Available online at http://ijcpe.uobaghdad.edu.iq and www.iasj.net Iraqi Journal of Chemical and Petroleum Engineering Vol.23 No.4 (December 2022) 17 – 24 EISSN: 2618-0707, PISSN: 1997-4884 Corresponding Author: Name: Ohood Salman, Email: ohoodthaar@gmail.com IJCPE is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Permeability Prediction in One of Iraqi Carbonate Reservoir Using Statistical, Hydraulic Flow Units, and ANN Methods Ohood Salmana, Omar Al-Fatlawia,b, and Sameer Al-Jawadc a Department of Petroleum Engineering, College of Engineering, University of Baghdad, Baghdad, Iraq b WASM: Energy and Chemical Engineering, Curtin University, WA, Australia c Ministry of Oil/RFD, Baghdad, Iraq Abstract Permeability is an essential parameter in reservoir characterization because it is determined hydrocarbon flow patterns and volume, for this reason, the need for accurate and inexpensive methods for predicting permeability is important. Predictive models of permeability become more attractive as a result. A Mishrif reservoir in Iraq's southeast has been chosen, and the study is based on data from four wells that penetrate the Mishrif formation. This study discusses some methods for predicting permeability. The conventional method of developing a link between permeability and porosity is one of the strategies. The second technique uses flow units and a flow zone indicator (FZI) to predict the permeability of a rock mass using data from cores and well logs. The approach is used to predict the permeability of some uncored wells/intervals. The flow zone indicator is an efficient metric for calculating hydraulic flow units since it is based on the geological properties of the material and varied geometries pore of rock mass (HFU) and Artificial Neural Network (ANN) analysis is another way for predicting permeability. The result shows the FZI method, gave acceptable results compared with the obtained from core analysis than the other methods. Keywords: permeability, FZI, Artificial Neural Network, Mishrif formation. Received on 06/06/2022, Accepted on 10/09/2022, Published on 30/12/2022 https://doi.org/10.31699/IJCPE.2022.4.3 1- Introduction Reservoir characterization approaches are important to provide a better indication of the flow capabilities and storage of petroleum reservoirs [1], especially for heterogeneous carbonate reservoirs [2]. Permeability which reflects the rock's capacity to transmit fluids (oil, gas, and water) through pore spaces, is one of the essential properties of reservoir rocks. Laboratory core analysis can get permeability data on (1.5) in core plugs and sidewall core. However, permeability prediction in uncored sections is crucial because most wells do not core because of challenges during coring and more significant expenses [3]-[5]. One of the essential properties of a petroleum deposit is its permeability. Permeability can be assessed in the laboratory or the field by using core samples or other well-test information [6]. You need to know how permeable the rock is to write an effective reservoir description [7]. Because permeability is recognized as a fundamental quantity that influences reservoir management, well completion, and production methods, it's vital to get it right [8]. Flow zone indicators (FZIs), one of the most used approaches for permeability prediction, identify flow units (groups of rocks) whose elements have particular flow characteristics that are different from those of other units in the rock volume [9]. Artificial Neural Network (ANN) which is the most often used since it does not require any correlations between variables, and neural networks offers a flexible technique to generalize linear regression [10], [11]. Three different methods are used in to estimate permeability Flow Zone Indicator and classical approaches rely on relationship between porosity- permeability, and an artificial neural network (ANN) is using traditional well log and core data to predict permeability [12]. The approach is demonstrated by applying it to one of Iraq's oil fields. Four wells were chosen from field as located at east south of Iraq (XX 1, XX 2, XX 3, XX 4) because they were evenly distributed across the Mishrif formation to assess the reservoir's properties and rock type. The field is one of Iraq's most important oil fields in the southeast. Seismic tests undertaken between 1973 and 1988 discovered the field in the Dhi Qar city. The field is 34 kilometres long and 17 kilometres wide, implying the presence of unfaulted underlying fold structure with a general northwest – southeast trend [13]. The shallowest of Iraq's X field's hydrocarbon-bearing formations is the Mishrif reservoir. Fine to coarse bioclastic limestones exhibit a shallow depositional domain, the average http://ijcpe.uobaghdad.edu.iq/ http://www.iasj.net/ mailto:ohoodthaar@gmail.com http://creativecommons.org/licenses/by-nc/4.0/ https://doi.org/10.31699/IJCPE.2022.4.3 O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 18 thickness of this formation is about 170 m. Mishrif formation consists of two parts: upper part (MA) unit and lower Mishrif (MB) separated by shale. The lower part also subdivided into two reservoir subunits (MB1 and MB2) [14]. 2- Methodology 2.1. Classical method The permeability-porosity relationship is found through core analysis and turned into well-log data. Using the equation below, log-derived porosity in uncored wells or zones is used to figure out empirical permeability [15], [16]. 𝐾 = 𝑎 ∗ 𝑒𝑥𝑝(𝑏𝜙) (1) Where: K: is the permeability (md), ϕ: is the porosity (fraction), and, a and b: are the constants to be fitted to the case study. The link between porosity and permeability was determined from core for MB1 and MB2 Units from four of the wells studied; However, in some cases, the association between core analysis results and porosity and permeability is low because of the heterogeneity of rocks as shown in Fig. 1 and Fig. 2. In the same reservoir, can exits both high and low permeability zone with same porosity values. That requires accurate alternative methods to predict permeability in uncored intervals. Fig. 1. Permeability vs Porosity Cross Plot for MB1 Unit Fig. 2. Permeability vs Porosity Cross Plot for MB2 Unit The results of the correlation between permeability - porosity of Mishrif formation obtained from core analysis are shown in Table 1. Table 1. Classical Permeability Formulas Unit Name Formula Number of core samples (N) (R2) MB1 for all wells K = 0.0129*exp(28.9996*Ø) 201 0.368 MB2 for all wells K = 0.0799*exp(17.64*Ø) 87 0.3062 2.2. Flow Zone indicator This technique is advised for determining the permeability of the reservoir. Based on the hydraulic flow units, core data was categorised by the slope of the linear fitted line between porosity and permeability. This revealed that geological conditions corresponded to each other [16], [17]. The equation is simplified if permeability and porosity are measured in millidarcy and fraction, respectively [18]. 𝑅𝑄𝐼 = 0.0314 ∗ √𝐾 ∅e⁄ (2) It is possible to express the normalized porosity index (∅z) in terms of the porous volume to grain volume ratio (fraction). Ø𝑧 = Øe 1−Øe (3) FZI is given by: 𝐹𝑍𝐼 = 𝑅𝑄𝐼 ∅e (4) RQI vs Øz log-log plots show that the slope of a line connecting all samples with identical FZI values is one, and that the slopes of lines connecting samples with FZI values that are significantly different from the preceding one are all equal to one. It is possible to create a single hydraulic flow unit by aligning samples in a straight line that all have the same pore throat characteristics. For each Hydraulic Flow Unit (HFU), the intercept of this line with Øz = 1 reflects the mean FZI value [19]. Mishrif formation was divided into four HFU or FZI, and four porosity-permeability relations are applied by different equations with powerful correlated factors for each one, as in in Fig. 3 and Fig. 4, the equation results of the regression analysis for the hydraulic flow units are given in Table 2. Table 2. Permeability Formulas for Each HFU FZI Formula R2 FZI_1 K= 710.23*Øeff3.7475 0.8889 FZI_2 K= 1123.7*Øeff 3.3357 0.9359 FZI_3 K = 2624.9Øeff3.1939 0.8873 FZI_4 k= 64471*Øeff3.6175 0.95 O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 19 Fig. 3. Permeability vs. Porosity Cross Plot for Specific FZI Fig. 4. RQI versus. Øz Cross Plot 2.3. Artificial Neural Network An artificial neural network (ANNs) is a computer model that tries to mimic the basic biological learning process and the specialized function of the human nervous system. An adaptive parallel information processing system, it is capable of developing associations and transformations between input and output data input and output the In an ANNs analysis [20]. Artificial neural networks (ANNs) have proven to be an effective method for modeling generic relationships. They've been employed in remote sensing, biomedical engineering, and other fields [21]. ANNs are excellent predictors because they can learn a problem from a small number of samples and their generalizing ability allows them to make predictions based on data that was not included in their training set. ANNs are also stronger than typical prediction methods in dealing with incomplete or noisy data [22]. A training set is created using (water saturation SW, effective porosity PHIE, invasion depth Di, shale volume VSH, variables as inputs and their related permeability values (known from core analysis) as desired outputs to predict permeability by using the ANNs algorithm which build in interactive petrophysical software V4.5. 3- Results and Discussions 1. According to the classical technique and neural network, the permeability of the core data was much lower than the calculated permeability Because it is challenging to establish a simple correlation between porosity and permeability in these formations, it is challenging to identify the permeability of heterogeneous formations using well log data. However, none of these methods can be applied to every case as shown in Fig. 5 and Fig. 6 a plot of prediction permeability versus core permeability of MB1and MB2, which were applied the formulas in Table 1 and in Fig. 7 and Fig. 8 which is represented the permeability estimated by ANNs and permeability by core analysis. Fig. 5. K-core and K –classic for XX_1 O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 20 Fig. 6. K-core and K –classic for XX _2 Fig. 7. K-core and K-ANNs for XX _1 Fig. 8. K-core and K-ANNs for XX _2 2. According to values of FZI four groups were identified in permeability– porosity plot and permeability formula generated for each group. Each of them represent the different type of rock. The generated permeability formulas are applied in uncored wells and intervals depending on the porosity value from the logs. The produced permeability formulas in Table 2 were used in the cored wells (xx-1, xx-2, xx- 3 and xx-4) to compare the estimated permeability values with the measured core values as illustrated in Fig. 9 to Fig. 12. O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 21 Fig. 9. K-core and K-FZI for XX_1 Fig. 10. K-core and K-FZI for XX_2 Fig. 11. K-core and K-FZI for XX_3 Fig. 12. K-core and K-FZI for XX_4 O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 22 4- Conclusion 1. ANNs and classical methods failed to give a good match between calculated permeability and core permeability because due to heterogeneity and variation in pores geometry. 2. The (FZI) gives the best results for permeability prediction because it gave good agreement between the predicted and cored values at most depth intervals of the two units in the wells, so this study has adopted the Flow Zone Indicator (FZI) method to predict permeability in uncored wells/units. 3. Using the FZI approach, Mishrif reservoir is divided into s four HFUs groups with high correlation coefficient (R2) for each (HFU) represents a different type of rock, which has a similar porosity and similar qualities. 4. A method based on HFUs has been developed for better permeability assessment in uncored wells or uncored intervals of otherwise cored wells. The method produces good results when its limitations and applicability range are acknowledged and considered. Nomenclature ANN: Artificial Neural Network FZI: Flow Zone Indicator, μm HFU: Hydraulic flow unit PHIE: effective porosity, fraction Sw: water saturation Di: invasion depth VSH: shale volume RQI: Reservoir Quality Index, μm Symbols k: permeability, md R2: correlation coefficient Øz: normalized porosity, fraction Øe: effective porosity, fraction References [1] D. A. Alobaidi, “Permeability prediction in one of Iraqi carbonate reservoir using hydraulic flow units and neural networks,” Iraqi Journal of Chemical and Petroleum Engineering, vol. 17, no. 1, pp. 1–11, 2016. [2] M. A. Kargarpour, “Carbonate reservoir characterization: an integrated approach,” J Pet Explor Prod Technol, vol. 10, no. 7, pp. 2655–2667, 2020. [3] V. T. Ngo, V. D. Lu, and V. M. Le, “A comparison of permeability prediction methods using core analysis data for sandstone and carbonate reservoirs,” Geomechanics and Geophysics for Geo-Energy and Geo-Resources, vol. 4, no. 2, pp. 129–139, Jun. 2018, doi: 10.1007/s40948-017-0078-y. [4] S. Saffarzadeh and S. R. Shadizadeh, “Reservoir rock permeability prediction using support vector regression in an Iranian oil field,” Journal of Geophysics and Engineering, vol. 9, no. 3, pp. 336– 344, Jun. 2012, doi: 10.1088/1742-2132/9/3/336. [5] M. M. Hossain, O. Al-Fatlawi, D. Brown, and M. Ajeel, “Numerical approach for the prediction of formation and hydraulic fracture properties considering elliptical flow regime in tight gas reservoirs,” 2018. [6] H. Mahmood and O. Al-Fatlawi, “Construction of Comprehensive Geological Model for an Iraqi Oil Reservoir,” Iraqi Geological Journal, vol. 54, no. 2F, pp. 22–35, Dec. 2021, doi: 10.46717/igj.54.2f.3ms- 2021-12-20. [7] B. Rafik and B. Kamel, “Prediction of permeability and porosity from well log data using the nonparametric regression with multivariate analysis and neural network, Hassi R’Mel Field, Algeria,” Egyptian Journal of Petroleum, vol. 26, no. 3, pp. 763–778, 2017, doi: 10.1016/j.ejpe.2016.10.013. [8] W. Mustafa Al-Qattan and A. Habeeb Al Mohammed, “Permeability Prediction by Classical and Flow Zone Indictor (FZI) Methods for an Iraqi Gas Field,” Iraqi Journal of Chemical and Petroleum Engineering, vol. 18, no. 3, pp. 59–65, 2017. [9] H. Abdulelah, S. Mahmood, and G. Hamada, “Hydraulic flow units for reservoir characterization: A successful application on arab-d carbonate,” in IOP Conference Series: Materials Science and Engineering, Jul. 2018, vol. 380, no. 1. doi: 10.1088/1757-899X/380/1/012020. [10] K. Aminian, S. Ameri, A. Oyerokun, and B. Thomas, “Prediction of flow units and permeability using artificial neural networks,” 2003. [11] M. AlJuboori, M. Hossain, O. Al-Fatlawi, A. Kabir, and A. Radhi, “Numerical simulation of gas lift optimization using genetic algorithm for a Middle East oil field: feasibility study,” 2020. [12] A. A. Ramadhan and A. J. Mahmood, “Petrophysical Properties and Well Log Interpretations of Tertiary Reservoir in Khabaz Oil Field/Northern Iraq,” Journal of Engineering, vol. 26, no. 6, pp. 18–34, 2020. [13] G. Jreou, “A Preliminary Study to Evaluate Mishrif Carbonate Reservoir of Nasiriya Oil Field Gas condensate Reservoirs View project Reservoir Management View project,” 2013. [14] H. D. Khalaf, “Enhancement of Oil Production from Mishrif Reservoir in Nasiriyah Oil Field OF BAGHDAD IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF SCIENCE IN PETROLEUM ENGINEERING,” 2009. [15] Y. N. A. Majeed, A. A. Ramadhan, and A. J. Mahmood, “Comparing between permeability prediction by using classical and FZI methods/Tertiary Reservoir in Khabaz Oil Field/Northern Iraq,” Iraqi Journal of Oil & Gas Research, vol. 2, no. 1, 2022. https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/85 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/85 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/85 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/85 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/85 https://link.springer.com/article/10.1007/s13202-020-00946-w https://link.springer.com/article/10.1007/s13202-020-00946-w https://link.springer.com/article/10.1007/s13202-020-00946-w https://link.springer.com/article/10.1007/s13202-020-00946-w https://link.springer.com/article/10.1007/s40948-017-0078-y https://link.springer.com/article/10.1007/s40948-017-0078-y https://link.springer.com/article/10.1007/s40948-017-0078-y https://link.springer.com/article/10.1007/s40948-017-0078-y https://link.springer.com/article/10.1007/s40948-017-0078-y https://link.springer.com/article/10.1007/s40948-017-0078-y https://academic.oup.com/jge/article/9/3/336/5127392 https://academic.oup.com/jge/article/9/3/336/5127392 https://academic.oup.com/jge/article/9/3/336/5127392 https://academic.oup.com/jge/article/9/3/336/5127392 https://academic.oup.com/jge/article/9/3/336/5127392 https://onepetro.org/OTCASIA/proceedings-abstract/18OTCA/2-18OTCA/D021S007R004/179519 https://onepetro.org/OTCASIA/proceedings-abstract/18OTCA/2-18OTCA/D021S007R004/179519 https://onepetro.org/OTCASIA/proceedings-abstract/18OTCA/2-18OTCA/D021S007R004/179519 https://onepetro.org/OTCASIA/proceedings-abstract/18OTCA/2-18OTCA/D021S007R004/179519 https://onepetro.org/OTCASIA/proceedings-abstract/18OTCA/2-18OTCA/D021S007R004/179519 https://igj-iraq.org/igj/index.php/igj/article/view/594 https://igj-iraq.org/igj/index.php/igj/article/view/594 https://igj-iraq.org/igj/index.php/igj/article/view/594 https://igj-iraq.org/igj/index.php/igj/article/view/594 https://igj-iraq.org/igj/index.php/igj/article/view/594 https://www.sciencedirect.com/science/article/pii/S1110062116300290 https://www.sciencedirect.com/science/article/pii/S1110062116300290 https://www.sciencedirect.com/science/article/pii/S1110062116300290 https://www.sciencedirect.com/science/article/pii/S1110062116300290 https://www.sciencedirect.com/science/article/pii/S1110062116300290 https://www.sciencedirect.com/science/article/pii/S1110062116300290 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/66 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/66 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/66 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/66 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/66 https://iopscience.iop.org/article/10.1088/1757-899X/380/1/012020/meta https://iopscience.iop.org/article/10.1088/1757-899X/380/1/012020/meta https://iopscience.iop.org/article/10.1088/1757-899X/380/1/012020/meta https://iopscience.iop.org/article/10.1088/1757-899X/380/1/012020/meta https://iopscience.iop.org/article/10.1088/1757-899X/380/1/012020/meta https://iopscience.iop.org/article/10.1088/1757-899X/380/1/012020/meta https://onepetro.org/SPEWRM/proceedings-abstract/03WRM/All-03WRM/SPE-83586-MS/137416 https://onepetro.org/SPEWRM/proceedings-abstract/03WRM/All-03WRM/SPE-83586-MS/137416 https://onepetro.org/SPEWRM/proceedings-abstract/03WRM/All-03WRM/SPE-83586-MS/137416 https://onepetro.org/IPTCONF/proceedings-abstract/20IPTC/3-20IPTC/D031S095R001/154786 https://onepetro.org/IPTCONF/proceedings-abstract/20IPTC/3-20IPTC/D031S095R001/154786 https://onepetro.org/IPTCONF/proceedings-abstract/20IPTC/3-20IPTC/D031S095R001/154786 https://onepetro.org/IPTCONF/proceedings-abstract/20IPTC/3-20IPTC/D031S095R001/154786 https://www.iasj.net/iasj/download/d557fdbeb53c9af7 https://www.iasj.net/iasj/download/d557fdbeb53c9af7 https://www.iasj.net/iasj/download/d557fdbeb53c9af7 https://www.iasj.net/iasj/download/d557fdbeb53c9af7 https://www.iasj.net/iasj/download/d557fdbeb53c9af7 https://www.researchgate.net/profile/Yousif-Abdul-Majeed-2/publication/359823742_Comparing_between_permeability_prediction_by_using_classical_and_FZI_methodsTertiary_Reservoir_in_Khabaz_Oil_Field_Northern_Iraq_Iraqi_Journal_of_Oil_Gas_Research/links/6250c74def013420666258ca/Comparing-between-permeability-prediction-by-using-classical-and-FZI-methods-Tertiary-Reservoir-in-Khabaz-Oil-Field-Northern-Iraq-Iraqi-Journal-of-Oil-Gas-Research.pdf https://www.researchgate.net/profile/Yousif-Abdul-Majeed-2/publication/359823742_Comparing_between_permeability_prediction_by_using_classical_and_FZI_methodsTertiary_Reservoir_in_Khabaz_Oil_Field_Northern_Iraq_Iraqi_Journal_of_Oil_Gas_Research/links/6250c74def013420666258ca/Comparing-between-permeability-prediction-by-using-classical-and-FZI-methods-Tertiary-Reservoir-in-Khabaz-Oil-Field-Northern-Iraq-Iraqi-Journal-of-Oil-Gas-Research.pdf https://www.researchgate.net/profile/Yousif-Abdul-Majeed-2/publication/359823742_Comparing_between_permeability_prediction_by_using_classical_and_FZI_methodsTertiary_Reservoir_in_Khabaz_Oil_Field_Northern_Iraq_Iraqi_Journal_of_Oil_Gas_Research/links/6250c74def013420666258ca/Comparing-between-permeability-prediction-by-using-classical-and-FZI-methods-Tertiary-Reservoir-in-Khabaz-Oil-Field-Northern-Iraq-Iraqi-Journal-of-Oil-Gas-Research.pdf https://www.researchgate.net/profile/Yousif-Abdul-Majeed-2/publication/359823742_Comparing_between_permeability_prediction_by_using_classical_and_FZI_methodsTertiary_Reservoir_in_Khabaz_Oil_Field_Northern_Iraq_Iraqi_Journal_of_Oil_Gas_Research/links/6250c74def013420666258ca/Comparing-between-permeability-prediction-by-using-classical-and-FZI-methods-Tertiary-Reservoir-in-Khabaz-Oil-Field-Northern-Iraq-Iraqi-Journal-of-Oil-Gas-Research.pdf https://www.researchgate.net/profile/Yousif-Abdul-Majeed-2/publication/359823742_Comparing_between_permeability_prediction_by_using_classical_and_FZI_methodsTertiary_Reservoir_in_Khabaz_Oil_Field_Northern_Iraq_Iraqi_Journal_of_Oil_Gas_Research/links/6250c74def013420666258ca/Comparing-between-permeability-prediction-by-using-classical-and-FZI-methods-Tertiary-Reservoir-in-Khabaz-Oil-Field-Northern-Iraq-Iraqi-Journal-of-Oil-Gas-Research.pdf https://www.researchgate.net/profile/Yousif-Abdul-Majeed-2/publication/359823742_Comparing_between_permeability_prediction_by_using_classical_and_FZI_methodsTertiary_Reservoir_in_Khabaz_Oil_Field_Northern_Iraq_Iraqi_Journal_of_Oil_Gas_Research/links/6250c74def013420666258ca/Comparing-between-permeability-prediction-by-using-classical-and-FZI-methods-Tertiary-Reservoir-in-Khabaz-Oil-Field-Northern-Iraq-Iraqi-Journal-of-Oil-Gas-Research.pdf O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 23 [16] J. O. Amaefule, M. Altunbay, D. G. Kersey, and D. K. Keelan, “SPE 26436 Enhanced Reservoir Description: Using Core and Log Data to Identify Hydraulic (Flow) Units and Predict Permeability in Uncored Intervals/Wells,” 1993. [17] A. A. Bhatti et al., “Permeability prediction using hydraulic flow units and electrofacies analysis,” Energy Geoscience, vol. 1, no. 1–2, pp. 81–91, 2020. [18] S. N. Al-Jawad and A. H. Saleh, “Flow units and rock type for reservoir characterization in carbonate reservoir: case study, south of Iraq,” J Pet Explor Prod Technol, vol. 10, no. 1, pp. 1–20, Jan. 2020, doi: 10.1007/s13202-019-0736-4. [19] H. Ali Baker, S. Noori AL-Jawad, and Z. Imad Murtadha, “Permeability Prediction in Carbonate Reservoir Rock Using FZI,” Iraqi Journal of Chemical and Petroleum Engineering, vol. 14, no. 3, pp. 49–54, 2013. [20] S. Mohaghegh, R. Arefi, L. Bilgesu, S. Ameri, D. Rose, and V. U. West, “Design and Development of an Artificial Neural Network for Estimation of Formation Permeability,” 1995. [21] O. Isaac Abiodun, A. Jantan, A. Esther Omolara, K. Victoria Dada, N. AbdElatif Mohamed, and H. Arshad, “State-of-the-art in artificial neural network applications: A survey,” Heliyon, vol. 4, p. 938, 2018, doi: 10.1016/j.heliyon.2018. [22] Z. Huang, J. Shimeld, M. Williamson, and J. Katsube, “Permeability prediction with artificial neural network modeling in the Venture gas field, offshore eastern Canada,” GEOPHYSICS, vol. 61, no. 2, pp. 422–436, Mar. 1996, doi: 10.1190/1.1443970. https://onepetro.org/SPEATCE/proceedings-abstract/93SPE/All-93SPE/SPE-26436-MS/55155 https://onepetro.org/SPEATCE/proceedings-abstract/93SPE/All-93SPE/SPE-26436-MS/55155 https://onepetro.org/SPEATCE/proceedings-abstract/93SPE/All-93SPE/SPE-26436-MS/55155 https://onepetro.org/SPEATCE/proceedings-abstract/93SPE/All-93SPE/SPE-26436-MS/55155 https://onepetro.org/SPEATCE/proceedings-abstract/93SPE/All-93SPE/SPE-26436-MS/55155 https://www.sciencedirect.com/science/article/pii/S2666759220300056 https://www.sciencedirect.com/science/article/pii/S2666759220300056 https://www.sciencedirect.com/science/article/pii/S2666759220300056 https://link.springer.com/article/10.1007/s13202-019-0736-4 https://link.springer.com/article/10.1007/s13202-019-0736-4 https://link.springer.com/article/10.1007/s13202-019-0736-4 https://link.springer.com/article/10.1007/s13202-019-0736-4 https://link.springer.com/article/10.1007/s13202-019-0736-4 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/318 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/318 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/318 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/318 https://ijcpe.uobaghdad.edu.iq/index.php/ijcpe/article/view/318 https://onepetro.org/CA/article-abstract/7/06/151/70238/Design-and-Development-of-An-Artificial-Neural https://onepetro.org/CA/article-abstract/7/06/151/70238/Design-and-Development-of-An-Artificial-Neural https://onepetro.org/CA/article-abstract/7/06/151/70238/Design-and-Development-of-An-Artificial-Neural https://onepetro.org/CA/article-abstract/7/06/151/70238/Design-and-Development-of-An-Artificial-Neural https://www.sciencedirect.com/science/article/pii/S2405844018332067 https://www.sciencedirect.com/science/article/pii/S2405844018332067 https://www.sciencedirect.com/science/article/pii/S2405844018332067 https://www.sciencedirect.com/science/article/pii/S2405844018332067 https://www.sciencedirect.com/science/article/pii/S2405844018332067 https://library.seg.org/doi/abs/10.1190/1.1443970 https://library.seg.org/doi/abs/10.1190/1.1443970 https://library.seg.org/doi/abs/10.1190/1.1443970 https://library.seg.org/doi/abs/10.1190/1.1443970 https://library.seg.org/doi/abs/10.1190/1.1443970 O. Salman et al. / Iraqi Journal of Chemical and Petroleum Engineering 23,4 (2022) 17 - 24 24 وحدات و يةالتنبؤ بالنفاذية في أحد مكامن الكاربونية العراقية باستخدام الطرق التقليد التدفق الهيدروليكي وطرق الشبكة العصبية االصطناعية 3سمير الجواد و 1,2عمر فالح حسن ,1عهود سلمان غدادبجامعة -كلية الهندسة -النفط قسم هندسة ١ جامعة كيرتن ٢ وزارة النفط العراقية ٣ الخالصة يةةةةحم ت ديةةةةد فق ةةةةا تةةةةدف فةةةة ت اةةةةي ال ن ةةةةن أل ةةةةن ر هةةةةا األساسةةةةية هةةةة مةةةةن ال عل مةةةةا النفاذيةةةةة م تة. مه ةة للغايةةمنلفةة للحن ةب بالنفاذيةة ، فةن ال اجةة ىلةر ةري دقي ةة و يةرالهيدروكرب وحج ه، ولهةاا السة اخحيار من ةن مرةرف فة جنة ق اةري العةراي هت ةال هةاة الدراسةة، واسةحند الدراسةة ىلةر بياقةا مةن فربعةة بةار ر الطر ةةة اهولةةر هةة الطر ةةة الح ليديةةة لحطةة ، تنةةاقه هةةاة الدراسةةة ةةدة ةةري للحن ةةب بالنفاذيةةة. تخحةةري ال ن ةةن خ ر والطر ةة الااقيةة هة باه ح ةاد لةر كحلةة الصة .اهسةحراتيجيا الصلة بين النفاذية وال سامية ه واحةدة مةن بنة و ر ةة فخةرل للحن ةب بالنفاذيةة هة بالرة .رال ياقا من اللباق وسجال اآلبةاومبار منط ة الحدف باسحخدال .العص ية اهاطناعية حدف الهيدرولين ألقهفظهر النحائج ف ر ة مبار منط ة الحدف ه مقياس فعال ل ساق وحدا ال قد و ل م ارقة بالطري األخر يعح د لر الخصائص الجي ل جية لل ادة وهندسة ال سال ال حن ة لكحلة الصخ ر .اظهر قحائج م لة ل ساق النفاذية م ارقة بالطري اهخرل .النفاذية، مبار منط ة الحدف ، الربنة العص ية اهاطناعية: الدالة الكل ا