Fluidized bed technology known for its efficient heat and mass transfer and controlled material handling, is widely used across industries. However, CFD simulation of fluidized beds presents challenges that require extensive validation. This study leverages the Multiphase Particle-In-Cell (MP-PIC) method, a recent Lagrangian modeling technique to improve computational efficiency and accuracy. The CAD model was developed using SolidWorks 2020 and simulation was carried out in the commercial CFD package Barracuda VR 21.1.0. The sensitivity of grid size, drag models and the impact of recirculating pipe height after loop seal was examined. Sand particles 63-200 μm and air were used as bed material and fluidization gas respectively achieving full flow circulation at 650 SL/min and 12 SL/min aeration in the riser and loop seal. A total of 19 different simulations were conducted, varying grid size and drag models each for a duration of 45 seconds with a time step of 0.0005 seconds. Pressure transducers along the CFB walls provided validation data. The Wen-Yu Ergun drag model showed a minimal error margin of 0.60%, followed by the Wen-Yu 80000 model at 0.62%, demonstrating high predictive accuracy.

Oil and gas will remain an important source of energy for years and it is crucial to improve oil recovery with less carbon footprint. Carbon capture utilization and storage offers a potential solution to mitigate the effects of anthropogenic CO2. The captured CO2 can be utilized to enhanced oil recovery (EOR) and is injected into the oil fields for storage and/or EOR. However, the injected CO2 can be reproduced without contributing to EOR. This is due to the breakthrough of CO2 into the well. Also, the corrosive mixture of CO2 and water can be produced from the production well. This may cause damages to the pipeline and process equipment on the platform. Autonomous inflow control valves (AICVs) can mitigate these problems. They may reduce or stop the reproduction of CO2 from the zones with CO2 breakthrough and reduce the production of mixture of CO2 and water. The main objective of this study is modelling and simulation of oil production in a heterogenous reservoir using CO2-EOR in combination with AICVs. The outcome of numerical simulations is analyzed to study the effect of various parameters on oil recovery. In addition, the impact of AICVs on EOR is assessed against perforated casing completion (without AICV). The results demonstrate that oil recovery factor, water cut, and cumulative gas production are better in the wells completed with AICVs than perforated casing completion. This will result into both increased oil production and a better CO2 storage potential.

The utilization of advanced multilateral wells to enhance well-reservoir contact, coupled with water injection, stands out as a common approach to boost oil extraction efficiency. It is imperative to develop precise, fully integrated, dynamic, well-reservoir models tailored for this type of oil recovery to enhance the design of advanced multilateral well completions. This study addresses the challenge by constructing a well model using OLGA®, which is, a dynamic multiphase flow simulator, and a reservoir model using EclipseTM, a reservoir simulator. Subsequently, these models are seamlessly integrated to perform comprehensive simulations. The proposed approach is tested on a case study involving oil recovery through an advanced multilateral well completed with various Flow Control Devices (FCDs) supported by water injection. Results from the simulations demonstrate the success of the integration approach, offering a reliable method for accurately modelling oil recovery from advanced multilateral wells to improve oil recovery. Notably, according to this study, wells completed with Autonomous Inflow Control Valves (AICVs) exhibit superior performance, optimizing oil recovery with a reduced carbon footprint.

Improving the efficiency of oil recovery is a crucial necessity in the current energy landscape. The widespread adoption of advanced wells, equipped with Autonomous Inflow Control Devices (AICDs), represents a leading strategy for this purpose. However, the absence of a predefined and straightforward option for modeling advanced wells in dynamic multiphase flow simulators like OLGA® poses a significant challenge. To address the issue, this paper proposes a novel approach based on developing a mathematical model derived from experimental data characterizing the AICD behavior. The Algebraic Controller option in OLGA is then leveraged to integrate the AICD effects into the simulation seamlessly. The proposed methodology undergoes rigorous testing on the PUNQ-S3 reservoir model as a benchmark case study with Water Alternating Gas (WAG) injection. Results demonstrate that AICD has a better water reduction rate of 36.3% and 3.7% compared to OPENHOLE and ICD. This result also indicates the accurate modeling and simulation of AICD performance in the software, showcasing the effectiveness of the developed mathematical model. Comparative analyses of advanced wells with different Flow Control Devices (FCDs) underscore the conclusion that AICDs significantly enhance oil recovery efficiency, thereby maximizing profit and minimizing the carbon footprint.

Circulating fluidized beds is one of the emerging technologies to convert waste to energy and an attractive method on a large scale. Key components such as the loop seal, gas distributor and cyclone separator play pivotal roles in facilitating solid recirculation and heat transfer within the system. This study focuses on the design and optimization of a CFB reactor using data derived from Barracuda Virtual Reactor software (CPFD). Initially, data from a small scale CFB reactor with main dimensions of 84 mm diameter and a loop seal diameter of 34 mm was utilized for simulation validation. By comparing simulation results with experimental data, the accuracy and reliability of the computational model were ensured. Subsequently, different reactor models were constructed and analyzed to explore various configurations and operating conditions. The results obtained from simulation based design and optimization provided valuable insights into achieving the optimal performance of the CFB system. By refining geometry, efficiency was increased by 32%. Overall, this study contributes to advancing the understanding, application and design modification of CFB technology in waste to energy conversion and large-scale industrial processes.

There has been a tendency in oil and gas industry towards the adoption of multilateral wells (MLWs) with completions that incorporate multiple types of flow control devices (FCDs). In this completion technique, passive inflow control devices (ICDs) or autonomous inflow control devices (AICDs) are positioned within the laterals, while interval control valves (ICVs) are installed at lateral junctions to regulate the overall flow from each lateral. While the outcomes observed in real field applications appear promising, the efficacy of this specific downhole completion combination has yet to undergo comparative testing against alternative completion methods that employ a singular flow control device type. Additionally, the design and current evaluations of such completions are predominantly based on analytical tools that overlook dynamic reservoir behavior, long-term production impacts, and the correlation effects among different devices. In this study, we explore the potential of integrating various types of flow control devices within multilateral wells, employing dynamic optimization process using numerical reservoir simulator while the Grey Wolf Optimizer (GWO) is used as optimization algorithm. The Egg benchmark reservoir model is utilized and developed with two dual-lateral wells. These wells serve as the foundation for implementing and testing 22 distinct completion cases considering single-type and multiple types of flow control devices under reactive and proactive management strategies. This comprehensive investigation aims to shed light on the advantages and limitations of these innovative completion methods in optimizing well and reservoir performance. Our findings revealed that the incorporation of multiple types of FCDs in multilateral well completions significantly enhance well performance and can surpass single-type completions including ICDs or AICDs. However, this enhancement depends on the type of the device implemented inside the lateral and the control strategy that is used to control the ICVs at the lateral junctions. The best performance of multiple-type FCD-based completion was achieved through combining AICDs with reactive ICVs which achieved around 75 million USD profit. This represents 42% and 22% increase in the objective function compared to single-type ICDs and AICDs installations, respectively. The optimal settings for ICD and AICD in individual applications may significantly differ from the optimal settings when combined with ICVs. This highlights a strong correlation between the different devices (control variables), proving that using either a common, simplified analytical, or a standard sequential optimization approach that do not explore this inter-dependence between devices would result in sub-optimal solutions in such completion cases. Notably, the ICV-based completion, where only ICVs are installed with lateral completion, demonstrated superior performance, particularly when ICVs are reactively controlled, resulting in an impressive 80 million USD NPV which represents 53% and 30% increase in the objective function compared to single-type ICDs and AICDs installations, respectively.

Wells equipped with flow control devices across their completion intervals have become a proven field development option for geologically complex and/or viscous oil reservoirs. Such wells increase oil recovery, reduce water and gas production, minimize the need for well workover operations, and subsequently lower the wells' carbon footprint. The uncontrolled types of inflow control devices include early-generation passive inflow control devices (ICDs) and later-generation autonomous inflow control devices (AICDs). The superior performance of AICDs over ICDs in managing water and gas production, as well as enhancing the overall well and reservoir performance has been demonstrated in multiple research and case studies. This superiority stems from the AICDs' ability to self-adjust and increase their flow resistance when undesired fluids (i.e., water and/or gas) flow through them. While ICDs lack this self-adjusting feature, they are more affordable and more readily available on the market. This study aims to reduce the performance gap between passive and autonomous inflow control devices by developing a hybrid dynamic optimization technique. This approach integrates a metaheuristic algorithm, machine learning, global sensitivity analysis, and correlation measures to facilitate the optimization problem by identifying the high-impact control variables. Next, the proposed workflow finds the necessary adjustments to the original well completion design by modifying the high-impact control variables during the optimization process. This results in a modified well completion design that is less influenced by the type of inflow control device (passive or autonomous), thereby bridging the performance gap between these two completion types. The study employs a benchmark 'Egg field' model, featuring two multilateral wells (MLWs) producing under a water flooding recovery mechanism. Two different completion designs, utilizing either ICDs or AICDs, are optimized using standard optimization (SO) and the proposed hybrid dynamic optimization techniques. The standard optimization, which employs a standalone Particle Swarm Optimization (PSO) algorithm, highlights, as expected, the superiority of the AICD-based completion, yielding an approximately 13% increase in the net present value (NPV) over the ICD-based completion. However, when applying the hybrid optimization (HO) technique, this difference is significantly reduced to 3.4%. This indicates the potential for the hybrid optimization technique to make ICD-based completions more competitive and economically favourable compared to their AICD-based counterparts.

Summary Oil production from thin-oil-rim fields can be challenging as such fields are prone to gas coning. Excessive gas production from these fields results in poor production and recovery. Hence, these resources require advanced recovery methods to improve the oil recovery. One of the recovery methods that is widely used today is advanced inflow control technology such as autonomous inflow control valve (AICV). AICV restricts the inflow of gas in the zones where breakthrough occurs and may consequently improve the recovery from thin-oil-rim fields. This paper presents a performance analysis of AICVs, passive inflow control devices (ICDs), and sand screens based on the results from experiments and simulations. Single- and multiphase-flow experiments are performed with light oil, gas, and water at typical Troll field reservoir conditions (RCs). The obtained data from the experiments are the differential pressure across the device vs. the volume flow rate for the different phases. The results from the experiments confirm the significantly better ability of the AICV to restrict the production of gas, especially at higher gas volume fractions (GVFs). Near-well oil production from a thin-oil-rim field considering sand screens, AICV, and ICD completion is modeled. In this study, the simulation model is developed using the CMG simulator/STARS module. Completion of the well with AICVs reduces the cumulative gas production by 22.5% and 26.7% compared with ICDs and sand screens, respectively. The results also show that AICVs increase the cumulative oil production by 48.7% compared with using ICDs and sand screens. The simulation results confirm that the well completed with AICVs produces at a beneficial gas/oil ratio (GOR) for a longer time compared with the cases with ICDs and sand screens. The novelty of this work is the multiphase experiments of a new AICV and the implementation of the data in the simulator. A workflow for the simulation of AICV/ICD is proposed. The simulated results, which are based on the proposed workflow, agree with the experimental AICV performance results. As it is demonstrated in this work, deploying AICV in the most challenging light oil reservoirs with high GOR can be beneficial with respect to increased production and recovery.

Oil recovery can be enhanced by maximizing the well-reservoir contact using advanced wells. The successful design of such wells requires an appropriate integrated dynamic model of the oil field, well, and production network. In this study, the model of advanced wells developed in the dynamic multiphase flow simulator OLGA® is linked to a reservoir model to develop transient fully-coupled well-reservoir models for the simulation of oil recovery through advanced wells. The obtained results from the developed models in OLGA are compared with the results from the widely used MultiSegment Well (MSW) model. Flow Control Devices (FCDs) are the key component of advanced wells and the functionality of the main types of FCDs is investigated. According to the obtained results, by employing advanced wells with an appropriate completion design, the production of unwanted fluids (water and/or gas) can be highly reduced while the oil recovery is slightly increased compared to using conventional wells. Besides, by comparing the performance of the OLGA and MSW models, it can be concluded that OLGA is a robust tool for conducting an accurate simulation of oil recovery through advanced wells. However, running such simulations with OLGA is relatively slow and may face convergence problems.

The suitable design of Advanced Multilateral Well (AMW) completions under uncertain information is challenging but crucial for achieving cost-effective and low-carbon oil recovery. This requires an accurate and fast coupled dynamic well-reservoir model. To this end, some commercial software packages are available to be used. However, using a free open-source tool like MATLAB® Reservoir Simulation Toolbox (MRST) can help oil companies to reduce costs and allows petroleum engineers to make fit-for-purpose simulation models. This paper aims at using MRST to assess the performance of AMWs in improving waterflooding oil recovery under petrophysical uncertainties. Using the MultisegmentWell class in MRST, this study develops appropriate models for the simulation of long-term oil recovery from AMWs completed with various Flow Control Devices (FCDs). Inflow Control Devices (ICDs), Autonomous Inflow Control Devices (AICDs), Autonomous Inflow Control Valves (AICVs), and Interval Control Valves (ICVs) are the main types of FCDs and are evaluated in this paper. Considering several uncertain parameters with varied distribution profiles, the Latin Hypercube Sampling (LHS) approach is applied to generate various realizations of the reservoir model for providing a confident degree of petrophysical uncertainty. The MRST simulation results are validated against the obtained results from the EclipseSM reservoir simulator, and these simulators are compared in terms of speed and accuracy. The preliminary findings demonstrated that in the waterflooding oil recovery, the production of oil is improved with an optimum design of AMWs completed with reactive FCDs (AICDs or AICVs) and proactive FCDs (ICVs) compared to employing passive FCDs (ICDs). Moreover, water production is highly reduced by using reactive and proactive FCDs than passive FCDs. Lifting and separating water is costly and carbon-intensive. Therefore, deploying AMWs with reactive and proactive FCDs is a valuable measure for achieving efficient and environmentally friendly waterflooding oil recovery. According to the preliminary results, it can also be concluded that ICV and AICV completions have better functionality than AICDs and ICD completions in mitigating the risks associated with reservoir uncertainties. Besides, the initial comparison of the MRST and Eclipse performances in the modeling and simulation of AMWs proves that MRST is a robust and computationally efficient tool for developing industry-standard simulation models.

Hydrogen is an efficient energy carrier and an important contribution to sustainable energy development. Hydrogen can be produced based on different methods and on different raw materials. Blue hydrogen is hydrogen produced from natural gas via a steam-methane reformer with subsequent carbon capture and storage. The CO2 from the process can be stored in matured oil and gas fields or in an aquifer.This paper studies the potential of producing blue hydrogen from methane from the Troll gas field on the Norwegian continental shelf. The production rate of methane from the Troll field is predicted and based on the calculated methane production the steam-methane reformation process is modelled and simulated. The model includes the required steps to convert natural gas into hydrogen and CO2 and further to catch the CO2. The volume of captured CO2 per m3 of produced hydrogen is calculated. Production of blue hydrogen also includes storage of CO2, and the required storage capacity is calculated.The purpose of this paper was to investigate whether blue hydrogen produced by natural gas from the Troll field is an alternative to reducing CO2 emissions to reach the climate target. The simulation was performed with Aspen HYSYS 12 and the calculation on how much CO2 must be stored and the storage capacity needed were performed manually. The mass of CO2 resulting from the conversion of about 2400 tons natural gas/h to blue hydrogen and CO2 at the Troll field is 5600 tons CO2/hour or 49 megatons CO2/year. The produced hydrogen had a purity of 95%. The predicted storage capacity for CO2 at the Troll field is found to be 136 megatons. A profitability analysis is performed and the results are promissing.

The demand for non-conventional oil has increased globally. Non-conventional oil is categorized as extra heavy oil and bitumen. In reservoirs with extra heavy oil and bitumen, thermal methods are used to reduce the oil viscosity. Steam assisted gravity drainage (SAGD) is a thermal recovery method to enhance the bitumen recovery. In this method, steam is injected to bitumen and heavy oil to reduce the viscosity and make the oil mobile and extractable. To obtain an efficient SAGD process, the residence time for steam in the reservoir must be long enough for the steam to condense and release the latent energy to be transferred to the cold bitumen. Early breakthrough of steam in some parts of the well will eventually limit the oil production and must be avoided. Autonomous inflow control valve (AICV) can prevent the steam breakthrough and restrict the excessive production of steam. The objective of this paper is to investigate the performance of AICV and its impacts on increased oil production in a SAGD production well. This is achieved by focusing on the implementation, and performance evaluation of inflow control devices (ICDs) and AICVs compared with standard well perforations. CMG STARS, a multi-phase, multi-component thermal reservoir simulator, is used to perform numerical simulation studies. The simulation results demonstrate the significant benefit of AICV in steam reduction compared to ICD and well perforations. The simulation results demonstrate that utilizing AICV in a SAGD reservoir will lead to higher oil production, less steam production, and a more uniform temperature distribution, and steam chamber conformance. Reduction in steam production, will improve the overall SAGD operation performance. This will also result in more cost-effective oil production, as less steam is needed to be generated for production of each barrel of oil.

Oil recovery can be enhanced by maximizing the well-reservoir contact using long horizontal wells. One of the main challenges of using such wells is the early breakthrough of unwanted fluids due to the heel-toe effect and heterogeneity along the well. To tackle this problem, advanced wells are widely applied today. The successful design of such wells requires an accurate integrated dynamic model of the well and reservoir. This paper aims at developing appropriate integrated well-reservoir models for achieving optimal long-term oil recovery from advanced well models.In this study, OLGA® which is a dynamic multiphase flow simulator is implicitly coupled to ECLIPSETM which is a dynamic reservoir simulator for developing accurate models to simulate oil production from advanced wells under various production/injection strategies. A realistic heterogeneous light oil reservoir with an advanced horizontal well is used as a case study. Flow Control Devices (FCDs) are the key component of advanced wells and the functionality of the main types of FCDs in improving the oil production, minimizing the cost and carbon footprint is investigated.According to the obtained results, by implementation of FCDs the water breakthrough time is delayed by 180 days and the cumulative water production with ICD, AICD, and AICV completions is reduced by 26.8%, 33.1%, and 49.1%, respectively, compared to the open-hole case. Besides, the results show that linking OLGA and ECLIPSE is a numerically stable and accurate approach for modeling the interaction between the dynamic reservoir and dynamic well behavior for simulation oil recovery from advanced wells.

The conversion efficiency,operation, and design of bubbling fluidizedbed (BFB) reactors depend on the bed dynamics behavior, which is significantlyinfluenced by the bubble properties. To establish the best operatingcondition for efficient conversion, this study investigates the dynamicsbehavior of a BFB reactor using experimental measurements and computationalparticle-fluid dynamics simulation. The simulations account for particlesize distribution and variation of particle properties used in theexperiments to eliminate the possible effects on the bed behavior.Compared with a cold bed of similar biomass load and gas velocity,the results show that bubbles propagate with a wider distribution,a smaller size, and a higher frequency in the hot gasifying bed. Thebubble diameter and amount of unconverted char particles increasewith increasing air flow rate at a constant air-fuel ratio.Although the solid particle distribution over the bed can be uniformwith increasing air flow rate, the temperature and gas species distributionslack uniformity due to different degrees of reactions across the bed.An increase in the air flow rate also results in a decrease in thegas residence time, thereby lowering the biomass conversion efficiencyin the bed. At the optimum gas residence time, the concentration ofhydrogen is maximum, while the concentrations of carbon dioxide andwater vapor are minimum in the product gas. For efficient biomassgasification in a bubbling bed, the superficial gas velocity, u (0), and average bubble diameter, D ( b ), over the bed are related by gD ( b )/u (0) = 3.0, where g = 9.81 m/s(2) is the gravityconstant. This proposed model can therefore be used to size BFB reactorsor set the operating gas velocity to achieve optimum gasification.

Steam assisted gravity drainage (SAGD) is an effective thermal recovery method for enhanced bitumen recovery. However, the success of SAGD operation depends on several factors. Reduction in gas and steam production is a crucial factor to achieve a successful SAGD operation. Autonomous inflow control valve (AICV) restricts the inflow of steam and/or gas in the zones where breakthrough occurs and improves recovery from SAGD operations. This can be achieved by restricting the excessive steam and/or gas production in a well that is perfectly isolated by packers. This paper presents the performance analysis of AICVs, and passive inflow control devices (ICDs) based on the results from experiments and simulations. Experiments which illustrate the performance of an orifice type ICD and AICV is presented and compared. The results confirm the significantly better ability of the AICV to restrict the production of gas and/or steam. Simulations are performed with OLGA/ROCX which provides a dynamic wellbore- reservoir model. Simulation results show that utilizing AICV in the SAGD production wells will reduce the gas and steam production by 74% after 365 days of production. The results confirmed the significant benefit of AICV in steam and/or gas reduction and consequently increased oil production. Reduction in steam production will improve the overall SAGD operation performance. This will also result in more cost-effective oil production. In addition, the annular flow in a well completed by inflow controllers was studied by using OLGA and NETool. Almost all the reservoir simulators calculate the multiphase flow properties in annulus with no-slip. This study was an attempt to initiate discussions and provide an insight into a fundamental problem that almost all the reservoir simulators are dealing with.

CO2 flooding is a proven method to mobilize the immobile oil in the reservoirs for enhanced oil recovery (EOR). Using CO2 for EOR has been commercially used for several decades in onshore and offshore oil fields in North America, Canada, and Brazil. The injection of CO2 will both improve oil recovery and contribute significantly to reduction of greenhouse gas emissions. Breakthrough and direct reproduction of CO2, and production of corrosive carbonated water are among the challenges with CO2 EOR projects. Breakthrough of CO2 leads to poor distribution of CO2 in the reservoir and low CO2 storage. Carbonated water production results in corrosion of process equipment on the platform. Autonomous inflow control valve (AICV) is capable of autonomously restricting the reproduction of CO2 from the zones with CO2 breakthrough, and at the same time produce oil from the other zones with high oil saturation. In addition, AICV can reduce the production of carbonated water. The objective of this paper is to investigate the impact of AICV on oil production in a heterogeneous reservoir where CO2 is injected for EOR. The AICV performance is simulated with a dynamic reservoir simulator in a CO2 EOR oil reservoir. AICV restricts the inflow of unwanted fluids such as pure water, gas, carbonated water, and pure CO2. To achieve the objective, experiments and simulations are conducted. Experiments are carried out with realistic reservoir fluids to generate single phase flow performance curves for AICV and for an orifice type inflow control device (ICD). Simulations are performed using CMG STARS, which is a multi-phase, multi-component reservoir simulator. The performance of AICV is evaluated and compared with perforated casing completion. The experimental results confirm the significant benefit of AICV regarding water and CO2 reduction compared to ICD. Under the same conditions and at a given differential pressure, AICV compared to ICD, reduces the water and CO2 volume flow rate by approximately 58% and 82%, respectively. Experimental AICV performance curves are used to generate the flow control device (FCD) tables in CMG STARS. The FCD tables are used to simulate the AICV behavior. The simulation results indicate that AICV reduces the water cut significantly. The cumulative water production is reduced by approximately 25% by using AICVs compared to the perforated casing completion. Indeed, reduction in carbonated water production will minimize the recirculation of CO2. Also, reduction in production of carbonated water will mitigate the problem related to the corrosion of the producing wells and process equipment on the platform. In addition, simulation results show that the AICV completion delivers the highest cumulative oil production after five years of production. From the environmental aspects, utilizing AICV in CO2 EOR projects will contribute significantly to reduction of greenhouse gas emissions. A better distribution of CO2 in the reservoir contributes to a larger storage capacity and thereby more CO2 storage.

Circulating fluidized bed (CFB) technology has diverse applications from process industry to energy generation. Experimental studies were performed in a CFB to analyse the effect of loopseal aeration for the rate of particle circulation, which is a crucial process parameter. The experimental data were used to re-evaluate the performance of optimized particle modeling parameters in computational particle fluid dynamic (CPFD) simulations. Two sand particle sizes of 850–1000 μm and 1000–1180 μm were used in the experiments with varying loopseal aeration. The experiments could conclude that the rate of circulation is possible to improve greatly by slight reduction of the particle size. The aeration at the standpipe of the loopseal showed a higher contribution for the circulation than bottom aeration. CPFD simulations could capture exact rate of particle circulation and the core-annulus structure in the riser section. Subsequently, the duly validated CPFD model was used to analyse the particle residence time, effects of particle inventory and the riser aeration.

The petroleum industry operates under great uncertainty. Achieving an efficient approach to quantify uncertainty in oil production models is of key importance in supporting decision-makers to find suitable strategies for mitigating risks and maximizing profit. Uncertainty quantification is commonly performed based on the Monte Carlo approach and this is a very time-consuming process by using the physics-based models developed by reservoir simulators. To solve this challenge, data-driven proxy models which are less complex and computationally efficient can be used as an alternative. This paper aims to investigate the functionality of the ANN method in developing proxy models for uncertainty quantification of oil production from advanced wells. The investigation is conducted through a case study for uncertainty assessment of cumulative oil and water productions from a long horizontal well with ICD completion and zonal isolation in a synthetic reservoir for 10 years. In this study, the Eclipse® reservoir simulator is used for developing the base case model and it is coupled with MATLAB® for generating the required data sets to train and test the ANN proxy model. According to the obtained results, the trained and developed ANN proxy model can predict the production of oil and water from advanced wells accurately with a mean error of less than 4%. Besides, the proxy model is 150 times faster than the Eclipse model and can solve the challenge of the time-consuming process of uncertainty quantification.

In order to improve the design of advanced wells, the performance of such wells needs to be carefully assessed by taking the reservoir uncertainties into account. This research aimed to develop data-driven proxy models for the simulation and assessment of oil recovery through advanced wells under uncertainty. An artificial neural network (ANN) was employed to create accurate and computationally efficient proxy models as an alternative to physics-based integrated well–reservoir models created by the Eclipse® reservoir simulator. The simulation speed and accuracy of the data-driven proxy models compared to physic-driven models were then evaluated. The evaluation showed that while the developed proxy models are 350 times faster, they can predict the production of oil and unwanted fluids through advanced wells with a mean error of less than 1% and 4%, respectively. As a result, the data-driven proxy models can be considered an efficient tool for uncertainty analysis where several simulations need to be performed to cover all possible scenarios. In this study, the developed proxy models were applied for uncertainty quantification of oil recovery from advanced wells completed with different types of downhole flow control devices (FCDs). According to the obtained results, compared to other types of well completion design, advanced wells completed with autonomous inflow control valve (AICV) technology have the best performance in limiting the production of unwanted fluids and are able to reduce the associated risk by 91%.