Towards Better Estimations of Rock Mechanical Properties Integrating Machine Learning Techniques for Application to Hydraulic Fracturing
- Yiwen Gong (The Ohio State University) | Mohamed Mehana (Earth and Environmental Sciences Division, Los Alamos National Laboratory, Los Alamos, USA) | Fengyang Xiong (The Ohio State University) | Feng Xu (Research Institute of Petroleum Exploration and Development CO., LTD, CNPC; China National Oil and Gas Exploration and Development Corporation) | Ilham El-Monier (The Ohio State University)
- Document ID
- Society of Petroleum Engineers
- SPE Annual Technical Conference and Exhibition, 30 September - 2 October, Calgary, Alberta, Canada
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Petroleum Engineers
- Mechanical Rock Properties, Microcrack Density, Rock Elastic Moduli Estimation, Fracture Roughness, Data Mining
- 188 in the last 30 days
- 189 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 9.50|
|SPE Non-Member Price:||USD 28.00|
Rock elastic moduli are one of the major perspectives for the hydraulic fracturing design. Among all of them, Young's modulus and Poisson's ratio essentially control fracture aperture for the proppant placement. The objective of this work is to predict the elastic moduli by applying data mining techniques as a comparison to the experimental measurements. We have collected attributes representing the pore structure, mineralogy and geomechanical characteristics. We implemented classification techniques such as k-means, hierarchical and PAM (partition around medoids). PAM results in more evenly-distributed clusters compared to the rest. Artificial Neural Network (ANN) is used for regression. We formulated two scenarios; firstly, all the data is grouped into one group and the other involves performing the regression on the clustered data. Interestingly, both scenarios yield acceptable results. The classification results could guide the fracturing operations where clusters with high brittleness, low anisotropy and high microfracture intensity could be identified as fracture candidates. Still the main limitation to unleash the machine learning capabilities in this domain is the data scarcity
|File Size||1 MB||Number of Pages||13|
Birkle, Peter, 2016. Recovery rates of fracturing fluids and provenance of produced water from hydraulic fracturing of Silurian Qusaiba hot shale, northern Saudi Arabia, with implications on fracture network. AAPG Bull. 100 (6): 917-941. DOI: https://doi.org/10.1306/02101615120
Gong, Y., El-monier, I., 2018. Quantification of Fracture Surface Roughness and Its Insights to Mechanical Rock Properties Determination Using Image Analysis Techniques. SPE, Pittsburgh, PA. https://doi.org/https://doi.org/10.2118/191824-18ERM-MS
Gong, Y.; Mehana, M.; Monier, I.; Xu, F.; Xiong, F., 2019. Machine learning for estimating rock mechanical properties beyond traditional considerations. Unconventional Resources Technology Conference, Denver, Cololado, USA. DOI: 10.15530/urtec-2019-1234.
Kuila, U., Prasad, M., 2013. Specific surface area and pore-size distribution in clays and shales. Geophysical Prospecting 61, 341-362. https://doi.org/10.1111/1365-2478.12028
Martins, F.F.; Miranda, T.F.S., 2012. Estimation of the rock deformation modulus and RMR based on Data Mining techniques. Geotech Geol. Eng. 30: 787. https://doi.org/10.1007/s10706-012-9498-1.
McCulloch, Warren; Walter Pitts, 1943. A Logical Calculus of Ideas Immanent in Nervous Activity. Bull. Math. Biophy. 5 (4): 115-133. DOI: 10.1007/BF02478259.
Ocak, I. and Seker, S.E., 2012. Estimation of elastic modulus of intact rocks by Artificial Neural Network. Rock Mech. Rock Eng. 45: 1047. DOI: https://doi.org/10.1007/s00603-012-0236-z.
Thomsen, L., 1986. Weak elastic anisotropy. GEOPHYSICS 51. https://doi.org/http://dx.doi.org/10.1190/1.1442051
Verma, S.; Zhao, T.; Marfurt, K.J.; Devegowda, D., 2016. Estimation of total organic carbon and brittleness volume. Interp. 4(3): T373-T385. DOI: https://doi.org/10.1190/INT-2015-0166.1.