Modern approaches to automating the infill drilling process on mature fields: from selection of infill wells locations to cost optimization

   Introduction. Thanks to the automation of various development processes, the economic efficiency of extraction in depleted fi elds is increasing. Infill drilling is one of the key activities for enhancing oil recovery in the later stages. Modern approaches to locating new drilling zones, optimizing well placement and economically evaluating of initial production increasingly use machine learning, big data analytics and digital twins.

   Aim. The objective of this article is to conduct a literature review on the latest approaches to infill drilling and highlight the most effective methods for automating the search for well candidates in large fields with limited datasets.

   Materials and methods. Modern approaches to identifying new zones for infill drilling were explored, including the generation of probability maps and the use of machine learning for data analysis. Additionally, automatic interpretation techniques of geophysical data to identify missed intervals of reservoirs was reviewed. Methods for well placement optimization were described, taking into account geological risks and economic factors. It was noted that the complexities and risks associated with infill drilling in mature fields stress the need to balance accuracy and timeliness of methods for effective decision-making.

   Results. The most effective and universal approaches for each stage of planning infill drilling were highlighted. The main stages include generating probability maps, well placement optimization and forecasting production parameters using analytical methods and machine learning.

   Conclusions. Modern approaches to automating infill drilling, which include machine learning and integration of various models, significantly increase the efficiency and accuracy of planning. These methods require further research to adapt to different field development conditions.

1. Mata C., Saputelli L., Badmaev D., Zhao W., Mohan R., Gönczi D. Automated Reservoir Management Workfl ows to Identify Candidates and Rank Opportunities for Production Enhancement and Cost Optimization in a Giant Field in Offshore Abu Dhabi. Offshore Technology Conference, Houston, TX, USA. 2021. OTC 31295

2. Algarhy A., Bateman R.M., Soliman M.Y. An Innovative Technique To Evaluate Shale Sweetspots: A Case Study From North Africa. SPWLA 56^th Annual Logging Symposium held in Long Beach, California, USA. July 18–22, 2015

3. Algarhy A., Ibrahim A.F., A. Gabry M., Ali Amr G. Predicting Shale Production Performance Through Machine Learning: The Development and Application of the Sweet Spot Quality Index. Society of Petroleum Engineers, Wheeling, West Virginia, USA. 2023. SPE 215911

4. Su Sh., Schulze-Riegert R., Mustapha H., Lang Ph., Kloucha Ch.K. Artificial Intelligence for Infill Well Placement and Design Optimization in Multi-layered/stacked Reservoirs Under Subsurface Uncertainty. Society of Petroleum Engineers, Abu Dhabi, UAE. 2021. SPE 207899

5. Pongtepupathum W., Lang Ph., Adeyemi T. An Ensemble-Based Infi ll Well Location Solution: A Cloud Native Application for Automating Well Placement and Evaluation. Society of Petroleum Engineers, Abu Dhabi, UAE. 2022. SPE 211361

6. Su Sh., Tahir S., Ghorayeb K., Ramatullayev S., Garcia-Teijeiro X. Multidisciplinary Data Integration for Artificial-IntelligenceAssisted Well Placement and Trajectory Design Optimization Under Uncertainty. Society of Petroleum Engineers, Abu Dhabi, UAE. 2022. SPE 211367

7. Bernadi B., Silalahi Eli S., Reksahutama A., Miraza D. Infill Wells Placement in High Water-Cut Mature Carbonate Field with Simulation Opportunity Index Method. Society of Petroleum Engineers, Bali, Indonesia. 2019. SPE 196388

8. Zijlstra E., Riethmuller G., Schäff tlein S., Mahruqi S. Using Marketing Technology in Reservoir Engineering: The Application of Data Driven Predictive Analysis on a Mature Oil Field. International Petroleum Technology Conference, Bangkok, Thailand. 2011. IPTC 14676

9. Al-Kinani A., Nunez G., Stundner M., Zangl G., Mata T., Cottone S. Selection of Infill Drilling Locations Using Customized Type Curves. Society of Petroleum Engineers, Cartagena, Columbia. 2019. SPE 122186

10. Aslanyan A., Kovalenko I., Ilyasov I., Gulyaev D., Buyanov A., Musaleev Kh. Waterflood study of high viscosity saturated reservoir with multiwell retrospective testing and cross-well pressure pulse-code testing. Society of Petroleum Engineers, Kuwait City, Kuwait. 2018. SPE-193712-MS

11. Aslanyan A., Asmadiyarov R., Kaeshkov I., Bikkulov M., Farakhova R., Krichevsky V., Gulyaev D., Musaleev Kh. Multiwell deconvolution as important guideline to production optimisation: Western Siberia Case Study. The International Petroleum Technology Conference, Beijing, China. 2019. IPTC-19566-MS

12. Aslanyan A., Grishko F., Krichevsky V., Gulyaev D., Panarina E., Buyanov A. Assessing waterflood efficiency with deconvolution based multi-well retrospective test technique. Society of Petroleum Engineers, London, England, UK. 2019. SPE195518-MS

13. Kovaleno I.V., Nemirovich G.M., Ilyasov I.R., Buyanov A.V., Gulyaev D.N. The usage of impulse-code interference technology during water flooding in difficult geological conditions. Ne1yanoe khozyaystvo. June 2018. (In Russ.)

14. Sabzabadi A., Masoudi R., Arsanti D., Aslanyan I., Garnyshev M., Minakhmetova R., Karancharat R. Verifying Local Oil Reserves Using Multi-Well Pressure Pulse Code Testing. Offshore Technology Conference Asia, Kuala Lumpur, Malaysia. 2018. OTC-28601-MS

15. Qin Zh., Xu T. Shale gas geological “sweet spot” parameter prediction method and its application based on convolutional neural network. Scientific Reports, Nature Portfolio, China. 2022. doi: 10.1038/s41598-022-19711-6

16. Egorov D.V., Sabirov A.R. Applying Machine Learning Methods to Search for Missing Net Pay Zones in Mature Oilfi elds Wells. Society of Petroleum Engineers, Moscow, Russia. 2019. SPE 196869

17. Semenikhin A.S., Shchepetnov A.A. Missed Net Pay Zones in Mature Oilfields Via Injection of Expert Knowledge in Deep Learning Algorithms. Society of Petroleum Engineers, Moscow, Russia. 2020. SPE 201922

18. Belozerov B., Bukhanov N. Automatic Well Log Analysis Across Priobskoe Field Using Machine Learning Methods. Society of Petroleum Engineers, Moscow, 2018. (In Russ.) SPE 191604-18RPTC-RU

19. Sakhnyuk V.I., Novikov E.V., Sharifullin A.M., Belokhin V.S., Antonov A.P. Machine learning applications for well-logging interpretation of the Vikulov Formation. Lomonosov Moscow State University, Moscow, 2022, vol. 24, № 2, pp. 230–238. (In Russ.) doi: 10.18599/grs.2022.2.21

20. Litvak M., Gane B., Williams G. Field Development Optimization Technology. Society of Petroleum Engineers, Houston. 2007. SPE 106426

21. Roussennac B., Gijs van Essen. Streamlining the Well Location Optimization Process — An Automated Approach Applied to a Large Onshore Carbonate Field. Society of Petroleum Engineers, Dubai, UAE. 2021. SPE 205913

22. Boah E.A., Senyo Kondo O.K., Borsah A.A. Critical Evaluation of Infill Well Placement and Optimization of Well Spacing Using the Particle Swarm Algorithm. Journal of Petroleum Exploration and Production Technology. 2019, no. 9 (4). doi: 10.1007/s13202-019-0710-1

23. Ma Zh., Davani E., Ma X. Finding a Trend Out of Chaos: A Machine-Learning Approach for Well-Spacing Optimization. Society of Petroleum Engineers, Denver, Colorado, USA. 2020. SPE 201698

24. Li С., Fang Ch., Huang Y., Zuo H. Infill well placement optimization for secondary development of waterfl ooding oilfields with SPSA algorithm. Frontiers in Energy Research. 2022. doi: 10.3389/fenrg.2022.1005749

25. Forouzanfar F., Li G., Reynolds A.C. A two-stage well placement optimization method based on adjoint gradient. Society of Petroleum Engineers, Florence, Italy. 2010. SPE 135304

26. Alpak F., Wang Y., Gao G. Benchmarking and Field-Testing of the Distributed Quasi-Newton Derivative-Free Optimization Method for Field Development Optimization. Society of Petroleum Engineers, Dubai, UAE. 2021. SPE 206267

27. Litvak M., Onwunalu J., Baxter J. Field Development Optimization with Subsurface Uncertainties. Society of Petroleum Engineers, Colorado, USA. 2011. SPE 146512

28. Motlagh M., Thenon A. Automated Well Location Optimization Using Wish Technology. Society of Petroleum Engineers, Abu Dhabi, UAE. 2022. SPE 211621-MS

29. Kristoff ersen B.S., Bellout M.C., Silva T.L., Berg F.C. An Automatic Well Planner for Complex Well Trajectories. Math Geosci. 2021, no. 53 (4). doi: 10.1007/s11004-021-09953-x

30. Kristoff ersen B.S., Bellout M.C., Silva T.L., Berg F.C. An Automatic Well Planner for Efficient Well Placement Optimization Under Geological Uncertainty. ECMOR XVII. 2020, no. 17. doi: 10.3997/2214-4609.202035211

31. Abdul-Hameed M.R., Hamd-Allah S.M. Optimization sequence of infi ll well-drilling using Latin hypercube plus radial basis function network. Int. J. Nonlinear Anal. Appl. 2024, no. 15, pp. 87–96. doi: 10.22075/ijnaa.2023.29922.4296

32. Zhang P., Gao T., Fu J., Li R. Deep-Learning-Based Approach for Optimizing Infill Well Placement. Society of Petroleum Engineers, San Antonio, Texas, USA. 2023. SPE 215072

33. Willigers B.J.A., Begg S., Bratvold R.B. Appraising Unconventional Resources: How Many Wells To Drill and Where To Place Them?. Society of Petroleum Engineers. 2016. SPE 179736

34. Qadeer Siddiqui M.A., Khan R.A., Md Sarim J. Multi-objective Well Placement Optimization Considering Energy Sustainability Along With Economical Gains. Society of Petroleum Engineers, Cairo, Egypt. 2015. SPE 175842-MS

35. Sieberer M., Peisker J., Clemens T., Thiele M.R. Infill Well Portfolio Management under Uncertainty — Application to the 8TH Reservoir, Austria. Society of Petroleum Engineers, Paris, France. 2017. SPE 185803

36. Allard D.N., Hillyer M.G., Gerbacia W.E., Rychener L.M. Empirical Risk Assessment of Infill Drilling Locations, Barrow Island, Australia. Society of Petroleum Engineers, Houston, Texas, USA. 1999. SPE 56816

37. Bansal Y., Ertekin, T., Karpyn, Z., Ayala, L., Nejad, A. Forecasting Well Performance in a Discontinuous Tight Oil Reservoir Using Artifi cial Neural Networks. Society of Petroleum Engineers, The Woodlands, Texas, USA. 2013. SPE 164542

38. Kolesov V. V., Kurganov D. V. Well ranking for infill drilling using machine learning with production and geological data. Samara State Technical University. Series: Technical Sciences. 2019, no. 1 (61). (In Russ.)

39. Wang Z., Tang H., Cai H., Hou Y., Shi H., Li J., Yang T., Feng Y. Production prediction and main controlling factors in a highly heterogeneous sandstone reservoir: Analysis on the basis of machine learning. Energy Science & Engineering. 2022. doi: 10.1002/ese3.1297