EOR Screening and Early Production Forecasting in Heavy Oil Fields: A Machine Learning Approach
- Eduardo Andrés Muñoz Vélez (Ecopetrol) | Felipe Romero Consuegra (Colombian Chamber of Oilfield Services) | Carlos Andrés Berdugo Arias (Universidad Industrial de Santander)
- Document ID
- Society of Petroleum Engineers
- SPE Latin American and Caribbean Petroleum Engineering Conference, 27-31 July, Virtual
- Publication Date
- Document Type
- Conference Paper
- 2020. Society of Petroleum Engineers
- 5.4 Improved and Enhanced Recovery, 5 Reservoir Desciption & Dynamics, 5.6.9 Production Forecasting, 7.6 Information Management and Systems, 5.4 Improved and Enhanced Recovery, 5.4.6 Thermal Methods, 7.6.7 Neural Networks, 5.6 Formation Evaluation & Management, 7 Management and Information, 7.6.6 Artificial Intelligence
- EOR Screening, Artificial Neural Networks, Production Forecasting, Heavy oil, Machine Learning
- 83 in the last 30 days
- 83 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
A new mathematical model was proposed integrating the algorithms of neural networks and gradient boosting for the selection of the optimal EOR method in heavy and extra heavy oil fields as well as to predict the oil production of the field in the first five years of the project. The parameters were selected from genetic algorithms using the technique of auto-machine learning.
The model was developed with a database of 919 fields, from different public sources, and consists of three stages: 1) A dimensional reduction of the initial variables using t-SNE (t-Distributed Stochastic Neighbor Embedding), passing from 12 variables to 2 final variables. 2) An estimation of the optimal EOR method from an Artificial Neural Network. And 3) the integration of 1) and 2), serve as the input for a genetic algorithm in order to forecast the production of the first years of the field after the project started.
The obtained results show a correlation of 87% for the classification neural network, and 93% for the genetic algorithm in the test database. Therefore, an integrated workflow was also developed, which takes the generated production profile and performs cash flow analysis, leading to the calculation of key financial parameters for determining project feasibility from given reservoir, fluid, and economic conditions input by the user.
The developed model is presented as an opportunity to experience the possibilities that artificial intelligence has in the oil and gas industry, and how it can be of great help in the prediction of variables for process optimization. Employing the optimal EOR method from the beginning of field development can increase long-term profitability. In addition, the developed screening software eases decision making for operators in selecting, technically and economically, the most feasible thermal EOR method for the development of heavy and extra heavy oil fields, maximizing asset value and E&P portfolio.
|File Size||821 KB||Number of Pages||13|
Afra, S., & Tarrahi, M. (2016). An Efficient EOR Screening Approach with Statistical Pattern Recognition: Impact of Rock/Fluid Feature Selection and Extraction. Offshore Technology Conference. 10.4043/27272-ms
Alvarado, V., & Manrique, E. (2010). Reservoir Development Plans. Enhanced Oil Recovery, 1-5. 10.1016/b978-1-85617-855-6.00007-3
Boscan, H., & Chourio, G. (2015). Heavy Oil Reserve Development by Cycle Steam Stimulation + Gas Process in Bach-01 Reservoir. SPE Latin American and Caribbean Petroleum Engineering Conference. 10.2118/177116-ms
Escobar, M. A., Valera, C. A., & Perez, R. E. (1997). A Large Heavy Oil Reservoir in Lake Maracaibo Basin: Cyclic Steam Injection Experiences. International Thermal Operations and Heavy Oil Symposium. 10.2118/37551-ms
Guerillot, D. R. (1988). EOR Screening With an Expert System. Petroleum Computer Conference. 10.2118/17791-ms
Guo, H., Dong, J., Wang, Z., Liu, H., Ma, R., Kong, D.,… She, H. (2018). 2018 EOR Survey in China-Part 1. SPE Improved Oil Recovery Conference. 10.2118/190286-ms
Jill, H., Song, Q., & Hu, X. (2018). Auto-Keras: An Efficient Neural Architecture Search System. Retrieved from arXiv.org website: http://arxiv.org/abs/1806.10282
Khazali, N., Sharifi, M., & Ahmadi, M. A. (2019). Application of fuzzy decision tree in EOR screening assessment. Journal of Petroleum Science and Engineering, 177, 167-180. 10.1016/j.petrol.2019.02.001 .
Koothungal, L. (2014, April 7). 2014 worldwide EOR survey. Retrieved from Oil & Gas Journal website: http://www.ogj.com/drillingproduction/production-operations/ior-eor/article/17210637/2014-worldwide-eor-survey
Meyer-Baese, A., & Schmid, V. (2014). Genetic Algorithms. Pattern Recognition and Signal Analysis in Medical Imaging, 135-149. 10.1016/b978-0-12-409545-8.00005-4
Ramirez, A. M., Valle, G. A., Romero, F., & Jaimes, M. (2017). Prediction of PVT Properties in Crude Oil Using Machine Learning Techniques MLT. SPE Latin America and Caribbean Petroleum Engineering Conference. 10.2118/185536-ms
Romero, C., & Carter, J. N. (2003). Chapter 17 Using genetic algorithms for reservoir characterisation. Developments in Petroleum Science, 323-363. 10.1016/s0376-7361(03)80021-3
Uribe Hidalgo, C. A., Munoz Navarro, S. F., Oliveros Gomez, L. R., & Naranjo Suarez, C. E. (2013). Technical and Financial Evaluation of a Process of Cyclic Steam Injection Using Horizontal Wells. SPE Enhanced Oil Recovery Conference. 10.2118/165297-ms
Zerafat, M. M., Ayatollahi, S., Mehranbod, N., & Barzegari, D. (2011). Bayesian Network Analysis as a Tool for Efficient EOR Screening. SPE Enhanced Oil Recovery Conference. 10.2118/143282-ms