Classification of oil and gas reservoirs based on recovery factor: A data-mining approach

A. Sharma, Sanjay Srinivasan, L. W. Lake

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Rigorous flow simulations to obtain estimates for recovery are infeasible given many combinations of reservoir and development scenarios. This motivates an alternative approach to calibrate likelihood of recovery using reservoir datasets. A proxy model relating reservoir, well, and operational factors to the ultimate recovery factor could guide subsequent field-scale flow simulations. There are two reservoir datasets that we have used for the classification and estimation of ultimate recovery: the Tertiary Oil Recovery Information System (TORIS) database for oil reservoirs and the Gas Information System (GASIS) database for gas reservoirs. For oil reservoirs, 19 predictor variables were used to estimate the ultimate recovery factor. Cluster analysis was followed by linear regression analysis within the identified clusters that provided a reliable deterministic model for predicting the recovery factor. The linear regression model was compared with the empirical correlations given by Arps et al. (1967) and Guthrie et al. (1995). Analysis showed that geological and engineering parameters are correlated and both are important to the prediction of recovery factor. Later, we used a naïve Bayesian approach on principal scores of the predictors for the calibration of recovery factor likelihood. The likelihood function of the recovery factor for oil reservoirs provided the uncertainty in recovery. It was computed to be multimodal and non-Gaussian. In case of the gas reservoirs, good deterministic estimation was achieved by introducing cluster analysis to the data. The robustness of the linear regression model was tested on tight gas reservoirs. The likelihood of recovery factor was multimodal and non-Gaussian. It also indicates that gas reservoirs are less complex.

Original languageEnglish (US)
Title of host publicationSociety of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010
Pages50-70
Number of pages21
StatePublished - Dec 1 2010
EventSPE Annual Technical Conference and Exhibition 2010, ATCE 2010 - Florence, Italy
Duration: Sep 20 2010Sep 22 2010

Publication series

NameProceedings - SPE Annual Technical Conference and Exhibition
Volume1

Other

OtherSPE Annual Technical Conference and Exhibition 2010, ATCE 2010
CountryItaly
CityFlorence
Period9/20/109/22/10

Fingerprint

Data mining
Recovery
Gases
Linear regression
Flow simulation
Cluster analysis
Oils
Information systems
Regression analysis
Calibration

All Science Journal Classification (ASJC) codes

  • Fuel Technology
  • Energy Engineering and Power Technology

Cite this

Sharma, A., Srinivasan, S., & Lake, L. W. (2010). Classification of oil and gas reservoirs based on recovery factor: A data-mining approach. In Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010 (pp. 50-70). (Proceedings - SPE Annual Technical Conference and Exhibition; Vol. 1).
Sharma, A. ; Srinivasan, Sanjay ; Lake, L. W. / Classification of oil and gas reservoirs based on recovery factor : A data-mining approach. Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010. 2010. pp. 50-70 (Proceedings - SPE Annual Technical Conference and Exhibition).
@inproceedings{60117ba0e398457c8224d3d875b075c7,
title = "Classification of oil and gas reservoirs based on recovery factor: A data-mining approach",
abstract = "Rigorous flow simulations to obtain estimates for recovery are infeasible given many combinations of reservoir and development scenarios. This motivates an alternative approach to calibrate likelihood of recovery using reservoir datasets. A proxy model relating reservoir, well, and operational factors to the ultimate recovery factor could guide subsequent field-scale flow simulations. There are two reservoir datasets that we have used for the classification and estimation of ultimate recovery: the Tertiary Oil Recovery Information System (TORIS) database for oil reservoirs and the Gas Information System (GASIS) database for gas reservoirs. For oil reservoirs, 19 predictor variables were used to estimate the ultimate recovery factor. Cluster analysis was followed by linear regression analysis within the identified clusters that provided a reliable deterministic model for predicting the recovery factor. The linear regression model was compared with the empirical correlations given by Arps et al. (1967) and Guthrie et al. (1995). Analysis showed that geological and engineering parameters are correlated and both are important to the prediction of recovery factor. Later, we used a na{\"i}ve Bayesian approach on principal scores of the predictors for the calibration of recovery factor likelihood. The likelihood function of the recovery factor for oil reservoirs provided the uncertainty in recovery. It was computed to be multimodal and non-Gaussian. In case of the gas reservoirs, good deterministic estimation was achieved by introducing cluster analysis to the data. The robustness of the linear regression model was tested on tight gas reservoirs. The likelihood of recovery factor was multimodal and non-Gaussian. It also indicates that gas reservoirs are less complex.",
author = "A. Sharma and Sanjay Srinivasan and Lake, {L. W.}",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781617389641",
series = "Proceedings - SPE Annual Technical Conference and Exhibition",
pages = "50--70",
booktitle = "Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010",

}

Sharma, A, Srinivasan, S & Lake, LW 2010, Classification of oil and gas reservoirs based on recovery factor: A data-mining approach. in Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010. Proceedings - SPE Annual Technical Conference and Exhibition, vol. 1, pp. 50-70, SPE Annual Technical Conference and Exhibition 2010, ATCE 2010, Florence, Italy, 9/20/10.

Classification of oil and gas reservoirs based on recovery factor : A data-mining approach. / Sharma, A.; Srinivasan, Sanjay; Lake, L. W.

Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010. 2010. p. 50-70 (Proceedings - SPE Annual Technical Conference and Exhibition; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Classification of oil and gas reservoirs based on recovery factor

T2 - A data-mining approach

AU - Sharma, A.

AU - Srinivasan, Sanjay

AU - Lake, L. W.

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Rigorous flow simulations to obtain estimates for recovery are infeasible given many combinations of reservoir and development scenarios. This motivates an alternative approach to calibrate likelihood of recovery using reservoir datasets. A proxy model relating reservoir, well, and operational factors to the ultimate recovery factor could guide subsequent field-scale flow simulations. There are two reservoir datasets that we have used for the classification and estimation of ultimate recovery: the Tertiary Oil Recovery Information System (TORIS) database for oil reservoirs and the Gas Information System (GASIS) database for gas reservoirs. For oil reservoirs, 19 predictor variables were used to estimate the ultimate recovery factor. Cluster analysis was followed by linear regression analysis within the identified clusters that provided a reliable deterministic model for predicting the recovery factor. The linear regression model was compared with the empirical correlations given by Arps et al. (1967) and Guthrie et al. (1995). Analysis showed that geological and engineering parameters are correlated and both are important to the prediction of recovery factor. Later, we used a naïve Bayesian approach on principal scores of the predictors for the calibration of recovery factor likelihood. The likelihood function of the recovery factor for oil reservoirs provided the uncertainty in recovery. It was computed to be multimodal and non-Gaussian. In case of the gas reservoirs, good deterministic estimation was achieved by introducing cluster analysis to the data. The robustness of the linear regression model was tested on tight gas reservoirs. The likelihood of recovery factor was multimodal and non-Gaussian. It also indicates that gas reservoirs are less complex.

AB - Rigorous flow simulations to obtain estimates for recovery are infeasible given many combinations of reservoir and development scenarios. This motivates an alternative approach to calibrate likelihood of recovery using reservoir datasets. A proxy model relating reservoir, well, and operational factors to the ultimate recovery factor could guide subsequent field-scale flow simulations. There are two reservoir datasets that we have used for the classification and estimation of ultimate recovery: the Tertiary Oil Recovery Information System (TORIS) database for oil reservoirs and the Gas Information System (GASIS) database for gas reservoirs. For oil reservoirs, 19 predictor variables were used to estimate the ultimate recovery factor. Cluster analysis was followed by linear regression analysis within the identified clusters that provided a reliable deterministic model for predicting the recovery factor. The linear regression model was compared with the empirical correlations given by Arps et al. (1967) and Guthrie et al. (1995). Analysis showed that geological and engineering parameters are correlated and both are important to the prediction of recovery factor. Later, we used a naïve Bayesian approach on principal scores of the predictors for the calibration of recovery factor likelihood. The likelihood function of the recovery factor for oil reservoirs provided the uncertainty in recovery. It was computed to be multimodal and non-Gaussian. In case of the gas reservoirs, good deterministic estimation was achieved by introducing cluster analysis to the data. The robustness of the linear regression model was tested on tight gas reservoirs. The likelihood of recovery factor was multimodal and non-Gaussian. It also indicates that gas reservoirs are less complex.

UR - http://www.scopus.com/inward/record.url?scp=78651069662&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651069662&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78651069662

SN - 9781617389641

T3 - Proceedings - SPE Annual Technical Conference and Exhibition

SP - 50

EP - 70

BT - Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010

ER -

Sharma A, Srinivasan S, Lake LW. Classification of oil and gas reservoirs based on recovery factor: A data-mining approach. In Society of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2010, ATCE 2010. 2010. p. 50-70. (Proceedings - SPE Annual Technical Conference and Exhibition).