Analogy in the World of Geological Uncertainties, or How Reservoir Analogs May Refine Your Probabilistic Geomodel

Popova, Oksana

doi:10.2118/192551-ms

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many of these issues can be efficiently solved using machine learning. For example, an important geologic task is to find analogous reservoirs [38]. In terms of time and labour costs, the simplest method to search for reservoir analogues is to consider oil and gas reservoirs located near to the study area [51].…”

Section: Introductionmentioning

confidence: 99%

Oil reservoir recovery factor assessment using Bayesian networks based on advanced approaches to analogues clustering

Andriushchenko¹,

Deeva²,

Bubnova³

et al. 2022

Preprint

View full text Add to dashboard Cite

The work focuses on the modelling and imputation of oil and gas reservoirs parameters, specifically, the problem of predicting the oil recovery factor (RF) using Bayesian networks (BNs). Recovery forecasting is critical for the oil and gas industry as it directly affects a company's profit. However, current approaches to forecasting the RF are complex and computationally expensive. In addition, they require vast amount of data and are difficult to constrain in the early stages of reservoir development. To address this problem, we propose a BN approach and describe ways to improve parameter predictions' accuracy. Various training hyperparameters for BNs were considered, and the best ones were used. The approaches of structure and parameter learning, data discretization and normalization, subsampling on analogues of the target reservoir, clustering of networks and data filtering were considered. Finally, a physical model of a synthetic oil reservoir was used to validate BNs' predictions of the RF. All approaches to modelling based on BNs provide full coverage of the confidence interval for the RF predicted by the physical model, but at the same time require less time and data for modelling, which demonstrates the possibility of using in the early stages of reservoirs development. The main result of the work can be considered the development of a methodology for studying the parameters of reservoirs based on Bayesian networks built on small amounts of data and with minimal involvement of expert knowledge. The methodology was tested on the example of the problem of the recovery factor imputation.

show abstract

Section: Introductionmentioning

confidence: 99%

Oil reservoir recovery factor assessment using Bayesian networks based on advanced approaches to analogues clustering

Andriushchenko¹,

Deeva²,

Bubnova³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Building A Production Analysis Tool for Analog Field Analysis Brazil and Mexico

Pederson

Eburi

Boyarko

2020

SPE Latin American and Caribbean Petroleum Engineering Conference

View full text Add to dashboard Cite

This paper showcases how public data was integrated using data visualization software to develop appropriate analog information for new prospects and field evaluations in Brazilian Campos and Santos and Mexican Gulf of Mexico deepwater plays. The data visualization software was selected for its ability to integrate geologic map files (.shp files) and digital production data. This work was extended to evaluate Mexican opportunities since similar production data is available from the government. In the exploration workflow, analog field data is used to develop potential prospect estimated ultimate recovery ("EUR"), recovery factors, the appropriate EUR per well and initial production rates. This information is then used in a conceptual development plan that allows potential economic scenarios to be assessed. Both in Brazil and Mexico, substantial well data is available from the respective governments. The team successfully used this information to develop appropriate low, mid, and high oil production forecasts.

show abstract

Knowledge Management Best Practices and Application in Field Development, IORs and Life-Cycle Reservoir Management

2021

SPE/IATMI Asia Pacific Oil &Amp; Gas Conference and Exhibition

View full text Add to dashboard Cite

This paper presents a unique E&P knowledge management system which has been widely accepted and applied by upstream petroleum industry. This knowledge management system started in mid-1990s and consists of standard static and dynamic knowledge base, comprehensive evaluation reports, and fit-for-purpose analytics tools applicable to the entire E&P lifecycle. Emphasis is placed on illustrating the breadth and depth of the E&P knowledge and advanced analytics in terms of their capturing and applications in field development and production. This knowledge base consists of >1600 reservoirs from around the world, each containing ~400 reservoir-level static parameters and a set of dynamic performance data. The static parameter covers reservoir characteristics, fluid properties, original in-place volume, EUR, recovery factor, production-related data (such as well spacing, well pattern, well EUR et al.), reservoir management practices, and key IORs/EORs and their incremental recovery. The knowledge extraction process involves collecting, reviewing, and synthesizing geologic, reservoir engineering and production data on a representative sample of global reservoirs. The reliable, coherent, high-quality knowledge base provides a foundation for the development of primary recovery index using supervised machine learning. Insights and intelligence derived from this knowledge base are critical to decision-making for both initial or early field development and production stages. The development application includes, but not limited to: (1) quantifying in-place volume, EUR, and recovery factor; (2) characterizing possible production performance and uncertainties and obtaining a conceptual production performance curve; (3) validating development plan options; and (4) benchmarking reservoir simulation results. The production application includes: (1) benchmarking production performance; (2) identifying upside potential and improved oil recovery opportunities; (3) finding best practices and lessons learned in reservoir management and secondary recovery practice; and (4) screening EOR methods, calibrating potential incremental recovery and characterizing EOR process performance. Lack of knowledge standardization and absence of coherence of data from various data sources are the main challenges facing industry's data-driven application. The knowledge management system presented in this study provides the most reliable knowledge base, advanced analytics tools, and practical application workflow to help the upstream industry become more efficient in applying collective human intelligence.

show abstract

Analogy in the World of Geological Uncertainties, or How Reservoir Analogs May Refine Your Probabilistic Geomodel

Cited by 3 publications

References 9 publications

Oil reservoir recovery factor assessment using Bayesian networks based on advanced approaches to analogues clustering

Oil reservoir recovery factor assessment using Bayesian networks based on advanced approaches to analogues clustering

Building A Production Analysis Tool for Analog Field Analysis Brazil and Mexico

Knowledge Management Best Practices and Application in Field Development, IORs and Life-Cycle Reservoir Management

Contact Info

Product

Resources

About