Enhancing Reservoir Management Quality and Efficiency of Thermal Assets with Data-Driven Models
- Tae Hyung Kim (Chevron North America E&P)
- Document ID
- Society of Petroleum Engineers
- SPE Western Regional Meeting, 23-26 April, San Jose, California, USA
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Petroleum Engineers
- steam flooding, artificial intelligence, machine learning, data-driven model, reservoir management
- 1 in the last 30 days
- 97 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Temperature monitoring is the most important surveillance in thermal assets, but temperature logging is limited in frequencies and locations. In addition, it is extremely difficult to review all the measured temperature and injection data manually since there are 10,000+ wells in Kern River field. To overcome the limitations, data-driven reservoir temperature models are presented that are built using past temperature logs and steam injection rates of the Kern River field, California.
Based on the physics and geologic understanding the reservoir, adequate input features were selected and queried. Data cleanup was conducted to remove erroneous data or fix data errors using statistical tools such as multivariate Gaussian distribution. Voronoi diagram based dynamic injector selection algorithm (DISA) was developed to correctly capture the injectors which impact on temperature changes of a temperature observation well. Based on geologic characteristics of the Kern River, reservoir was divided into two sub-reservoirs, North-East and South-West. Two full field models were developed for predicting maximum and mean temperatures of a heated zone with multi-layer perceptron for both sub-reservoirs using about 120,000 data points from over 25,000 temperature curves measured at 700+ temperature observation wells.
To estimate proper model update frequencies and verify the process, three yearly models (models 2015, 2016, and 2017) were built and validated by using one-year future temperature predictions in 2016, 2017, and 2018. For instance, model 2015 was trained with data until the end of 2015 and validated against 2016 data. Maximum temperature prediction r2 of 2017 South-West and North-East models were 0.96 and 0.98, respectively. Model 2017 has been deployed for alerting exception cases automatically and flagging abnormal temperature measurements. Also, the models improve the quality of heat injection design by providing temperature predictions based on planned heat injection rates. This novel automated workflow with data-driven models enhances reservoir management efficiency by reducing engineers’ unproductive time such as data manipulation and allowing them to focus on value-added works like analysis and optimization.
|File Size||1 MB||Number of Pages||14|
Blevins, T. and Billingsley, R. 1975. The Ten-Pattern Steamflood, Kern River Field, California. J Pet Technol 27 (12): 1505-1514. https://doi.org/10.2118/4756-PA.
Bursell, C. and Pittman, G. 1975. Performance of Steam Displacement in the Kern River Field. J Pet Technol 27 (8): 997-1004. https://doi.org/10.2118/5017-PA.
Demirbas, A., Bafail, A., and Nizami, A. 2016. Heavy Oil Upgrading: Unlocking the Future Fuel Supply. Petroleum Science and Technology 34 (4): 303-308. https://doi.org/10.1080/10916466.2015.1136949.
Castineira, D., Zhai, X., Darabi, H.. 2018. Augmented AI Solutions for Heavy Oil Reservoirs: Innovative Workflows That Build from Smart Analytics, Machine Learning And Expert-Based Systems. Presented at the SPE International Heavy Oil Conference and Exhibition, Kuwait City, Kuwait, 10-12 December. SPE-193650-MS. https://doi.org/10.2118/193650-MS.
Guevara, J., Patel, R., and Trivedi, J. 2018. Optimization of Steam Injection for Heavy Oil Reservoirs Using Reinforcement Learning. Presented at the SPE International Heavy Oil Conference and Exhibition, Kuwait City, Kuwait, 10-12 December. SPE-193769-MS. https://doi.org/10.2118/193769-MS.
Jin, F., Xi, W., Shunyuan, Z.. 2018. Application of Multi-Well Steam Injection and CO2 Technology in Heavy Oil Production, Liaohe Oilfield. Presented at the SPE Improved Oil Recovery Conference, Tulsa, Oklahoma, 14-18 April. SPE-190186-MS. https://doi.org/10.2118/190186-MS.
Kim, T., Crane, D., and Grijalva, E. 2018. Infill Well Location Selection Procedures in Lost Hills Using Machine Learning. Presented at the SPE Western Regional Meeting. Garden Grove, California, 22-27 April. SPE-190101-MS. https://doi.org/10.2118/190101-MS.
Korjani, M., Popa, A., Grijalva, E.. 2016. Reservoir Characterization Using Fuzzy Kriging and Deep Learning Neural Networks. Presented at the SPE Annual Technical Conference and Exhibition, Dubai, UAE, 26-28 September. SPE-181578-MS. https://doi.org/10.2118/181578-MS.
Kumar, A., Novlesky, A., Bityutsky, E.. 2018. Field Surveillance and AI Based Steam Allocation Optimization Workflow for Mature Brownfield Floods. Presented at the SPE International Heavy Oil Conference and Exhibition, Kuwait City, Kuwait, 10-12 December. SPE-193700-MS. https://doi.org/10.2118/193700-MS.
Li, Y., Agarwal, A., and Kovscek, A. 2018. Continuous Variable Pressure Steam Injection for Enhanced Oil Recovery. Presented at the SPE Western Regional Meeting, Garden Grove, California, 22-27 April. SPE-190100-MS. https://doi.org/10.2118/190100-MS.
Li, Y., Popa, A., Johnson, A.. 2018. Dynamic Layered Pressure Map Generation in a Mature Waterflooding Reservoir Using Artificial Intelligence Approach. Presented at the SPE Western Regional Meeting, Garden Grove, California, 22-27 April. SPE-190042-MS. https://doi.org/10.2118/190042-MS.
Moussa, T., Mahmoud, M., Patil, S.. 2018. Optimization of a Thermochemical Recovery Process Using Global Optimization Methods to Enhanced Heavy Oil Recovery. Presented at the SPE International Heavy Oil Conference, Kuwait City, Kuwait, 10-12 December. SPE-193791-MS. https://doi.org/10.2118/193791-MS.
Riveros, G. and Barrios, H. 2011. Steam Injection Experiences in Heavy and Extra-Heavy Oil Fields, Venezuela. Presented at the SPE Heavy Oil Conference and Exhibition, Kuwait City, Kuwait, 12-14 December. SPE-150283-MS. https://doi.org/10.2118/150283-MS.
Saleri, N. 2017. Climate Change: Why Oil and Gas Must Join the Debate. J Pet Technol 69 (12): 14-15. https://doi.org/10.2118/1217-0014-JPT.
Scikit-learn v0.20.2. 2018. Neural network models (supervised), Scikit-learn, 20 December, 2018, https://scikit-learn.org/stable/modules/neural_networks_supervised.html (accessed 14 January, 2019).
Shutler, N. 1970. Numerical Three-Phase Model of the Two-Dimensional Steamflood Process. SPE J. 10 (4): 405-417. https://doi.org/10.2118/2798-PA.