Decline Curve Analysis for Production Forecasting Based on Machine Learning
- Yunan Li (Texas A&M University) | Yifu Han (University of Oklahoma)
- Document ID
- Society of Petroleum Engineers
- SPE Symposium: Production Enhancement and Cost Optimisation, 7-8 November, Kuala Lumpur, Malaysia
- Publication Date
- Document Type
- Conference Paper
- 2017. Society of Petroleum Engineers
- 5.6.9 Production Forecasting, 5 Reservoir Desciption & Dynamics, 7.6.6 Artificial Intelligence, 3 Production and Well Operations, 7.6.7 Neural Networks, 7.6 Information Management and Systems, 2 Well completion, 5.6 Formation Evaluation & Management, 7 Management and Information
- Decline Curve Analysis, hydraulic fractures, Reservoir Properties, Unconventional Reservoirs, Machine Learning
- 19 in the last 30 days
- 493 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
A new method is developed by using machine learning technique to forecast single well production in both conventional and unconventional reservoirs. Unlike investigating and analyzing existing wells production rate and decline curve, this method predicts new well production rate according to reservoir properties such as matrix permeability, porosity, formation pressure and temperature, as well as hydraulic fracture parameters including fracture half length, fracture width and fracture conductivity.
In this paper, an inversion scheme is coupled with decline curve model, Logistic Growth Model (LGM), to obtain a set of decline curve parameters by fitting with production data. Both the Principal Component Analysis (PCA) and sensitivity study are applied to analyze the variance and identify key factors that influence production rate from reservoir and hydraulic fracture parameters. The sensitivity analysis results and scree plot from PCA serve as references to select key factors. Lastly, Neural Network (NN) technology is applied to investigate the pattern and correlation of selected reservoir and hydraulic fracture parameters and decline curve parameters. Therefore, the NN model can be applied to forecast production rate for a new well according to given reservoir and hydraulic information.
There is a good agreement between the available production data and decline curve model predicated production data based on the inverted decline curve model parameters. The scree plot and bi-plot generated by PCA provide the weight percentage of each component and help to identify factors that should be considered. Field production data is used to verify the feasibility of this method. This field case study is conducted by fitting the predicted production data (decline curve) based on NN model with field production data. The Mean Squared Estimation (MSE) of NN model is 0.013 Mscf/D and the overall R value is 0.917. This indicates that NN model is reliable to study the dataset and provide proper production (decline curve) prediction. The results illustrate that the predicted production data (decline curve) has good accuracy.
This paper proposes a statistical way for production forecasting based on machine learning. Instead of forecasting future production of existing wells, it provides meaningful reference for the evaluation of a new well and decision making.
|File Size||1 MB||Number of Pages||14|
Abass, H. H., Al-Tahini, A. M., Abousleiman, Y., and Khan, M. R. 2009. New Technique to Determine Biot Coefficient for Stress-Sensitive Dual-Porosity Reservoirs. Presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, 4-7 October. SPE-124484-MS. http://dx.doi.org/10.2118/124484-MS
Cao, Q., Banerjee, R., Gupta, S., Li, J., Zhou, W., & Jeyachandra, B. 2016. Data Driven Production Forecasting Using Machine Learning. Presented at SPE Argentina Exploration and Production of Unconventional Resources Symposium, Buenos Aires, Argentina, 1-3 June. doi: 10.2118/180984-MS
Chen, C., Gao, G., Honorio, J., Gelderblom, P., Jimenez, E., and Jaakkola, T. 2014. Integration of Principal-Component-Analysis and Streamline Information for the History Matching of Channelized Reservoirs. Presented at SPE Annual Technical Conference and Exhibition, Amsterdam, The Netherlands, 27-29 October. doi: 10.2118/170636-MS
Duong, A. N. 2010. An Unconventional Rate Decline Approach for Tight and Fracture-Dominated Gas Wells. Presented at the SPE Canadian Unconventional Resources & International Petroleum Conference, Calgary, Alberta, Canada, 19-21 October. doi: 10.2118/137748-MS
Hawkes, R., Su, Z., and Leech, D. 2000. Field Data Demonstrates Thermal Effects-Important in Gas Well Pressure Buildup Tests. Presented at the SPE Canadian International Petroleum Conference, Calgary, Alberta, Canada, 4-8 June. doi: 10.2118/2000-031
Kazakov, N., and Miskimins, J. L. 2011. Application of Multivariate Statistical Analysis to Slickwater Fracturing Parameters in Unconventional Reservoir Systems. Presented at the SPE Hydraulic Fracturing Technology Conference, Woodlands, Texas, 24-26 January. doi: 10.2118/140478-MS
Saleh, L. D., Wei, M., and Bai, B. 2014. Data Analysis and Updated Screening Criteria for Polymer Flooding Based on Oilfield Data. Society of Petroleum Engineers. doi: 10.2118/168220-PA