Smart Determination of Estimated Ultimate Recovery in Shale Gas Reservoir
- Qin He (Saint Francis University)
- Document ID
- Society of Petroleum Engineers
- SPE Eastern Regional Meeting, 4-6 October , Lexington, Kentucky, USA
- Publication Date
- Document Type
- Conference Paper
- 2017. Society of Petroleum Engineers
- 7 Management and Information, 7.6 Information Management and Systems, 5.8.2 Shale Gas, 5.8.1 Tight Gas, 7.6.4 Data Mining, 5.8 Unconventional and Complex Reservoirs, 7.6.6 Artificial Intelligence, 5 Reservoir Desciption & Dynamics
- Shale Gas Reservoir, Decline Curve Analysis, Neural Network Model, EUR Estimate
- 10 in the last 30 days
- 65 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
The development of shale gas reservoir has made rapid progress due to the technology advancement in the past decades, which triggered the energy revolution in the United States. Estimating ultimate recovery, the amount of shale gas that can be economically recovered from a reservoir, is an essential task for E&P companies. Based on the estimated ultimate recovery information, a reservoir engineer could determine the economic investment of whether a single well or series of wells would be worthy. Thus, it must be done fast and right.
For the past years, the typical methodology of evaluating remaining reserves or estimated ultimate recovery (EUR) of a well or a field is decline curve analysis. This traditional methodology only requires production data for analysis, which is very easy to access and very convenient to use. There are several empirical formulation specifically designed for shale or tight gas reservoir, such as powerlaw exponential decline, stretched exponential decline, doung’s method, etc due to the complexibities of the reservoir nature, flow behavior. However, this curve fitting technique is still problemtic because the reservoir nature itself and the operation performance are not considered into the analysis, which we believe must be a big deal for determination of ultimate recovery.
In this work, the data driven analytics, which is deemed as a smart technique, has been implemented in one asset of Marcellus shale. Different from traditional decline curve analysis, data-driven analytics is a data mining and artificial intelligence based technique, which not only considers measured production data, but also takes reservoir characterisitics and completion data into account. Through this research, we are trying to investigate the impact weight of different groups of parameters such as reservoir characteristics, operational activities on the ultimate recovery determination in shale gas reservoir.
|File Size||2 MB||Number of Pages||10|