AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Petroleum Science Article
PDF (7.4 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Original Paper | Open Access

Machine learning for carbonate formation drilling: Mud loss prediction using seismic attributes and mud loss records

Hui-Wen Panga,b, Han-Qing Wangc, Yi-Tian Xiaoc, Yan Jina,d( ), Yun-Hu Lua,d, Yong-Dong Fana,d, Zhen Niee
National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing), Beijing, 102249, China
College of Science, China University of Petroleum-Beijing, Beijing, 102249, China
Petroleum Exploration and Production Research Institute, SINOPEC, Beijing, 102206, China
College of Petroleum Engineering, China University of Petroleum-Beijing, Beijing, 102249, China
Research Institute of Petroleum Exploration and Development, CNPC, Beijing, 100083, China

Edited by Jia-Jia Fei

Show Author Information

Abstract

Due to the complexity and variability of carbonate formation leakage zones, lost circulation prediction and control is one of the major challenges of carbonate drilling. It raises well-control risks and production expenses. This research utilizes the H oilfield as an example, employs seismic features to analyze mud loss prediction, and produces a complete set of pre-drilling mud loss prediction solutions. Firstly, 16 seismic attributes are calculated based on the post-stack seismic data, and the mud loss rate per unit footage is specified. The sample set is constructed by extracting each attribute from the seismic trace surrounding 15 typical wells, with a ratio of 8:2 between the training set and the test set. With the calibration results for mud loss rate per unit footage, the nonlinear mapping relationship between seismic attributes and mud loss rate per unit size is established using the mixed density network model. Then, the influence of the number of sub-Gausses and the uncertainty coefficient on the model's prediction is evaluated. Finally, the model is used in conjunction with downhole drilling conditions to assess the risk of mud loss in various layers and along the wellbore trajectory. The study demonstrates that the mean relative errors of the model for training data and test data are 6.9% and 7.5%, respectively, and that R2 is 90% and 88%, respectively, for training data and test data. The accuracy and efficacy of mud loss prediction may be greatly enhanced by combining 16 seismic attributes with the mud loss rate per unit footage and applying machine learning methods. The mud loss prediction model based on the MDN model can not only predict the mud loss rate but also objectively evaluate the prediction based on the quality of the data and the model.

Keywords

Lost circulationRisk predictionMachine learningSeismic attributesMud loss records

References

 

Abbas, A.K., Bashikh, A.A., Abbas, H., et al., 2019. Intelligent decisions to stop or mitigate lost circulation based on machine learning. Energy 183, 1104–1113. https://doi.org/10.1016/j.energy.2019.07.020.
Crossref Google Scholar
 

Ali, P.J.M., Faraj, R.H., Koya, E., et al., 2014. Data normalization and standardization: a technical report. Mach Learn Tech Rep 1 (1), 1–6.
Crossref Google Scholar
 

Anderson, R.A., Ingram, D.S., Zanier, A.M., 1973. Determining fracture pressure gradients from well logs. J. Petrol. Technol. 25 (11), 1259–1268. https://doi.org/10.2118/4135-PA.
Crossref Google Scholar
 

Ahdaya, M., Al Brahim, A., Bai, B., et al., 2022. Low-temperature recrosslinkable preformed particle gel as a material for lost circulation control. SPE J. 1–11. https://doi.org/10.2118/209783-PA.
Crossref Google Scholar
 
Bishop, C.M., 1994. Mixture Density Networks. Technical Report NCRG/97/004, Neural Computing Research Group. Aston University.
 

Brown, A.R., 1996. Seismic attributes and their classification. Lead. Edge 15 (10), 1090. https://doi.org/10.1190/1.1437208.
Crossref Google Scholar
 
Chan, A.W., Hauser, M., Couzens-Schultz, B.A., et al., 2013. An alternative interpretation of leakoff and lost circulation pressure measurements. In: The 47th U.S. Rock Mechanics/Geomechanics Symposium, 23–26 June. ARMA-2013-302.
Crossref
 

Chen, Q., Sidney, S., 1997. Seismic attribute technology for reservoir forecasting and monitoring. Lead. Edge 16 (5), 445–448. https://doi.org/10.1190/1.1437657.
Crossref Google Scholar
 
Choi, S., Lee, K., Lim, S., et al., 2018. Uncertainty-aware learning from demonstration using mixture density networks with sampling-free variance modeling. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 6915–6922.
Crossref
 

Chopra, S., Marfurt, K.J., 2005. Seismic attributes—a historical perspective. Geophysics 70 (5), 3SO–28SO. https://doi.org/10.1190/1.2098670.
Crossref Google Scholar
 

Civan, F., Rasmussen, M.L., 2002. Further discussion of fracture width logging while drilling and drilling mud/loss-circulation-material selection guidelines in naturally fractured reservoirs. SPE Drill. Complet. 17 (4), 249–250.
Google Scholar
 

Cook, J., Growcock, F., Guo, Q., et al., 2011. Stabilizing the wellbore to prevent lost circulation. Oilfield Rev. 23 (4), 26–35.
Google Scholar
 

Camacho-Velázquez, R., Vásquez-Cruz, M., Castrejón-Aivar, R., et al., 2005. Pressure-transient and decline-curve behavior in naturally fractured vuggy carbonate reservoirs. SPE Reservoir Eval. Eng. 8 (2), 95–112. https://doi.org/10.2118/77689-PA.
Crossref Google Scholar
 

Daines, S.R., 1982. Prediction of fracture pressures for wildcat wells. J. Petrol. Technol. 34 (4), 863–872. https://doi.org/10.2118/9254-PA.
Crossref Google Scholar
 
Ding, Y., Cui, M., Wang, H., et al., 2021. Predicting seismic-based anisotropy for prevent pre-drill risk using a novel type neural network. In: The SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Virtual, 12–14 October. https://doi.org/10.2118/205710-MS.
Crossref
 

Dyke, C.G., Wu, B., Milton-Tayler, D., 1995. Advances in characterising natural fracture permeability from mud log data. SPE Form. Eval. 10 (3), 160–166. https://doi.org/10.2118/25022-PA.
Crossref Google Scholar
 

Eaton, B.A., 1969. Fracture gradient prediction and its application in oilfield operations. J. Petrol. Technol. 21 (10), 1353–1360. https://doi.org/10.2118/2163-PA.
Crossref Google Scholar
 

Fomel, S., 2007. Local seismic attributes. Geophysics 72 (3), A29–A33. https://doi.org/10.1190/1.2437573.
Crossref Google Scholar
 
Gao, J., Lin, H., Sun, J., et al., 2021. A porothermoelastic model considering the dynamic temperature-perturbation boundary effect for borehole stability in fractured porous rocks. In: The SPE/AAPG/SEG Asia Pacific Unconventional Resources Technology Conference, Virtual, 16–18 November. https://doi.org/10.15530/AP-URTEC-2021-208266.
Crossref
 

Geng, Z., Wang, H., Fan, M., et al., 2019. Predicting seismic-based risk of lost circulation using machine learning. J. Pet. Sci. Eng. 176, 679–688. https://doi.org/10.1016/j.petrol.2019.01.089.
Crossref Google Scholar
 

Gulbransen, A.F., Hauge, V.L., Lie, K.A., 2010. A multiscale mixed finite-element method for vuggy and naturally fractured reservoirs. SPE J. 15 (2), 395–403. https://doi.org/10.2118/119104-PA.
Crossref Google Scholar
 

Hauser, M.R., 2021. Evaluating an integrated physical model for borehole-leakoff pressures. SPE J. 26 (6), 3389–3409. https://doi.org/10.2118/204453-PA.
Crossref Google Scholar
 

Huang, R., 1984. A model for prediction formation fracture pressure. Journal of East China Petroleum Institute 4, 335–347 (in Chinese).
Google Scholar
 

Hubbert, M.K., Willis, D.G., 1957. Mechanics of hydraulic fracturing. Transactions of the AIME 210 (1), 153–168. https://doi.org/10.2118/686-G.
Crossref Google Scholar
 
Hou, X., Yang, J., Yin, Q., et al., 2020. Lost circulation prediction in South China Sea using machine learning and big data technology. In: The Offshore Technology Conference, 4–7 May. https://doi.org/10.4043/30653-MS.
Crossref
 

Jiang, X., 2006. Drilling Accidents and Complex Problems. Petroleum Industry Press, Beijing, p. 439 (in Chinese).
 

Jin, J., Jin, Y., Lu, Y., et al., 2021. Image processing and machine learning based cavings characterization and classification. J. Pet. Sci. Eng., 109525 https://doi.org/10.1016/j.petrol.2021.109525.
Crossref Google Scholar
 
Lavrov, A., Tronvoll, J., 2004. Modeling mud loss in fractured formations. In: The Abu Dhabi International Conference and Exhibition, Abu Dhabi, United Arab Emirates, 10–13 October. https://doi.org/10.2118/88700-MS.
Crossref
 
Li, X., Zhao, Q., Zhang, J., et al., 2019. A prediction model for extension limit of horizontal drilling based on leakage pressure in carbonate formations. In: The 53rd U.S. Rock Mechanics/Geomechanics Symposium, 23–26 June. ARMA-2019-1872.
 
Li, Z., Chen, M., Jin, Y., et al., 2018. Study on intelligent prediction for risk level of lost circulation while drilling based on machine learning. In: The 52nd U.S. Rock Mechanics/Geomechanics Symposium. Seattle, Washington, USA, 17–20 June. ARMA-2018-105.
 

Liétard, O., Unwin, T., Guillot, D.J., Hodder, M.H., 1999. Fracture width logging while drilling and drilling mud/loss-circulation-material selection guidelines in naturally fractured reservoirs. SPE Drill. Complet. 14 (3), 168–177. https://doi.org/10.2118/57713-PA.
Crossref Google Scholar
 

Majidi, R., Miska, S.Z., Yu, M., et al., 2010. Quantitative analysis of mud losses in naturally fractured reservoirs: the effect of rheology. SPE Drill. Complet. 25 (4), 509–517. https://doi.org/10.2118/114130-PA.
Crossref Google Scholar
 

Matthews, W.R., Kelly, J., 1967. How to predict formation pressure and fracture gradient from electric and sonic logs. Oil Gas J. 92–106.
Crossref Google Scholar
 
Morita, N., Black, A.D., Guh, G.F., 1990. Theory of lost circulation pressure. In: The SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, 23–26 September. https://doi.org/10.2118/20409-MS.
Crossref
 
Noshi, C.I., Schubert, J.J., 2018. The Role of Machine Learning in Drilling Operations: A Review. In: The Role of Machine Learning in Drilling Operations: A Review. The SPE/AAPG Eastern Regional Meeting, Pittsburgh, Pennsylvania, USA 7–11 October. https://doi.org/10.2118/191823-18ERM-MS.
Crossref
 

Özkaya, S.I., 2003. Fracture length estimation from borehole image logs. Math. Geol. 35 (6), 737–753. https://doi.org/10.1023/B:MATG.0000002987.69549.ba.
Crossref Google Scholar
 

Pang, H., Meng, H., Wang, H., et al., 2022. Lost circulation prediction based on machine learning. J. Pet. Sci. Eng. 208, 109364. https://doi.org/10.1016/j.petrol.2021.109364.
Crossref Google Scholar
 
Rabia, H., 2002. Well Engineering & Construction. Entrac Consulting Limited, London, pp. 288–289.
 

Sabah, M., Mehrad, M., Ashrafi, S.B., et al., 2021. Hybrid machine learning algorithms to enhance lost circulation prediction and management in the Marun Oil Field. J. Pet. Sci. Eng. 198, 108125. https://doi.org/10.1016/j.petrol.2020.108125.
Crossref Google Scholar
 

Sawaryn, S.J., 2001. Discussion of fracture width logging while drilling and drilling mud/loss-circulation-material selection guidelines in naturally fractured reservoirs. SPE Drill. Complet. 16 (4), 268–269.
Google Scholar
 

Schmidhuber, J., 2015. Deep learning in neural networks: an overview. Neural Network. 61, 85–117. https://doi.org/10.1016/j.neunet.2014.09.003.
Crossref Google Scholar
 
Shi, L., Jiang, H., Guo, Q., et al., 2012. Investigation on the differential pressure leakage of thief formation. In: The IADC/SPE Asia Pacific Drilling Technology Conference and Exhibition, 9–11 July. https://doi.org/10.2118/155699-MS.
Crossref
 

Tan, P., Jin, Y., Pang, H., 2021. Hydraulic fracture vertical propagation behavior in transversely isotropic layered shale formation with transition zone using XFEM-based CZM method. Eng. Fract. Mech. 248, 107707. https://doi.org/10.1016/j.engfracmech.2021.107707.
Crossref Google Scholar
 

Tan, P., Pang, H., Zhang, R., et al., 2020. Experimental investigation into hydraulic fracture geometry and proppant migration characteristics for southeastern Sichuan deep shale reservoirs. J. Pet. Sci. Eng. 184, 106517. https://doi.org/10.1016/j.petrol.2019.106517.
Crossref Google Scholar
 

Tian, M., Xu, H., Cai, J., et al., 2019. Artificial neural network assisted prediction of dissolution spatial distribution in the volcanic weathered crust: a case study from Chepaizi Bulge of Junggar Basin, northwestern China. Mar. Petrol. Geol. 110, 928–940. https://doi.org/10.1016/j.marpetgeo.2019.08.045.
Crossref Google Scholar
 
Wang, H., Chen, M., Wei, S., et al., 2020a. Breathing effect of sandstone reservoir formed in barrier coastal sedimentary system. In: The ISRM International Symposium - EUROCK 2020, Physical Event Not Held, 14–19 June. ISRM-EUROCK-2020-031.
 

Wang, H., Chen, M., Wei, S., et al., 2020b. The influence of barrier coastal sedimentary system lost circulation in sandstone. J. Pet. Sci. Eng. 185, 106654. https://doi.org/10.1016/j.petrol.2019.106654.
Crossref Google Scholar
 

Wei, S., Jin, Y., Xia, Y., 2020. Predict the mud loss in natural fractured vuggy reservoir using discrete fracture and discrete vug network model. J. Pet. Sci. Eng. 195, 107626. https://doi.org/10.1016/j.petrol.2020.107626.
Crossref Google Scholar
 

Wu, H., Pollard, D.D., 2002. Imaging 3-D fracture networks around boreholes. AAPG Bull. 86 (4), 593–604. https://doi.org/10.1306/61EEDB52-173E-11D7-8645000102C1865D.
Crossref Google Scholar
 

Wu, Y., Di, Y., Kang, Z., Fakcharoenphol, P., 2011. A multiple-continuum model for simulating single-phase and multiphase flow in naturally fractured vuggy reservoirs. J. Pet. Sci. Eng. 78 (1), 13–22. https://doi.org/10.1016/j.petrol.2011.05.004.
Crossref Google Scholar
 

Xia, Y., Jin, Y., Chen, M., 2015. Comprehensive methodology for detecting fracture aperture in naturally fractured formations using mud loss data. J. Pet. Sci. Eng. 135, 515–530. https://doi.org/10.1016/j.petrol.2015.10.017.
Crossref Google Scholar
 

Zheng, S., Yang, M., Kang, Z., et al., 2019. Controlling factors of remaining oil distribution after water flooding and enhanced oil recovery methods for fracturecavity carbonate reservoirs in Tahe Oilfield. Petrol. Explor. Dev. 46 (4), 786–795. https://doi.org/10.1016/S1876-3804(19)60236-3.
Crossref Google Scholar
 

Zoback, M.D., Healy, J.H., 1984. Friction, faulting and “in situ” stress. Ann. Geophys. 2, 689–698.
Google Scholar
Petroleum Science
Volume 21 Issue 2,
April 2024
Pages 1241-1256
DOI: 10.1016/j.petsci.2023.10.024
Cite this article:
Pang H-W, Wang H-Q, Xiao Y-T, et al. Machine learning for carbonate formation drilling: Mud loss prediction using seismic attributes and mud loss records. Petroleum Science, 2024, 21(2): 1241-1256. https://doi.org/10.1016/j.petsci.2023.10.024

2

Views

0

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 11 December 2022
Revised: 26 October 2023
Accepted: 29 October 2023
Published: 13 November 2023
© 2024 The Authors.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return