Active integration of sub-surface data: Building the bridge from Geophysics to Well and Reservoir Management
Welcome to the Active integration of sub-surface data: Building the bridge from Geophysics to Well and Reservoir Management. The virtual event is scheduled to take place in February 2021.
EAGE would like to thank the event Chair, Ms. Karina Miguel, DNO.
Event Programme
February 2021 I Online1pm CET- 4pm CET
| 1:00pm | Opening Address Ms. Karina Miguel (DNO) |
| 1:05pm | The practice of machine-learning in Geosciences: Common pitfalls and hands-on tips. Nicolas Leseur (Baker Hughes) |
| 1:30pm | Reservoir pressure fundamentals: Maximising the interpretation value of formation pressure test datasets. Tim Salter (Baker Hughes) |
| 1:55pm | Integrating Engineering and Geoscience data analytics for managing reservoir performance opportunities. Luigi Saputelli (Frontender) |
| 2:20pm | Break |
| 2:30pm | Vaca Muerta shale play: one reservoir, multiple challenges. Federico Gonzalez Tomassini (YPF) |
| 2:55pm | Integration and Impact of Subsurface Data in Field Reservoir Management. Ivan Yemez, Jesus Sotomayor (EPGC) |
| 3:20pm | Discussion Session |
| 3:55pm | Closing Address Ms. Karina Miguel (DNO) |
01:05 pm CET
The practice of machine-learning in Geosciences: Common pitfalls and hands-on tips. Nicolas Leseur, Baker Hughes.
Building on the breakthroughs made in the field of computer science over the last decade, operating companies and service providers have shown a renewed interest incomputational statistics, automation and self-learning algorithms. However, unlike a number of other industries, significant segments of the E&P still require substantial transformations before IOT-ready and self-updating digital oil fields become reality – a transition for which the subsurface realm is no exception.
While a successful implementation of IR 4.0 requires reservoir and production specificities to be acknowledged, various solutions are available to overcome current showstoppers such as restricted data access, spatio-temporal autocorrelation and small size sample. What is special about spatial data? What are the alternatives when limited labelled data is available? And why cannot we simply let the data decide? are among the questions which will be discussed and supported by a number of references and case studies.
Concluding on the need for humans-in-the-loop for sense-checking and accountability,the talk will touch upon how hybrid physics-based machine-learning approaches can speed up projects’ learning curve and increase generalizability of statistical predictions. A selection of open-source resources, books and code libraries will also be provided.
01:30 pm CET
Reservoir pressure fundamentals: Maximising the interpretation value of formation pressure test datasets. Tim Salter, Baker Hughes
Modern formation pressure test and sampling tools have optimized operational protocols to allow valid data from all reservoir settings. The inherent precision of the pressure gauges allows great confidence to be placed in the data and especially to the small pressure differences noted between successive data points. It can be shown that very often these small pressure differences help interpret the flow-unit heterogeneity of the reservoir. With suitable interrogation, many older pressure datasets can also be analysed to identify such informative reservoir heterogeneity.
The presentation will feature a number of real-life examples illustrating the vital role pretests have in providing detailed description of both the macro-scale reservoir compartmentalization as well as the meso-scale flow-unit interactions.
While interpretation techniques to identify a variety of reservoir pressure responses to short-term production activities and long-term burial influences also be shared, one will also discuss why a cautionary conclusion often needs to be drawn against the fitting of single ‘best-fit’ fluid gradients and accepting that datasets may just have a ‘natural scatter’.
01:55 pm CET
Integrating Engineering and Geoscience data analytics for managing reservoir performance opportunities. Dr. Luigi Saputelli, Frontender
Operators face recurrent challenges in swiftly identifying and ranking candidates for production enhancement. Conventional engineering and geoscience workflows hardly support day-to-day workover campaigns, while traditionally, simulation model poorly predict short term well productivity and post-job success.
In an attempt to circumvent the aforementioned shortcomings, a method was developed to leverage the integration of large amount of static and dynamic data in view of optimizing work-over opportunity identification, ranking and asset profitability.
Key inputs to the proposed approach can be summarized as: (1) reservoir maps generated by geo-modeling team, (2) pressure and saturation maps generated by reservoir simulation teams and (3) well events captured throughout the production history. The subsurface information is then integrated through a series of Bayesian networks that compute the scores of reservoir quality, production potential, known well completion challenges and well intervention risks. Finally, technical recommendations (multi-phase rates and decline) are complemented by the expected incremental value(e.g. production) and chance of success.
The presentation will show how, on large-scale carbonate field undergoing gas and water flooding, the newly introduced workflow was able to identify over 2,000 value-added well intervention opportunities.Implemented over the past 2 years, the systematic screening, assessment and ranking of underperforming and idle strings for infill drilling and behind-casing production enhancement opportunities was found to achieve an incremental 17% in workover efficiency when compared to existing conventional practices.
02:20pm - 02:30pm CET
02:30 pm CET
Vaca Muerta shale play: one reservoir, multiple challenges.
Federico Gonzalez Tomassini, YPF
More than 25.000 km2 and an average of four landing makes Vaca Muerta Formation a challenging unconventional play. Fluid and geology vary both, stratigraphic and geographically. Given the heterogeneity of the reservoir, different G&G workflows need to be considered to evaluate its potential across the basin. Some integrated workflows oriented to reduce uncertainty in reservoir productivity and optimize field development will be shared in this presentation. Focus will be placed on the impact of volcanic intrusions, faults, and the geometry of the depositional system.
02:55 pm CET
Integration and Impact of Subsurface Data in Field Reservoir Management. Ivan Yemez, Jesus Sotomayor (EPGC)
The oil and gas industry have made an important efforts to improve development planning and production forecast accuracy during the last decades. However, industry look-backs continue to show the difficulty of achieving a production forecast within an uncertainty band (P90 and P10) for both “Greenfield” projects with limited data and “Brownfield” projects with abundant data. Some of the identified key factors affecting production forecasts are: sparse and non-representative data, lack of data integration, biased estimates of Original Hydrocarbon In-Place, non-representative inputs distribution in the reservoir models, inadequate static and dynamic models, poor use of seismic data, use of improper analogs, non-unique history matching calibration processes for brown fields and inappropriate use of uncertainty workflows and tools. This has demanded to the industry additional efforts to understand the reservoir model limitations imposed by the data, associated uncertainty, or the underlying geostatistical algorithms or approaches and their input requirements. That along with the evolution of closed loop modeling workflow as new techniques and technologies are developed and implemented, enhancing our ability to capture the physical realities of the real subsurface world, generate better production forecasts to reduce the risk associated with field developments. This paper briefly discusses some of these factors which affect 3D reservoir interpretation and modelling outcomes based on lessons learned from 3D reservoir modelling studies, authors and industry experiences.