Modeling, History Matching, Forecasting and Analysis of Shale Reservoirs Performance Using Artificial Intelligence

Mohaghegh, Shahab D.; Grujic, Ognjen; Zargari, Saeed; Dahaghi, Amirmasoud Kalantari

doi:10.2118/143875-ms

Cited by 25 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that ITSPM is able to bring out the hidden information about the reservoir characteristics and its behavior, which is embedded within the production and field data. This technology has been incorporated in the top-down, intelligent-reservoir-modeling workflow that has been referenced extensively in this manuscript (Mohaghegh et al 2005;Mohaghegh 2009;Gomez et al 2009;Mohaghegh et al 2011). Geostatistic methods provide a full-field perception of the geological characteristics used in developing the fieldwide model.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Intelligent Production Modeling Using Full Field Pattern Recognition

Khazaeni

Mohaghegh

2011

SPE Reservoir Evaluation &Amp; Engineering

View full text Add to dashboard Cite

Production-data analysis has been applied extensively to predicting future production performance and field recovery. These applications operate mostly on a single-well basis. This paper presents a new approach to production-data analysis using artificial-intelligence (AI) techniques in which production history is used to build a fieldwide performance-prediction model. In this work, AI and data-driven modeling are used to predict future production of both synthetic-(for validation purposes) and real-field cases.In the approach presented in this article, production history is paired with field geological information to build data sets containing the spatio-temporal dependencies among different wells. These dependencies are addressed by compiling information from closest offset wells (COWs) that includes their geological and reservoir characteristics (spatial data) as well as their production history (temporal data).Once the data set is assembled, a series of neural networks are trained using a back-propagation algorithm. These networks are then fused together to form the intelligent time-successive production-modeling (ITSPM) system. This technique uses only the widely available measured data such as well logs and production history of existing wells to predict future performance of the existing wells and production performance of the new (infill) wells. To demonstrate the applicability of this method, a synthetic oil reservoir is modeled using a commercial simulator. Production and well-log data are extracted into an all-inclusive data set. Several neural networks are trained and validated to predict different stages of the production. The ITSPM method is used to estimate the production profile for nine new wells in the reservoir. Furthermore, ITSPM is also applied to two giant oil fields in the Middle East. The first one has more than 200 wells and 40 years of production history. ITSPM's production predictions of the four newest wells in this reservoir are compared with their actual production. The second real field has hundreds of wells producing from multiple layers. The field has undergone waterflooding for almost its whole life. This case also shows the capabilities of this technique in more-complex scenarios and especially multiphase systems. Production-Data-Analysis BackgroundMature fields that have been producing for a long time do not provide much reservoir-characterization data. This is because of their age and the lack of historical data from their old wells. In the time that oil price might not be in its highest range, infill-drilling decisions should be made with a better degree of understanding from such fields in order to have an economically better decision.Using production data as a tool in decision making has been an interest of petroleum engineers for many years. Different methods

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Intelligent Production Modeling Using Full Field Pattern Recognition

Khazaeni

Mohaghegh

2011

SPE Reservoir Evaluation &Amp; Engineering

View full text Add to dashboard Cite

show abstract

“…Simulator history matching usually uses a detailed geological model, relative permeability curves, and PVT data, and it adjusts permeability, porosity, and saturation. It is also possible to do probabilistic rate-transient analysis with numerical and analytical models that can account for uncertainty in the reservoir properties (Anderson and Liang 2011;Mohaghegh et al 2011;Chaudhri 2012;Olorode et al 2012;Souza et al 2012).…”

Section: Background and Related Literaturementioning

confidence: 99%

“…As another example, a general limitation of AI-based data-analysis methods is that they need large amounts of data. For example, Mohaghegh et al (2011) reports that fullfield analyses with a combination of fuzzy logic and neural networks require data for 35 to 40 wells with 5 years of production history. Moreover, the training of neural-network-based models remains a task that often needs a significant investment of time and effort.…”

Section: Background and Related Literaturementioning

confidence: 99%

Analysis of Production History for Unconventional Gas Reservoirs With Statistical Methods

Bhattacharya

Nikolaou

2013

SPE Journal

View full text Add to dashboard Cite

Unconventional gas resources have dramatically changed the future energy landscape. Developing these resources involves substantial risk. Such risk can be mitigated if information gathered at initial stages of the development of a field is used efficiently and effectively to guide future development. A variety of tools-such as decline-curve analysis (DCA), type-curve analysis, simulator history matching, and artificial intelligence (AI)-is used to that effect. These tools accomplish partially overlapping but different tasks. Additional tools that could not only facilitate the analysis of historical data but also guide future development would be of value. In this work, we propose an efficient methodology that can use historical production data from existing wells to answer questions such as the following: Which wells will behave similarly? Which wells will behave differently from each other or from standard expectations? Which factors will contribute to these differences? How can data from existing wells be used to anticipate the performance of new wells? The proposed methodology relies on standard principal-component analysis (PCA) and principal-component regression (PCR). The application of PCA to historical production data from twelve wells in the Holly Branch field quickly identified wells with distinct behavior. The subsequent investigation of pressure and the completion data for these wells revealed reasons for such distinct behavior. Finally, a simple linear model was built with PCR, with good ability to predict production from new wells, as assessed through cross-validation. The value of the efficiency offered by the proposed methodology would be much higher for larger data sets, for which manual analysis of production data is more cumbersome.

show abstract

“…Both industry and academia have already presented feasible numerical-simulation techniques and work flows for characterizing and simulating unconventional reservoirs. For example, fractures can be modelled explicitly (KAPPA 2015;Karimi-Fard et al 2003;Mirzaei and Cipolla 2012;Olorode et al 2012;Patzek et al 2014;Sun and Schechter 2014) as individual fractures; or upscaled and modelled by use of the dual-porosity/permeability approach (Yan et al 2013); or considered as embedded fractures (Moinfar et al 2011); or roughly modelled with fast-marching approaches (Xie et al 2015). Besides, field-production data have been incorporated into several numerical techniques such as decline-curve analysis, artificial intelligence, and data mining (Fuentes-Cruz et al 2014;Gong et al 2014;Mohaghegh et al 2011).…”

Section: Introductionmentioning

confidence: 99%

Investigating the Effect of Improved Fracture Conductivity on Production Performance of Hydraulically Fractured Wells: Field-Case Studies and Numerical Simulations

Sun

Schechter

2015

Journal of Canadian Petroleum Technology

View full text Add to dashboard Cite

Unconventional reservoirs require extensive hydraulic-fracturing treatments to produce fluids economically and efficiently. The main purpose of such treatments is to create complex fracture networks with high-conductivity paths deeper into the nonstimulated reservoir regions. Proppants play an important role in maintaining good-quality fracture conductivities, which then greatly affect long-term production performance. In addition, research on proppants has shown a reduction in conductivities under downhole stresses and multiphase-flow behaviours. Therefore, it is important to study the effect different proppants and conductivities have on production performance through actual field cases.To evaluate the production performance of wells completed with different proppants, the authors proposed an integrated work flow for characterization and simulation of unconventional reservoirs. This work flow is unique because of the stochastic fracturenetwork-generation algorithms and improved unstructured-gridgeneration techniques. Both analysis of field-production data and numerical simulations were performed on eight wells in the CAPA field of North Dakota. For the field-data analysis, three public-data resources were reviewed to prepare a summary of reservoir properties, fracture properties, proppant properties, and production history. For the numerical simulations, all the wells were modelled and simulated with the proposed work flow. Finally, sensitivity analyses were carried out to investigate the effects of fracture conductivities and natural fractures.After completing the field-case studies and reservoir simulations, it was concluded that with the same fracture design, higher fracture conductivity improves production performance. Pumping a smaller volume of upgraded proppants with higher conductivity not only improves long-term production performance, but also justifies the additional costs and reduces the overall operation time of the entire hydraulic-fracturing job. The stimulated reservoir volume was greatly increased, as was the production performance, where natural fractures exist.In this paper, field-data analysis was applied in the Bakken to demonstrate the integrated unconventional work flow. The proposed unstructured-gridding algorithms can be incorporated into any preprocessor to handle complex networks. Reservoir, fracture, and proppant characterization and reservoir simulation of the field cases can help engineers prepare and interpret simulation input and output.

show abstract

Modeling, History Matching, Forecasting and Analysis of Shale Reservoirs Performance Using Artificial Intelligence

Cited by 25 publications

References 8 publications

Intelligent Production Modeling Using Full Field Pattern Recognition

Intelligent Production Modeling Using Full Field Pattern Recognition

Analysis of Production History for Unconventional Gas Reservoirs With Statistical Methods

Investigating the Effect of Improved Fracture Conductivity on Production Performance of Hydraulically Fractured Wells: Field-Case Studies and Numerical Simulations

Contact Info

Product

Resources

About