scholarly journals Smart Proxy Modeling of a Fractured Reservoir Model for Production Optimization: Implementation of Metaheuristic Algorithm and Probabilistic Application

2021 ◽  
Vol 30 (3) ◽  
pp. 2431-2462
Author(s):  
Cuthbert Shang Wui Ng ◽  
Ashkan Jahanbani Ghahfarokhi ◽  
Menad Nait Amar ◽  
Ole Torsæter
Keyword(s):  
Fractured Reservoirs ◽  
Predictive Performance ◽  
Production Optimization ◽  
Reservoir Modeling ◽  
Computational Time ◽  
Fractured Reservoir ◽  
Temporal Database ◽  
Reservoir Model ◽  
Permeability Model ◽  
Proxy Modeling

AbstractNumerical reservoir simulation has been recognized as one of the most frequently used aids in reservoir management. Despite having high calculability performance, it presents an acute shortcoming, namely the long computational time induced by the complexities of reservoir models. This situation applies aptly in the modeling of fractured reservoirs because these reservoirs are strongly heterogeneous. Therefore, the domains of artificial intelligence and machine learning (ML) were used to alleviate this computational challenge by creating a new class of reservoir modeling, namely smart proxy modeling (SPM). SPM is a ML approach that requires a spatio-temporal database extracted from the numerical simulation to be built. In this study, we demonstrate the procedures of SPM based on a synthetic fractured reservoir model, which is a representation of dual-porosity dual-permeability model. The applied ML technique for SPM is artificial neural network. We then present the application of the smart proxies in production optimization to illustrate its practicality. Apart from applying the backpropagation algorithms, we implemented particle swarm optimization (PSO), which is one of the metaheuristic algorithms, to build the SPM. We also propose an additional procedure in SPM by integrating the probabilistic application to examine the overall performance of the smart proxies. In this work, we inferred that the PSO had a higher chance to improve the reliability of smart proxies with excellent training results and predictive performance compared with the considered backpropagation approaches.

Fractured-Reservoir Modeling and Interpretation

SPE Journal ◽  
2015 ◽  
Vol 20 (05) ◽  
pp. 983-1004 ◽  
Author(s):  
Fikri Kuchuk ◽  
Denis Biryukov ◽  
Tony Fitzpatrick
Keyword(s):  
Fractured Reservoirs ◽  
Transient Behavior ◽  
Discrete Distributions ◽  
Dual Porosity ◽  
Fractured Reservoir ◽  
Well Test ◽  
Reservoir Model ◽  
Pressure Transient ◽  
Matrix Block ◽  
Naturally Fractured

Summary Fractures are common features of many well-known reservoirs. Naturally fractured reservoirs (NFRs) consist of fractures in igneous, metamorphic, and sedimentary rocks (matrix). Faults in many naturally fractured carbonate reservoirs often have high-permeability zones and are connected to numerous fractures with varying conductivities. In many NFRs, faults and fractures frequently have discrete distributions rather than connected-fracture networks. Because faulting often creates fractures, faults and fractures should be modeled together. Accurately modeling NFR pressure-transient behavior is important in hydrogeology, the earth sciences, and petroleum engineering, including groundwater contamination to shale gas and oil reservoirs. For more than 50 years, conventional dual-porosity-type models, which do not include any fractures, have been used for modeling fluid flow in NFRs and aquifers. They have been continuously modified to add unphysical matrix-block properties such as matrix skin factor. In general, fractured reservoirs are heterogeneous at different length scales. It is clear that even with millions of gridblocks, numerical models may not be capable of accurately simulating the pressure-transient behavior of continuously and discretely NFRs containing variable-conductivity fractures. The conventional dual-porosity-type models are obviously an oversimplification; their serious limitations for interpreting well-test data from NFRs are discussed in detail. These models do not include wellbore-intersecting fractures, even though they dominate the pressure behavior of NFRs for a considerable length of testing time. Fracture conductivities of unity to infinity dominate transient behavior of both continuously and discretely fractured reservoirs, but again, dual-porosity models do not contain any fractures. Our fractured-reservoir model is capable of treating thousands of fractures that are periodically or arbitrarily distributed with finite- and/or infinite conductivities, different lengths, densities, and orientations. Appropriate inner-boundary conditions are used to account for wellbore-intersecting fractures and direct wellbore contributions to production. Wellbore-storage and skin effects in bounded and unbounded systems are included in the model. Three types of damaged-skin factors that may exist in wellbore-intersecting fracture(s) are specified. With this highly accurate model, the pressure-transient behavior of conventional dual-porosity-type models are investigated, and their limitations and range of applicability are identified. The behavior of the triple-porosity models is also investigated. It is very unlikely that triple-porosity behavior is caused by the local variability of matrix properties at the microscopic level. Rather, it is caused by the spatial variability of conductivity, length, density, and orientation of the fracture distributions. Finally, we have presented an interpretation of a field-buildup-test example from an NFR by use of both conventional dual-porosity models and our fractured-reservoir model. A substantial part of this paper is a review and discussion of the earlier work on NFRs, including the authors’ work.

scholarly journals A Methodological Framework to Discover Pharmacogenomic Interactions Based on Random Forests

Genes ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 933
Author(s):  
Salvatore Fasola ◽  
Giovanna Cilluffo ◽  
Laura Montalbano ◽  
Velia Malizia ◽  
Giuliana Ferrante ◽  
...  
Keyword(s):  
Random Forests ◽  
Cancer Cell Line ◽  
Predictive Performance ◽  
Computational Time ◽  
Gene Interactions ◽  
Methodological Framework ◽  
Concordance Correlation ◽  
Driver Genes ◽  
Tumor Tissues ◽  
Gene Alterations

The identification of genomic alterations in tumor tissues, including somatic mutations, deletions, and gene amplifications, produces large amounts of data, which can be correlated with a diversity of therapeutic responses. We aimed to provide a methodological framework to discover pharmacogenomic interactions based on Random Forests. We matched two databases from the Cancer Cell Line Encyclopaedia (CCLE) project, and the Genomics of Drug Sensitivity in Cancer (GDSC) project. For a total of 648 shared cell lines, we considered 48,270 gene alterations from CCLE as input features and the area under the dose-response curve (AUC) for 265 drugs from GDSC as the outcomes. A three-step reduction to 501 alterations was performed, selecting known driver genes and excluding very frequent/infrequent alterations and redundant ones. For each model, we used the concordance correlation coefficient (CCC) for assessing the predictive performance, and permutation importance for assessing the contribution of each alteration. In a reasonable computational time (56 min), we identified 12 compounds whose response was at least fairly sensitive (CCC > 20) to the alteration profiles. Some diversities were found in the sets of influential alterations, providing clues to discover significant drug-gene interactions. The proposed methodological framework can be helpful for mining pharmacogenomic interactions.

Forecasting the Water Flooding for the Production Wells of a Gas Condensate Field with a Fractured Reservoir Type

2021 ◽  
Author(s):  
Pavel Dmitrievich Gladkov ◽  
Anastasiia Vladimirovna Zheltikova
Keyword(s):  
Produced Water ◽  
Fractured Reservoirs ◽  
Gas Condensate ◽  
Water Flooding ◽  
Fractured Reservoir ◽  
Well Performance ◽  
Integrated Monitoring ◽  
Field Development ◽  
Water Gas ◽  
Gas Ratio

Abstract As is known, fractured reservoirs compared to conventional reservoirs have such features as complex pore volume structure, high heterogeneity of the porosity and permeability properties etc. Apart from this, the productivity of a specific well is defined above all by the number of natural fractures penetrated by the wellbore and their properties. Development of fractured reservoirs is associated with a number of issues, one of which is related to uneven and accelerated water flooding due to water breakthrough through fractures to the wellbores, for this reason it becomes difficult to forecast the well performance. Under conditions of lack of information on the reservoir structure and aquifer activity, the 3D digital models of the field generated using the hydrodynamic simulators may feature insufficient predictive capability. However, forecasting of breakthroughs is important in terms of generating reliable HC and water production profiles and decision-making on reservoir management and field facilities for produced water treatment. Identification of possible sources of water flooding and planning of individual parameters of production well operation for the purpose of extending the water-free operation period play significant role in the development of these reservoirs. The purpose of this study is to describe the results of the hydrochemical monitoring to forecast the water flooding of the wells that penetrated a fractured reservoir on the example of a gas condensate field in Bolivia. The study contains data on the field development status and associated difficulties and uncertainties. The initial data were results of monthly analyses of the produced water and the water-gas ratio dynamics that were analyzed and compared to the data on the analogue fields. The data analysis demonstrated that first signs of water flooding for the wells of the field under study may be diagnosed through the monitoring of the produced water mineralization - the water-gas ratio (WGR) increase is preceded by the mineralization increase that may be observed approximately a month earlier. However, the data on the analogue fields shows that this period may be longer – from few months to two years. Thus, the hydrochemical method within integrated monitoring of development of a field with a fractured reservoir could be one of the efficient methods to timely adjust the well operation parameters and may extend the water-free period of its operation.

Pressure-Transient Tests and Flow Regimes in Fractured Reservoirs

2015 ◽  
Vol 18 (02) ◽  
pp. 187-204 ◽  
Author(s):  
Fikri Kuchuk ◽  
Denis Biryukov
Keyword(s):  
History Matching ◽  
Fractured Reservoirs ◽  
Flow Regimes ◽  
Naturally Fractured Reservoirs ◽  
Dual Porosity ◽  
Hydraulic Fractures ◽  
Fractured Reservoir ◽  
Pressure Transient ◽  
Matrix Block ◽  
Naturally Fractured

Summary Fractures are common features in many well-known reservoirs. Naturally fractured reservoirs include fractured igneous, metamorphic, and sedimentary rocks (matrix). Faults in many naturally fractured carbonate reservoirs often have high-permeability zones, and are connected to numerous fractures that have varying conductivities. Furthermore, in many naturally fractured reservoirs, faults and fractures can be discrete (rather than connected-network dual-porosity systems). In this paper, we investigate the pressure-transient behavior of continuously and discretely naturally fractured reservoirs with semianalytical solutions. These fractured reservoirs can contain periodically or arbitrarily distributed finite- and/or infinite-conductivity fractures with different lengths and orientations. Unlike the single-derivative shape of the Warren and Root (1963) model, fractured reservoirs exhibit diverse pressure behaviors as well as more than 10 flow regimes. There are seven important factors that dominate the pressure-transient test as well as flow-regime behaviors of fractured reservoirs: (1) fractures intersect the wellbore parallel to its axis, with a dipping angle of 90° (vertical fractures), including hydraulic fractures; (2) fractures intersect the wellbore with dipping angles from 0° to less than 90°; (3) fractures are in the vicinity of the wellbore; (4) fractures have extremely high or low fracture and fault conductivities; (5) fractures have various sizes and distributions; (6) fractures have high and low matrix block permeabilities; and (7) fractures are damaged (skin zone) as a result of drilling and completion operations and fluids. All flow regimes associated with these factors are shown for a number of continuously and discretely fractured reservoirs with different well and fracture configurations. For a few cases, these flow regimes were compared with those from the field data. We performed history matching of the pressure-transient data generated from our discretely and continuously fractured reservoir models with the Warren and Root (1963) dual-porosity-type models, and it is shown that they yield incorrect reservoir parameters.

INTEGRATED TECHNOLOGY OF BROWN FIELD STUDY TO INCREASE PRODUCTION AND OIL RECOVERY

2020 ◽  
pp. 61-66
Author(s):  
I.A. Zhdanov ◽  
E.S. Pakhomov ◽  
A.M. Aslanyan ◽  
R.R. Farakhova ◽  
D.N. Gulyaev ◽  
...  
Keyword(s):  
Oil Recovery ◽  
Field Studies ◽  
Development Planning ◽  
Reservoir Modeling ◽  
Integrated Analysis ◽  
Well Testing ◽  
Reservoir Model ◽  
Scenario Development ◽  
Sweep Efficiency ◽  
High Level

Paper presents the results of integrated analysis of historically available data and additional field studies at the brown field. The results of the analysis increase the reliability of the geological and hydrodynamic reservoir model, current recovery and identification of areas, which are most promising for production enhancement operations for production increase and recovery increase. The integrated analysis of available data includes such tools as prelaminar data analysis of production and pressure changes (Prime) for high level reserves localization, multiwell retrospective testing (MRT) and pulsecode testing (PCT) for evaluation of reservoir geology, sweep efficiency and current reservoir saturation, geological and hydrodynamic reservoir modeling including petrofacies and model adaptation to the production logging, MRT, PCT and well-testing findings, multi-scenario development planning (MSDP) for the most economically profitable operations recommendation and supervision of their implementation. MSDP is based on the usage by several teams of reservoir engineers web-facility PloyPlan, which automatically translates the field activities (like drilling, workover, conversion, surveillance, etc.) into the model runs and reverts back with production and surveillance results and financial statements, based on which it is easy to choose the most profitable field operations. Up to today Prime analysis, field studies and reservoir model calibration on their results are finished.

An Integrated Approach for History Matching of Multiscale-Fracture Reservoirs

SPE Journal ◽  
2019 ◽  
Vol 24 (04) ◽  
pp. 1508-1525
Author(s):  
Mengbi Yao ◽  
Haibin Chang ◽  
Xiang Li ◽  
Dongxiao Zhang
Keyword(s):  
History Matching ◽  
Large Scale ◽  
Fractured Reservoirs ◽  
Integrated Approach ◽  
Small Scale ◽  
Gaussian Field ◽  
Limited Information ◽  
Fractured Reservoir ◽  
Discrete Fracture Model ◽  
Single Scale

Summary Naturally or hydraulically fractured reservoirs usually contain fractures at various scales. Among these fractures, large-scale fractures might strongly affect fluid flow, making them essential for production behavior. Areas with densely populated small-scale fractures might also affect the flow capacity of the region and contribute to production. However, because of limited information, locating each small-scale fracture individually is impossible. The coexistence of different fracture scales also constitutes a great challenge for history matching. In this work, an integrated approach is proposed to inverse model multiscale fractures hierarchically using dynamic production data. In the proposed method, a hybrid of an embedded discrete fracture model (EDFM) and a dual-porosity/dual-permeability (DPDP) model is devised to parameterize multiscale fractures. The large-scale fractures are explicitly modeled by EDFM with Hough-transform-based parameterization to maintain their geometrical details. For the area with densely populated small-scale fractures, a truncated Gaussian field is applied to capture its spatial distribution, and then the DPDP model is used to model this fracture area. After the parameterization, an iterative history-matching method is used to inversely model the flow in a fractured reservoir. Several synthetic cases, including one case with single-scale fractures and three cases with multiscale fractures, are designed to test the performance of the proposed approach.

A Simplified and Efficient Method for Water Flooding Production Index Calculations in Low Permeable Fractured Reservoir

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Shun Liu ◽  
Liming Zhang ◽  
Kai Zhang ◽  
Jianren Zhou ◽  
Heng He ◽  
...  
Keyword(s):  
Fractured Reservoirs ◽  
Water Injection ◽  
Cross Flow ◽  
Production Performance ◽  
Water Flooding ◽  
Simplified Model ◽  
Single Fracture ◽  
Fractured Reservoir ◽  
Production Index ◽  
Future Production

Presently, predicting the production performance of fractured reservoirs is often challenging because of the following two factors: one factor such as complicatedly connected and random distribution nature of the fractures and the other factor includes the limitations of the understanding of reservoir geology, deficient fracture-related research, and defective simulators. To overcome the difficulties of simulating and predicting fractured reservoir under complex circumstances of cross flow, a simplified model, which assumes cross flow only exists in the oil phase segment, is constructed. In the model, the pressure distribution of a single fracture can be described by solving an analytical mathematical model. In addition, due to research and field experience which indicate that cross flow also exists in the mixed-phase segment after water injection, the simplified model is modified to consider cross flow in the whole phase. The model constructed here is applicable for fractured reservoirs especially for a low-permeability fracture reservoir, and it moderately predicts future production index. By using iterative methods, the solution to the model can be feasibly obtained and related production performance index formulas can be derived explicitly. A case study was performed to test the model, and the results prove that it is good.

scholarly journals Evaluation of an uncertainty reduction methodology based on Iterative Sensitivity Analysis (ISA) applied to naturally fractured reservoirs

2019 ◽  
Vol 74 ◽  
pp. 40 ◽  
Author(s):  
Luís Augusto Nagasaki Costa ◽  
Célio Maschio ◽  
Denis José Schiozer
Keyword(s):  
Sensitivity Analysis ◽  
History Matching ◽  
Flow Behavior ◽  
Fractured Reservoirs ◽  
Search Space ◽  
Naturally Fractured Reservoirs ◽  
Reservoir Modeling ◽  
Naturally Fractured ◽  
Geostatistical Techniques

History matching for naturally fractured reservoirs is challenging because of the complexity of flow behavior in the fracture-matrix combination. Calibrating these models in a history-matching procedure normally requires integration with geostatistical techniques (Big Loop, where the history matching is integrated to reservoir modeling) for proper model characterization. In problems involving complex reservoir models, it is common to apply techniques such as sensitivity analysis to evaluate and identify most influential attributes to focus the efforts on what most impact the response. Conventional Sensitivity Analysis (CSA), in which a subset of attributes is fixed at a unique value, may over-reduce the search space so that it might not be properly explored. An alternative is an Iterative Sensitivity Analysis (ISA), in which CSA is applied multiple times throughout the iterations. ISA follows three main steps: (a) CSA identifies Group i of influential attributes (i = 1, 2, 3, …, n); (b) reduce uncertainty of Group i, with other attributes with fixed values; and (c) return to step (a) and repeat the process. Conducting CSA multiple times allows the identification of influential attributes hidden by the high uncertainty of the most influential attributes. In this work, we assess three methods: Method 1 – ISA, Method 2 – CSA, and Method 3 – without sensitivity analysis, i.e., varying all uncertain attributes (larger searching space). Results showed that the number of simulation runs for Method 1 dropped 24% compared to Method 3 and 12% to Method 2 to reach a similar matching quality of acceptable models. In other words, Method 1 reached a similar quality of results with fewer simulations. Therefore, ISA can perform as good as CSA demanding fewer simulations. All three methods identified the same five most influential attributes of the initial 18. Even with many uncertain attributes, only a small percentage is responsible for most of the variability of responses. Also, their identification is essential for efficient history matching. For the case presented in this work, few fracture attributes were responsible for most of the variability of the responses.

Sign in / Sign up

Export Citation Format

Share Document