservoir development, optimize the development process in a timely manner, significantly reduce the required costs, and make it a more feasible carbon utilization and EOR strategy.

Geothermal extraction performance in fractured granite from Gonghe Basin, Qinghai province, China: Long-term injection and production experiment

The efficient exploitation of geothermal energy through enhanced geothermal systems (EGS) has been a relevant topic for hot dry rock (HDR) geothermal resources. When cryogenic fluid is injected into a thermal reservoir, improving heat exchange efficiency is key to achieving the optimal exploitation of HDR. In this paper, granite outcrops from Gonghe Basin were used as the testing sample. The natural fractures in the granite samples were relatively well developed. To simulate long-term injection and production from multi-wells in situ, physical experiments were performed in a newly-developed, in-house large-scale true triaxial experimental system. Geothermal extraction performance of an HDR was simulated for long-term injection and production operations. Simultaneously, the mode of one-injection and multiple-production wells was represented. In the paper, the effects of the production-injection well spacing, the number of production wells and the injection rate on the production temperature and flow rate are discussed. The results show that, during long-term injection and production, there are two stages of production temperature variation, namely stabilization and attenuation. When the number of the production wells is increased, the heat extraction efficiency is accelerated. Moreover, competitive diversion of fluid among fractures occurred due to different conductivities. Furthermore, under different production modes, the production flow rate contributed differently to the heat extraction. Finally, the effect of the production-injection wells spacing on the heat exchange performance was analyzed; this is mainly reflected in the change of the effective heat exchange area between the rock and the injected fluid. The results emphasize the importance of designing an appropriate production mode and optimizing the injection-production parameters to ensure efficient HDR exploitation.

Experimental Study on ASP Flooding Horizontal-Vertical Joint Development

ASP flooding oil technology, as a highly concerned method for improving oil recovery in recent years, has the advantages of high oil displacement efficiency and good environmental protection. Horizontal-vertical joint development technology is a method of achieving efficient oil-field development by optimizing well network layout, adjusting injection production parameters, and other means. It improves the pressure field and flow field distribution inside the reservoir, enhances sweep efficiency and oil recovery efficiency, thereby achieving the goal of increasing crude oil recovery rate. This article aims to explore the combined application effect and mechanism of ASP flooding oil technology and horizontal-vertical joint development technology through experimental research, providing new ideas and methods for efficient development of oil fields. The joint application of ASP flooding oil technology and horizontal-vertical joint development technology provides a new approach for efficient oil-field development. This joint application can not only improve the recovery rate of crude oil, reduce development costs, but also help reduce environmental pollution and achieve the sustainability of oil-field development.

Front Movement and Sweeping Rules of CO2 Flooding under Different Oil Displacement Patterns

CO2 flooding is a pivotal technique for significantly enhancing oil recovery in low-permeability reservoirs. The movement and sweeping rules at the front of CO2 flooding play a critical role in oil recovery; yet, a comprehensive quantitative analysis remains an area in need of refinement. In this study, we developed 1-D and 2-D numerical simulation models to explore the sweeping behavior of miscible, immiscible, and partly miscible CO2 flooding patterns. The front position and movement rules of the three CO2 flooding patterns were determined. A novel approach to the contour area calculation method was introduced to quantitatively characterize the sweep coefficients, and the sweeping rules are discussed regarding the geological parameters, oil viscosity, and injection–production parameters. Furthermore, the Random Forest (RF) algorithm was employed to identify the controlling factor of the sweep coefficient, as determined through the use of out-of-bag (OOB) data permutation analysis. The results showed that the miscible front was located at the point of maximum CO2 content in the oil phase. The immiscible front occurred at the point of maximum interfacial tension near the production well. Remarkably, the immiscible front moved at a faster rate compared with the miscible front. Geological parameters, including porosity, permeability, and reservoir thickness, significantly impacted the gravity segregation effect, thereby influencing the CO2 sweep coefficient. Immiscible flooding exhibited the highest degree of gravity segregation, with a maximum gravity segregation degree (GSD) reaching 78.1. The permeability ratio was a crucial factor, with a lower limit of approximately 5.0 for reservoirs suitable for CO2 flooding. Injection–production parameters also played a pivotal role in terms of the sweep coefficient. Decreased well spacing and increased gas injection rates were found to enhance sweep coefficients by suppressing gravity segregation. Additionally, higher gas injection rates could improve the miscibility degree of partly miscible flooding from 0.69 to 1.0. Oil viscosity proved to be a significant factor influencing the sweep coefficients, with high seepage resistance due to increasing oil viscosity dominating the miscible and partly miscible flooding patterns. Conversely, gravity segregation primarily governed the sweep coefficient in immiscible flooding. In terms of controlling factors, the permeability ratio emerged as a paramount influence, with a factor importance value (FI) reaching 1.04. The findings of this study can help for a better understanding of sweeping rules of CO2 flooding and providing valuable insights for optimizing oil recovery strategies in the field applications of CO2 flooding.

Analysis of Factors Impacting CO2 Assisted Gravity Drainage in Oil Reservoirs with Bottom Water

In recent years, there has been significant focus on the issue of global carbon emissions. One of the most prominent areas of research in this regard is the use of carbon capture, utilization, and storage (CCUS) technology in the petrochemical industry. At present, the utilization of CO2 Assisted Gravity Drainage (CAGD) in oil reservoirs, particularly those containing bottom water, is considered to be in the early stages of exploration and development. In this study, a mechanistic model was built, and five key factors influencing CAGD were analyzed. These factors included the reservoir structure, CO2 injection site, initial formation pressure, reservoir thickness, and CO2 injection rate. Then, the applicable rules governing CAGD in oil reservoirs with bottom water were obtained. Finally, these rules were employed in an actual reservoir to optimize the injection-production parameters. The results of the influence factor analysis indicated that CAGD was more suitable for anticline structural reservoirs. The combined top-waist CO2 injection could fully utilize gravity differentiation in a short timeframe to expand the lateral sweep range of the CO2. CAGD was more effective when the reservoir pressure was greater than the minimum miscible pressure and the reservoir thickness was between 25–50 m. The generation of a secondary CO2 cap was favored when the CO2 injection rate was 35,000 m3/d. Results from A Oilfield applications indicated that, following the application of CAGD technology, A Oilfield experienced an increase in cumulative oil production of 15.76 × 104 t, a 10% reduction in water cut, and an amount of 82.15 × 106 m3 of CO2 that was sequestered in the subsurface. These findings can offer practical insights and guidance for the future development of CAGD techniques in similar reservoirs.

Sensitivity analysis of operation parameters of the salt cavern under long-term gas injection-production

Injection-production operation parameters, the minimum injection gas pressure (IGP: operation pressure), IGP interval, minimum IGP residence time, and injection-production cycle of the underground salt rock gas storage under long-term operation, affect not only the capacity and working ability of a salt cavern but also be crucial to the safety and stability of the surrounding rock. A 3D geo-mechanical model of the salt cavern is established to study the stability of the storage in the operation period. The deformation, expansion safety factor, volume shrinkage, and plastic zone are comprehensively considered for predicting the feasibility and stability of the salt cavern. The stability of the surrounding rock of the cavern with different injection-production parameters and the impact of each parameter on the stability of the cavern during operating are systematically investigated. The results indicate that the displacement, the expansion coefficient of the surrounding rock, and the volume shrinkage rate of the salt cavern reduces significantly with the increment of IGP interval and minimum IGP, while they increases with raising the minimum IGP residence time and injection-production cycle. With the continuous operation of the cavity, the displacement and the volume shrinkage rate enhances significantly year by year with the augment of operation parameters, moreover, their value show a fluctuating upward trend with the alternation of the gas injection and the production. The volume of the plastic zone is enlarged with the increment of the IGP interval, minimum IGP, and injection-production cycle, while it reduces with the extension of the minimum IGP residence time. The variation becomes remarkably with the augment of parameters. The sensitivity coefficients of each injection-production operation parameter are ranked, from large to small, as follows: IGP interval, minimum IGP, minimum IGP residence time, injection-production cycle. The results can offer beneficial reference for effectively optimize the injection-production parameters, so as to provide technical guidance for ensuring the stability of the storage and meeting requirements for the storage capacity.

Numerical analysis and economic evaluation of pinnate horizontal well for supercritical CO2-based enhanced geothermal system

Supercritical carbon dioxide (scCO2) is considered an alternative heat carrier for enhanced geothermal system due to its superior thermophysical property. Extensive investigations have been conducted to improve the heat extraction performance of scCO2-based EGS. However, few investigations have focused on the response mechanism of thermal reservoir for the scCO2-based EGS with fully coupled thermal-hydraulic-mechanical (THM) method. The evaluation differences between THM and TH coupling model are still not clear for the scCO2-based EGS. To further improve the heat extraction performance of scCO2-based EGS, a pinnate horizontal well (PHW) EGS is proposed in present work. Three-dimensional (3D) model with fully coupled thermal-hydraulic-mechanical (THM) is established considering the in-situ stress, which is used to evaluate the geothermal energy utilization and economic performance of PHW EGS. The effects of injection-production parameters, reservoir properties and fracture parameters on the heat extraction performance of PHW are probed. The results revealed that reservoir permeability shows a descending tendency while fracture aperture experiences a significant increase, when the effects of in-situ stress are taken into account. If the in-situ stress is ignored, the production temperature and maximum useful work will be overestimated by about 13 K and 16.4%, respectively. PHW EGS is characterized by the low pump consumption, high system efficiency and net revenue. Compared with doublet EGS, pump power is decreased by 58.1%, the system efficiency is boosted by 2.6 times, and the net revenue is increased by 35.3% at the terminal stage. It has been proved that the heat extraction performance is evidently affected by the injection flow rate and temperature of working fluid, initial reservoir permeability, initial aperture and maximum closure. Appropriate operation strategy can effectively improve the performance of PHW EGS. In addition, the optimized average electricity price, accumulative income and net revenue of PHW EGS can reach to 0.251 CNY/(kW·h), 9.27 × 108 CNY and 6.65 × 108 CNY after 40 years of operation, respectively.

Optimization Study of Injection-Production Parameters for CO2 Enhanced Oil Recovery and Storage in Low Permeability Oil Reservoirs

To address the difficulty of water injection in the late stage of developing a certain low-permeability reservoir, CO2 injection and fracturing parameter optimization were conducted. The Latin hypercube sampling and numerical simulation methods were used to study the five-spot well network model established, and evaluate the impact of injection and fracturing parameters on oil recovery and CO2 storage using a comprehensive evaluation factor of oil displacement and storage. The results show that the injection rate is the main controlling factor affecting the oil recovery and storage effect, and the optimal injection rate is 6000m3/d. There is a certain contradiction between the oil recovery and storage objectives at different stages of injection development, but after ten years of injection development, the objectives of oil recovery and storage are consistent. The optimal combination of ijection and fracturing parameters yields a recovery rate of 72.54% and a CO2 storage amount of 101635.81 tons. This paper proposes that there is a certain contradiction between the oil recovery and storage objectives at different stages and evaluates schemes with different injection development periods by constructing a comprehensive evaluation factor for oil displacement and storage, which has certain reference value for optimizing parameters in the CO2 injection development of low-permeability reservoirs.

Intelligent Optimization of Gas Flooding Based on Multi-Objective Approach for Efficient Reservoir Management

The efficient development of oil reservoirs mainly depends on the comprehensive optimization of the subsurface fluid flow process. As an intelligent analysis technique, artificial intelligence provides a novel solution to multi-objective optimization (MOO) problems. In this study, an intelligent agent model based on the Transformer framework with the assistance of the multi-objective particle swarm optimization (MOPSO) algorithm has been utilized to optimize the gas flooding injection–production parameters in a well pattern in the Middle East. Firstly, 10 types of surveillance data covering 12 years from the target reservoir were gathered to provide a data foundation for model training and analysis. The prediction performance of the Transformer model reflected its higher accuracy compared to traditional reservoir numerical simulation (RNS) and other intelligent methods. The production prediction results based on the Transformer model were 21, 12, and 4 percentage points higher than those of RNS, bagging, and the bi-directional gated recurrent unit (Bi-GRU) in terms of accuracy, and it showed similar trends in the gas–oil ratio (GOR) prediction results. Secondly, the Pareto-based MOPSO algorithm was utilized to fulfil the two contradictory objectives of maximizing oil production and minimizing GOR simultaneously. After 10,000 iterations, the optimal injection–production parameters were proposed based on the generated Pareto frontier. To validate the feasibility and superiority of the developed approach, the development effects of three injection–production schemes were predicted in the intelligent agent model. In the next 400 days of production, the cumulative oil production increased by 25.3% compared to the average distribution method and 12.7% compared to the reservoir engineering method, while GOR was reduced by 27.1% and 15.3%, respectively. The results show that MOPSO results in a strategy that more appropriately optimizes oil production and GOR compared to some previous efforts published in the literature. The injection–production parameter optimization method based on the intelligent agent model and MOPSO algorithm can help decision makers to update the conservative development strategy and improve the development effect.

Study on Enhanced Oil Recovery Mechanism of CO2 Miscible Flooding in Heterogeneous Reservoirs under Different Injection Methods.

The mechanism by which oil recovery can be enhanced by different injection methods of CO2 miscible flooding to alleviate the influence of heterogeneous reservoirs was studied to optimize the injection methods, further improving oil recovery. According to the reservoir heterogeneity characteristics of the TI oil formation group in Lunnan Oilfield, a 1 m double-layer long core was designed and prepared for four CO2 miscible displacement experiments with different injection methods. By analyzing the variation in the injection-production parameters, the displacement effects of different injection methods were compared, and the mechanism of enhanced oil recovery (EOR) was summarized. The results indicate the following. ① The displacement efficiency of the different injection methods lies in the following order. Alternate CO2-water injection, continuous CO2 flooding, cyclic CO2 flooding, and alternate CO2-hydrocarbon gas injection. ② The recovery of crude oil via CO2 miscible flooding in heterogeneous reservoirs relies on both convective diffusion and miscible mass transfer. Convective diffusion depends mainly on control of the displacement pressure differential and the plugging of preferential seepage channels in high-permeability areas, while miscible mass transfer depends mainly on the swept range of the convective diffusion and the degree of miscibility between CO2 and crude oil. ③ To improve the recovery efficiency of CO2 miscible flooding in heterogeneous reservoirs, it is necessary to choose an injection method that optimizes these two aspects.

Quantitative Analysis of Natural Gas Diffusion Characteristics in Tight Oil Reservoirs Based on Experimental and Numerical Simulation Methods.

As an important mechanism in gas injection development, the diffusion characteristics of natural gas in tight reservoirs are important in the dynamic prediction of the development effect and optimization of injection-production parameters. In this paper, a high-pressure and high-temperature oil-gas diffusion experimental device was built, which was used to study the effects of the porous medium, pressure, permeability, and fracture on oil-gas diffusion under tight reservoir conditions. Two mathematical models were used to calculate the diffusion coefficients of natural gas in bulk oil and cores. Besides, the numerical simulation model was established to study the diffusion characteristics of natural gas in gas flooding and huff-n-puff, and five diffusion coefficients were selected based on experimental results for simulation study. The remaining oil saturation of grids, the recovery of single layers, and the distribution of CH4 mole fraction in oil were analyzed based on the simulation results. The experimental results show that the diffusion process can be divided into three stages: the initial stage of instability, the diffusion stage, and the stable stage. The absence of medium, high pressure, high permeability, and the existence of fracture are beneficial to natural gas diffusion, which can also reduce the equilibrium time and increase the gas pressure drop. Furthermore, the existence of fracture is beneficial to the early diffusion of gas. The simulation results show that the diffusion coefficient has a greater influence on the oil recovery of huff-n-puff. For gas flooding and huff-n-puff, the diffusion features both perform such that a high diffusion coefficient results in a close diffusion distance, small sweep range, and low oil recovery. However, a high diffusion coefficient can achieve high oil washing efficiency near the injecting well. The study is helpful to provide theoretical guidance for natural gas injection in tight oil reservoirs.

Analysis and Application of Horizontal Well Test in Low Permeability Porous Carbonate Reservoir

Low permeability porous carbonate rocks occupy a certain proportion in the Middle East. Horizontal injection-production well pattern development is often adopted. Due to the influence of well type and wellbore, reservoir dynamic monitoring is mainly based on conventional daily measurement data, well test and pressure monitoring. Therefore, it is particularly important to combine well test interpretation with production dynamic analysis to diagnose the main control factors and production characteristics of this type of reservoir. In this paper, the point source function is used to obtain the pressure variation function of a horizontal well in infinite formation with upper and lower closed boundary. The difference between the horizontal well test curve of A reservoir and the typical horizontal well test curve is compared and analyzed, and the abnormal well test curve of horizontal wells is characterized by a linear flow phase with a slope of 1/3 or 1/4. The abnormal well test curve accounted for 33.34%. The main influencing factors are the permeability around the well and the well trajectory. By combining well test interpretation with dynamic inversion method, the correlation between well test interpretation and dynamic characteristics of horizontal wells with different characteristics is classified and clarified. The main controlling factors that affect the difference in the water injection development effect of different horizontal wells are further clarified, and provide an important reference for the adjustment of injection-production parameters and the optimal deployment of schemes.

Influence of Heterogeneous Caprock on the Safety of Carbon Sequestration and Carbon Displacement

Carbon Capture, Utilization and Storage (CCUS) is a method of burying the captured CO2 into the reservoir and displacement of crude oil from reservoirs, which considers both economy and environmental protection. At present, it is considered as an important means to deal with global climate change. To ensure the safety of the CCUS scheme, it is very important to study the invasion and migration of CO2 in different types of caprocks. In this paper, we first choose the injection-production method of fixed gas injection rate at the top of the reservoir and constant pressure oil production at the bottom. Secondly, the distribution of porosity and permeability in the caprock is designed, and four types of caprock models are established: homogeneous caprock, layered homogeneous caprock, heterogeneous caprock, and layered heterogeneous caprock. Finally, the intrusion amount and migration characteristics of CO2 in caprock of four schemes in injection-production stage and burial stage are studied, and comprehensive analysis and evaluation are made in combination with the pressure distribution of caprock. In addition, the oil recovery ratio, geological CO2 storage, and amount of CO2 intrusion in caprock under different injection-production parameters in this model are also analyzed. This study provides a scientific basis for the safe operation of CCUS and geological storage of CO2.

Prediction of Oil Saturation during Water and Gas Injection Using Controllable Convolutional Long Short-Term Memory

Oil saturation is a kind of spatiotemporal sequence that changes dynamically with time, and it is affected not only by the reservoir properties, but also by the injection–production parameters. When predicting oil saturation during water and gas injection, the influence of time, space and injection–production parameters should be considered. Aiming at this issue, a prediction method based on a controllable convolutional long short-term memory network (Ctrl-CLSTM) is proposed in this paper. The Ctrl-CLSTM is an unsupervised learning model whose input is the previous spatiotemporal sequence together with the controllable factors of corresponding moments, and the output is the sequence to be predicted. In this way, future oil saturation can be generated from the historical context. Concretely, the convolution operation is embedded into each unit to describe the interaction between temporal features and spatial structures of oil saturation, thus the Ctrl-CLSTM realizes the unified modeling of the spatiotemporal features of oil saturation. In addition, a novel control gate structure is introduced in each Ctrl-CLSTM unit to take the injection–production parameters as controllable influencing factors and establish the nonlinear relationship between oil saturation and injection–production parameters according to the coordinates of each well location. Therefore, different oil saturation prediction results can be obtained by changing the injection–production parameters. Finally, experiments on real oilfields show that the Ctrl-CLSTM comprehensively considers the influence of artificial controllable factors such as injection–production parameters, accomplishes accurate prediction of oil saturation with a structure similarity of more than 98% and is more time efficient than reservoir numerical simulation.

Performance of enhanced geothermal system with varying injection-production parameters and reservoir properties

The injection-production parameters and reservoir properties significantly affect the heat extraction performance of the enhanced geothermal system (EGS), while quantitative rankings of the effecting parameters have been yet unknown. This paper is devoted to investigating numerically the heat extraction performance of EGS by three-dimensional reservoir models under the influence of varying injection-production parameters and reservoir properties. A thermal-hydro-mechanical (THM) coupled model is used to quantify the complicated heat extraction process of EGS. Three-dimensional geothermal reservoir models containing random fracture networks are established based on the Monto Carlo algorithm to quantify the effect of fracture numbers in the process of heat extraction. The parameter sensitivity of the injection-production parameters (injection mass flow rate and injection temperature) and the reservoir properties (rock matrix porosity, fracture permeability, and rock matrix permeability) on the heat extraction performance are ranked and evaluated over the Qiabuqia enhanced geothermal system. It is found the heat extraction performance shows non-monotonic relationships with the fracture numbers in the three-dimensional reservoir model, which indicates the necessity of EGS fracture optimization. The injection mass flow rate turns out the first while the fracture permeability and injection temperature are the secondary dominating factors affecting the heat extraction performance among the evaluated parameters. The outcomes are beneficial to the high-efficiency construction, operation, and optimization of the EGS especially those with similar conditions to the Qiabuqia EGS.

Numerical Simulation and Economic Evaluation of Wellbore Self-Circulation for Heat Extraction Using Cluster Horizontal Wells

The heat extraction capacity of the self-circulation wellbore is usually small because of the limited heat exchange area. In the paper, the cluster horizontal well group technology was proposed to enhance the heat extraction capacity and decrease the unit cost. Based on the mathematical model of heat transfer, a numerical simulation model of wellbore self-circulation for heat extraction using cluster horizontal wells was established to study the influence of main factors on heat extraction capacity. The economic analysis of heat extraction and power generation was carried out according to the model of the levelized cost of energy. The results show that the enhancement of heat extraction capacity is limited after the injection rate exceeds 432 m3/d (1.59 MW/well). The inflection point of the injection rate can be determined as the design basis for injection-production parameters. When the thermal conductivity of formation increases from 2 to 3.5 W/(m·K), the heat extraction rate will increase 1.45 times, indicating that the sandstone reservoirs with good thermal conductivity can be preferred as the heat extraction site. It is recommended that the well spacing of cluster wells is larger than 50 m to avoid the phenomenon of thermal short circuit between wells, and the thermal conductivity of the tubing should be less than 0.035 W/(m·K) to reduce the heat loss of heat-carrying fluid in the tubing. Compared with a single well, a cluster horizontal well group can reduce the unit cost of heat extraction and power generation by 24.3% and 25.5%, respectively. The economy can also be improved by optimizing heat-carrying fluids and retrofitting existing wells.