Prediction of oil reservoir porosity based on BP-ANN

Hossein Hamidi; Roozbeh Rafati

doi:10.1109/ICIMTR.2012.6236396

Prediction of oil reservoir porosity based on BP-ANN

Hossein Hamidi, Roozbeh Rafati

Engineering

Research output: Contribution to conference › Paper › peer-review

5 Citations (Scopus)

Abstract

Porosity of oil reservoir rock is usually determined by Core Analysis. But this method is expensive and time consuming. Also because of lithology changes, heterogeneity of reservoir rock, and nonexistence of sufficient well cores, determination of the parameters by the usual methods is not accurate. So the best way to decrease cost, increase accuracy, and decrease time is applying advanced software such as Geolog and Back-Propagation of Error Artificial Neural Network (BP-ANN). In this paper, a BP-ANN was designed to predict the porosity of formations using the well logs data in Parsi field, located in southwest of Iran. The data of two wells (No. 33 and No. 19) that have core data were used for training, testing, validation, and generalization processes. Then the BP-ANN results were compared to evaluations obtained from Geolog Software (GS). With respect to the results, it was concluded that the BP-ANN is more accurate than GS in determining oil reservoir porosity. At the end, porosity was simulated in three other wells (No. 48, 49, and 64) that lack core data.

Original language	English
Pages	241-246
Number of pages	6
DOIs	https://doi.org/10.1109/ICIMTR.2012.6236396
Publication status	Published - 2012
Event	Innovation Management and Technology Research (ICIMTR), 2012 International Conference on - Duration: 21 May 2012 → 22 May 2012

Conference

Conference	Innovation Management and Technology Research (ICIMTR), 2012 International Conference on
Period	21/05/12 → 22/05/12

Access to Document

10.1109/ICIMTR.2012.6236396Licence: Unspecified

Fingerprint Dive into the research topics of 'Prediction of oil reservoir porosity based on BP-ANN'. Together they form a unique fingerprint.

Cite this

@conference{87ec4196876a4dad826c64264f38b29d,

title = "Prediction of oil reservoir porosity based on BP-ANN",

abstract = "Porosity of oil reservoir rock is usually determined by Core Analysis. But this method is expensive and time consuming. Also because of lithology changes, heterogeneity of reservoir rock, and nonexistence of sufficient well cores, determination of the parameters by the usual methods is not accurate. So the best way to decrease cost, increase accuracy, and decrease time is applying advanced software such as Geolog and Back-Propagation of Error Artificial Neural Network (BP-ANN). In this paper, a BP-ANN was designed to predict the porosity of formations using the well logs data in Parsi field, located in southwest of Iran. The data of two wells (No. 33 and No. 19) that have core data were used for training, testing, validation, and generalization processes. Then the BP-ANN results were compared to evaluations obtained from Geolog Software (GS). With respect to the results, it was concluded that the BP-ANN is more accurate than GS in determining oil reservoir porosity. At the end, porosity was simulated in three other wells (No. 48, 49, and 64) that lack core data.",

author = "Hossein Hamidi and Roozbeh Rafati",

year = "2012",

doi = "10.1109/ICIMTR.2012.6236396",

language = "English",

pages = "241--246",

note = "Innovation Management and Technology Research (ICIMTR), 2012 International Conference on ; Conference date: 21-05-2012 Through 22-05-2012",

}

TY - CONF

T1 - Prediction of oil reservoir porosity based on BP-ANN

AU - Hamidi, Hossein

AU - Rafati, Roozbeh

PY - 2012

Y1 - 2012

N2 - Porosity of oil reservoir rock is usually determined by Core Analysis. But this method is expensive and time consuming. Also because of lithology changes, heterogeneity of reservoir rock, and nonexistence of sufficient well cores, determination of the parameters by the usual methods is not accurate. So the best way to decrease cost, increase accuracy, and decrease time is applying advanced software such as Geolog and Back-Propagation of Error Artificial Neural Network (BP-ANN). In this paper, a BP-ANN was designed to predict the porosity of formations using the well logs data in Parsi field, located in southwest of Iran. The data of two wells (No. 33 and No. 19) that have core data were used for training, testing, validation, and generalization processes. Then the BP-ANN results were compared to evaluations obtained from Geolog Software (GS). With respect to the results, it was concluded that the BP-ANN is more accurate than GS in determining oil reservoir porosity. At the end, porosity was simulated in three other wells (No. 48, 49, and 64) that lack core data.

AB - Porosity of oil reservoir rock is usually determined by Core Analysis. But this method is expensive and time consuming. Also because of lithology changes, heterogeneity of reservoir rock, and nonexistence of sufficient well cores, determination of the parameters by the usual methods is not accurate. So the best way to decrease cost, increase accuracy, and decrease time is applying advanced software such as Geolog and Back-Propagation of Error Artificial Neural Network (BP-ANN). In this paper, a BP-ANN was designed to predict the porosity of formations using the well logs data in Parsi field, located in southwest of Iran. The data of two wells (No. 33 and No. 19) that have core data were used for training, testing, validation, and generalization processes. Then the BP-ANN results were compared to evaluations obtained from Geolog Software (GS). With respect to the results, it was concluded that the BP-ANN is more accurate than GS in determining oil reservoir porosity. At the end, porosity was simulated in three other wells (No. 48, 49, and 64) that lack core data.

U2 - 10.1109/ICIMTR.2012.6236396

DO - 10.1109/ICIMTR.2012.6236396

M3 - Paper

SP - 241

EP - 246

T2 - Innovation Management and Technology Research (ICIMTR), 2012 International Conference on

Y2 - 21 May 2012 through 22 May 2012

ER -