Optimization of Oil Field Development using a Surrogate Model: Case of Miscible Gas Injection
- Maksim Simonov (Gazpromneft Science & Technology Center, Peter the Great St. Petersburg Polytechnic University) | Andrei Shubin (Saint Petersburg State University) | Artem Penigin (Gazpromneft Science & Technology Center) | Dmitrii Perets (Gazpromneft Science & Technology Center) | Evgenii Belonogov (Gazpromneft Science & Technology Center) | Andrei Margarit (Gazpromneft Science & Technology Center)
- Document ID
- Society of Petroleum Engineers
- SPE Reservoir Characterisation and Simulation Conference and Exhibition, 17-19 September, Abu Dhabi, UAE
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Petroleum Engineers
- Surrogate modeling, EOR, gas injection, machine learning, reservoir management
- 46 in the last 30 days
- 46 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 9.50|
|SPE Non-Member Price:||USD 28.00|
The topic of the paper is an approach to find optimal regimes of miscible gas injection into the reservoir to maximize cumulative oil production using a surrogate model. The sector simulation model of the real reservoir with a gas cap, which is in the first stage of development, was used as a basic model for surrogate model training. As the variable (control) parameters of the surrogate model parameters of gas injection into injection wells and the limitation of the gas factor of production wells were chosen. The target variable is the dynamics of oil production from the reservoir. A set of data has been created to train the surrogate model with various input parameters generated by the Latin hypercube.
Several machine learning models were tested on the data set: ARMA, SARIMAX and Random Forest. The Random Forest model showed the best match with simulation results. Based on this model, the task of gas injection optimization was solved in order to achieve maximum oil production for a given period. The optimization issue was solved by Monte Carlo method. The time to find the optimum based on the Random Forest model was 100 times shorter than it took to solve this problem using a simulator. The optimal solution was tested on a commercial simulator and it was found that the results between the surrogate model and the simulator differed by less than 9%.
|File Size||1 MB||Number of Pages||11|
Application of Machine Learning Technologies for Rapid 3D Modelling of Inflow to the Well in the Development System. Simonov, M., Akhmetov, A., Temirchev, P., Koroteev, D., Kostoev, R., Burnaev, E., & Oseledets, I. (2018, October 15). Society of Petroleum Engineers. doi:10.2118/191593-18RPTC-MS
Methodology of surrogate models (metamodels) and their prospects for solving petroleum engineering challenges. M.V. Simonov, A.V. Penigin, A.S. Margarit, A.A. Pustovskikh, N.A. Smirnov, A.N. Sitnikov. "PROneft. Professionals about oil", vol 2 (12), 2019. DOI: 10.24887/2587-7399-2019-2-48-53
Latin hypercube sampling with multidimensional uniformit. Jared L., Clayton V. Journal of Statistical Planning and Inference, 2012, V. 142, no. 3, pp. 763-772, DOI: 10.1016/j.jspi.2011.09.016.
Breiman L., Random forests, Machine Learning. 2001, V. 45 (1), DOI:10.1023/A:101093340432