Data Driven Production Forecasting Using Machine Learning
- Q. Cao (Schlumberger) | R. Banerjee (Schlumberger) | S. Gupta (Schlumberger) | J. Li (Schlumberger) | W. Zhou (Schlumberger) | B. Jeyachandra (Schlumberger)
- Document ID
- Society of Petroleum Engineers
- SPE Argentina Exploration and Production of Unconventional Resources Symposium, 1-3 June, Buenos Aires, Argentina
- Publication Date
- Document Type
- Conference Paper
- 2016. Society of Petroleum Engineers
- 6.1.5 Human Resources, Competence and Training, 5.6 Formation Evaluation & Management, 6 Health, Safety, Security, Environment and Social Responsibility, 7.6.6 Artificial Intelligence, 5 Reservoir Desciption & Dynamics, 7.6.7 Neural Networks, 7.6 Information Management and Systems, 7 Management and Information, 6.1 HSSE & Social Responsibility Management, 5.6.9 Production Forecasting
- Unconventional forecasting, Neural network, Machine Learning, Data driven, Decline curve
- 67 in the last 30 days
- 3,181 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Forecasting of production in unconventional prospects has gained a lot of attention in the recent years. The key challenges in unconventional reservoirs have been the requirement to put online a) a large number of wells in a short period of time, b) well productivity significantly driven by completion characteristics and that c) the physics of fluid flow in these prospects still remain uncertain. In this paper, machine learning algorithms are used to forecast production for existing and new wells in unconventional assets using inputs like geological maps, production history, pressure data and operational constraints. One of the most popular Machine Learning methods – Artificial Neural Network (ANN) is employed for this purpose. ANN can learn from large volume of data points without assuming a predetermined model and can adapt to newer data as and when it becomes available. The workflow involves using these data sets to train and optimize the ANN model which, subsequently, is used to predict the well production performance of both existing wells using their own history and new wells by using the history of nearby wells which were drilled in analogous geological locations. The proposed technique requires users to do less data conditioning and model building and focus more on analyzing what-if scenarios and determining the well performance.
|File Size||2 MB||Number of Pages||10|
Ilk, D., Rushing, J.A., Perego, A.D.. 2008. Exponential Vs. Hyperbolic Decline in Tight Gas Sands: Understanding the Origin and Implications for Reserve Estimates Using Arps' Decline Curves. Presented at the SPE Annual Technical Conference and Exhibition, Denver, Colorado, USA, 21–24 September. SPE-116731-MS. http://dx.doi.org/10.2118/116731-MS.
Shahab D. MohagheghSPE, Intelligent Solutions and West Virginia University, and Ognjen Grujic, SPE, Seed Zargari, SPE, and Masoud Kalantari, West Virginia University: Modeling, History Matching, Forecasting, and Analysis of Shale-Reservoir Performance Using Artificial Intelligence, SPE Digital Energy Conference and Exhibition, the Woodlands, Texas, 19-21 April. SPE-0911-0060-JPT.
Valko, P.P. and Lee, W.J. 2010. A Better Way to Forecast Production from Unconventional Gas Wells. Presented at the SPE Annual Technical Conference and Exhibition, Florence, Italy. 19–22 September. SPE-134231-MS. http://dx.doi.org/10.2118/134231-MS.