Supervised Machine Learning and Multiple Regression Approach to Predict Successfulness of Matrix Acidizing in Hydraulic Fractured Sandstone Formation

  • Candra Kurniawan PT Medco E&P, The Energy Building, SCBD Lot 11A, Jl. Jendral Sudirman Kav 52-53 Jakarta 12190, Indonesia
  • Muhammad Mufti Azis Department of Chemical Engineering, Faculty of Engineering, Universitas Gadjah Mada, Jl. Grafika No. 2, Yogyakarta, 55281, Indonesia.
  • Teguh Ariyanto Department of Chemical Engineering, Faculty of Engineering, Universitas Gadjah Mada, Jl. Grafika No. 2, Yogyakarta, 55281, Indonesia.
Keywords: Matrix Acidizing, Sandstone, Machine Learning, PCR, PLS-R

Abstract

The success rate of matrix acidizing in hydraulic fractured sandstone formation is less than 55%, much lower compared to the more than 91% success rate in carbonate formation. The need for alternative approaches to help the success ratio in matrix acidizing is crucial. This paper demonstrates a modeling technique to improve the success ratio of matrix acidizing in a hydraulic fractured sandstone formation. Supervised machine learning with 4 models of a neural network, logistic regression, tree, and random forest was selected to predict the successfulness of matrix acidizing in hydraulic fracturing. In parallel, multivariate analysis of principal component regression and partial least square regression approach were utilized to predict the oil gain of the job. For qualitative prediction, the results showed that the random forest was the best model to predict the successfulness of the job with the area under the curve (AUC) of 0.68 and precision of 0.73 in the training model with 70% of the data. Subsequently, the validation test with the rest of the data (30% data) gave 0.51 AUC and 61% precision. For quantitative prediction, the net oil gain was evaluated by using principal component regression (PCR) and partial least square regression (PLS-R). The PCR and PLS-R model gave a coefficient of determination (Rsquare) of 0.22 and 0.35, respectively. The p-value of PLS-R was 0.047 (95% confidence interval) which indicates that the model is significant. The results of this work demonstrate the potential application of supervised machine learning, principal component regression, and partial least square regression to improve candidate selection of oil wells for matrix acidizing especially in hydraulic fractured wells with limited design data.

 

References

Al-Harbi, B.G., 2012. Evaluation of Organic-Hydrofluoric Acid Mixtures for Sandstone Acidizing. Thesis.

Alhamad, L., Alrashed, A., Al Munif, E., Miskimins, J., 2020. A review of organic acids roles in acidizing operations for carbonate and sandstone formations. In: Proceedings - SPE International Symposium on Formation Damage Control. p. 34.

Begdache, L., Kianmehr, H., Sabounchi, N., Marszalek, A., Dolma, N., Watson, T.J., Science, A., 2019. Principal component regression of academic performance, substance use and sleep quality in relation to risk of anxiety and depression in young adults. Trends Neurosci. Educ. 15, 29–37.

Eaton, P., Frank, B., Johnson, K., Willoughby, S., 2019. Comparing exploratory factor models of the Brief Electricity and Magnetism Assessment and the Conceptual Survey of Electricity and Magnetism. In: Physical Review Physics Education Research. American Physical Society, p. 11.

Ehrenberg, S.N., Nadeau, P.H., 2005. Sandstone vs. carbonate petroleum reservoirs: A global perspective on porosity-depth and porosity-permeability relationships. Am. Assoc. Pet. Geol. Bull. 89, 435–445.

Ghozali, imam, 2018. Aplikasi analisis multivariate dengan program SPSS, 9th ed, Badan Penerbit Universitas Diponogoro Semarang. Badan Penerbit Universitas Diponegoro, Semarang.

Hatcher, L., 2013. Advanced Statistics in Research. Shadow Finch Media, p. 26.

Joshi, K., Patil, B., 2020. Prediction of Surface Roughness by Machine Vision using Principal Prediction of Surface Roughness Machine Analysis Vision using Principal Components based by Regression Components based Regression Analysis. Procedia Comput. Sci. 167, 382–391.

Kalfayan, L., 2008. Production Enhancement with Acid Stimulation 2nd Ed. PennWell, Tulsa,Oklahoma, p. 252.

Mahmoud, M.A., Nasr-El-Din, H.A., De Wolf, C.A., Alex, A.K., 2011. Sandstone acidizing using a new class of chelating agents. Proc. - SPE Int. Symp. Oilf. Chem. 1, 1–17.

Mandrekar, J.N., 2010. Receiver Operating Characteristic Curve in Diagnostic Test Assessment. J. Thorac. Oncol. 5, 1315–1316.

Montgomery, D.C., 2013. Fitting Regression Models. In: Design and Analysis of Experiments Eighth Edition. Arizona State University. John Wiley & Sons, Inc., pp. 449–475.

Ramón, J.C., Cross, T., 1997. Characterization and prediction of reservoir architecture and petrophysical properties in fluvial channel sandstones, middle Magdalena Basin, Colombia. CT y F - Ciencia, Tecnol. y Futur. 1, 19–46.

Shafiq, M.U., 2018. Study of Different Acid Reaction Mechanisms during Matrix Acidizing. Curtin University.

Sidaoui, Z., Abdulraheem, A., Abbad, M., 2018. Prediction of optimum injection rate for carbonate acidizing using machine learning. In: Society of Petroleum Engineers - SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition 2018, SATS 2018. p. 12.

Tague, J.R., 2000. Multivariate Statistical Analysis Improves Formation Damage Remediation. In: SPE Annual Technical Conference and Exhibition. pp. 1–8.

Uddin, S., Khan, A., Hossain, M.E., Moni, M.A., 2019. Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inform. Decis. Mak. 19, 1–16.

Zhang, G.Q., Chen, M., 2010. Dynamic fracture propagation in hydraulic re-fracturing. J. Pet. Sci. Eng. 70, 266–272.

Published
2023-06-30
How to Cite
Kurniawan, C., Azis, M. M., & Ariyanto, T. (2023). Supervised Machine Learning and Multiple Regression Approach to Predict Successfulness of Matrix Acidizing in Hydraulic Fractured Sandstone Formation. ASEAN Journal of Chemical Engineering, 23(1), 113-127. Retrieved from https://journal.ugm.ac.id/v3/AJChE/article/view/9277
Section
Articles