Home Petroleum Science Article
PDF (8 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Abstract
Keywords
References
Show full outline
Hide outline
Original Paper | Open Access

Multifractal estimation of NMR T2 cut-off value in low-permeability rocks considering spectrum kurtosis: SMOTE-based oversampling integrated with machine learning

Xiao-Jun Chena,b, Rui-Xue Zhangc, Xiao-Bo Zhaoa, Jun-Wei Yanga, Zhang-Jian Land, Cheng-Fei Luoe, Jian-Chao Caia,f()
MOE Key Laboratory of Tectonics and Petroleum Resources, Wuhan, 430074, Hubei, China
Department of Chemical Engineering and Analytical Science, The University of Manchester, Manchester, M13 9PL, UK
Jianghan Oilfied, SINOPEC, Qianjiang, 430063, Hubei, China
Hainan Branch of CNOOC Ltd, Haikou, 570311, Hainan, China
CNOOC EnerTech-Drilling & Production Co. CNOOC Central Laboratory (Zhanjiang), Zhanjiang, 524057, Guangdong, China
National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum, Beijing, 102249, China

Edited by Jie Hao

Show Author Information

Abstract

The transverse relaxation time (T2) cut-off value plays a crucial role in nuclear magnetic resonance for identifying movable and immovable boundaries, evaluating permeability, and determining fluid saturation in petrophysical characterization of petroleum reservoirs. This study focuses on the systematic analysis of T2 spectra and T2 cut-off values in low-permeability reservoir rocks. Analysis of 36 low-permeability cores revealed a wide distribution of T2 cut-off values, ranging from 7 to 50 ms. Additionally, the T2 spectra exhibited multimodal characteristics, predominantly displaying unimodal and bimodal morphologies, with a few trimodal morphologies, which are inherently influenced by different pore types. Fractal characteristics of pore structure in fully water-saturated cores were captured through the T2 spectra, which were calculated using generalized fractal and multifractal theories. To augment the limited dataset of 36 cores, the synthetic minority oversampling technique was employed. Models for evaluating the T2 cut-off value were separately developed based on the classified T2 spectra, considering the number of peaks, and utilizing generalized fractal dimensions at the weight <0 and the singular intensity range. The underlying mechanism is that the singular intensity and generalized fractal dimensions at the weight <0 can detect the T2 spectral shift. However, the T2 spectral shift has negligible effects on multifractal spectrum function difference and generalized fractal dimensions at the weight >0. The primary objective of this work is to gain insights into the relationship between the kurtosis of the T2 spectrum and pore types, as well as to predict the T2 cut-off value of low-permeability rocks using machine learning and data augmentation techniques.

Keywords

Nuclear magnetic resonanceLow-permeability porous mediaT2 cut-off valueFractal and multifractalData augmentationMachine learning

References

 

Blunt, M.J., 2017. Multiphase Flow in Permeable Media: A Pore-Scale Perspective. Cambridge University Press. https://doi.org/10.1017/9781316145098.

Crossref
 

Blunt, M.J., Bijeljic, B., Dong, H., et al., 2013. Pore-scale imaging and modelling. Adv. Water Resour. 51, 197–216. https://doi.org/10.1016/j.advwatres.2012.03.003.

Crossref Google Scholar
 

Bultreys, T., De Boever, W., Cnudde, V., 2016. Imaging and image-based fluid transport modeling at the pore scale in geological materials: a practical introduction to the current state-of-the-art. Earth-Sci. Rev. 155, 93–128. https://doi.org/10.1016/j.earscirev.2016.02.001.

Crossref Google Scholar
 

Butler, J.P., Reeds, J.A., Dawson, S.V., 1981. Estimating solutions of first kind integral equations with nonnegative constraints and optimal smoothing. SIAM J. Numer. Anal. 18, 381–397. https://doi.org/10.1137/0718025.

Crossref Google Scholar
 

Cai, J., Xu, K., Zhu, Y., et al., 2020. Prediction and analysis of net ecosystem carbon exchange based on gradient boosting regression and random forest. Appl. Energy 262, 114566. https://doi.org/10.1016/j.apenergy.2020.114566.

Crossref Google Scholar
 

Camacho, L., Douzas, G., Bacao, F., 2022. Geometric SMOTE for regression. Expert Syst. Appl. 193, 116387. https://doi.org/10.1016/j.eswa.2021.116387.

Crossref Google Scholar
 

Chawla, N.V., Bowyer, K.W., Hall, L.O., et al., 2002. SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357. https://doi.org/10.1613/jair.953

Crossref Google Scholar
 

Chen, J., Huang, H., Cohn, A.G., et al., 2022. Machine learning-based classification of rock discontinuity trace: SMOTE oversampling integrated with GBT ensemble learning. Int. J. Min. Sci. Technol. 32, 309–322. https://doi.org/10.1016/j.ijmst.2021.08.004.

Crossref Google Scholar
 

Chen, X., Yao, G., Cai, J., et al., 2017. Fractal and multifractal analysis of different hydraulic flow units based on micro-CT images. J. Nat. Gas Sci. Eng. 48, 145–156. https://doi.org/10.1016/j.jngse.2016.11.048.

Crossref Google Scholar
 

Chen, X., Yao, G., Herrero-Bervera, E., et al., 2018. A new model of pore structure typing based on fractal geometry. Mar. Petrol. Geol. 98, 291–305. https://doi.org/10.1016/j.marpetgeo.2018.08.023.

Crossref Google Scholar
 

Cheng, Q., 1999. Multifractality and spatial statistics. Comput. Geosci. 25, 949–961. https://doi.org/10.1016/S0098-3004(99)00060-6.

Crossref Google Scholar
 

Chhabra, A., Jensen, R.V., 1989. Direct determination of the f(α) singularity spectrum. Phys. Rev. Lett. 62, 1327. https://doi.org/10.1103/PhysRevLett.62.1327.

Crossref Google Scholar
 

Coates, G.R., Xiao, L., Prammer, M.G., 1999. NMR Logging: Principles and Applications. Haliburton Energy Services, Houston.

 

Daigle, H., Johnson, A., 2016. Combining mercury intrusion and nuclear magnetic resonance measurements using percolation theory. Transp. Porous Media 111, 669–679. https://doi.org/10.1007/s11242-015-0619-1.

Crossref Google Scholar
 

Douzas, G., Bacao, F., 2019. Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE. Inf. Sci. 501, 118–135. https://doi.org/10.1016/j.ins.2019.06.007.

Crossref Google Scholar
 

Douzas, G., Bacao, F., Last, F., 2018. Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE. Inf. Sci. 465, 1–20. https://doi.org/10.1016/j.ins.2018.06.056.

Crossref Google Scholar
 

Douzas, G., Rauch, R., Bacao, F., 2021. G-SOMO: an oversampling approach based on self-organized maps and geometric SMOTE. Expert Syst. Appl. 183, 115230. https://doi.org/10.1016/j.eswa.2021.115230.

Crossref Google Scholar
 

Dullien, F.A., 2012. Porous Media: Fluid Transport and Pore Structure. Academic Press. https://doi.org/10.1016/0300-9467(81)80049-4.

Crossref
 

Fu, H., Wang, W., Chen, X., et al., 2019. Fractal and multifractal analysis of fracture surfaces caused by hydrogen embrittlement in high-Mn twinning/transformation-induced plasticity steels. Appl. Surf. Sci. 470, 870–881. https://doi.org/10.1016/j.apsusc.2018.11.179.

Crossref Google Scholar
 

Gao, H., Li, H.A., 2016. Pore structure characterization, permeability evaluation and enhanced gas recovery techniques of tight gas sandstones. J. Nat. Gas Sci. Eng. 28, 536–547. https://doi.org/10.1016/j.jngse.2015.12.018.

Crossref Google Scholar
 

Ge, X., Fan, Y., Deng, S., 2011. Research on T2 cutoff-value determination method for shaly sand based on experiments. Well Logging Technol. 35, 308–313.

Google Scholar
 

Ge, X., Fan, Y., Zhu, X., et al., 2015. Determination of nuclear magnetic resonance T2 cutoff value based on multifractal theory—an application in sandstone with complex pore structure. Geophysics 80, D11–D21.

Crossref Google Scholar
 

Ge, X., Chen, H., Fan, Y., et al., 2017. An improved pulse sequence and inversion algorithm of T2 spectrum. Comput. Phys. Commun. 212, 82–89. https://doi.org/10.1016/j.cpc.2016.10.012.

Crossref Google Scholar
 

Ge, X., Fan, Y., Liu, J., et al., 2021. Numerical investigating the low field NMR response of representative pores at different pulse sequence parameters. Comput. Geosci. 151, 104761. https://doi.org/10.1016/j.cageo.2021.104761.

Crossref Google Scholar
 

Godefroy, S., Fleury, M., Deflandre, F., et al., 2002. Temperature effect on NMR surface relaxation in rocks for well logging applications. J. Phys. Chem. B 106, 11183–11190. https://doi.org/10.1021/jp0213452.

Crossref Google Scholar
 

Guo, J.-C., Zhou, H.-Y., Zeng, J., et al., 2020. Advances in low-field nuclear magnetic resonance (NMR) technologies applied for characterization of pore space inside rocks: a critical review. Petrol. Sci. 17, 1281–1297. https://doi.org/10.1007/s12182-020-00488-0.

Crossref Google Scholar
 

Guo, X., Huang, Z., Zhao, L., et al., 2019. Pore structure and multi-fractal analysis of tight sandstone using MIP, NMR and NMRC methods: a case study from the Kuqa depression, China. J. Petrol. Sci. Eng. 178, 544–558. https://doi.org/10.1016/j.petrol.2019.03.069.

Crossref Google Scholar
 

Hidajat, I., Mohanty, K., Flaum, M., et al., 2004. Study of vuggy carbonates using NMR and X-ray CT scanning. SPE Reservoir Eval. Eng. 7, 365–377. https://doi.org/10.2118/88995-pa.

Crossref Google Scholar
 

Hu, Y., Guo, Y., Zhang, J., et al., 2020. A method to determine nuclear magnetic resonance T2 cutoff value of tight sandstone reservoir based on multifractal analysis. Energy Sci. Eng. 8, 1135–1148. https://doi.org/10.1002/ese3.574.

Crossref Google Scholar
 

Jiao, L., Andersen, P.Ø., Zhou, J., et al., 2020. Applications of mercury intrusion capillary pressure for pore structures: a review. Capillarity 3, 62–74. https://doi.org/10.46690/capi.2020.04.02

Crossref Google Scholar
 

Karimpouli, S., Tahmasebi, P., 2019. Image-based velocity estimation of rock using Convolutional Neural Networks. Neural Network. 111, 89–97. https://doi.org/10.1016/j.neunet.2018.12.006.

Crossref Google Scholar
 
KKleinberg, R., Boyd, A., 1997. Tapered Cutoffs for Magnetic Resonance Bound Water Volume. SPE Annual Technical Conference and Exhibition, OnePetro. https://doi.org/10.2523/38737-ms.
Crossref
 

Li, C., Liu, G., Cao, Z., et al., 2020a. Analysis of petrophysical characteristics and water movability of tight sandstone using low-field nuclear magnetic resonance. Nat. Resour. Res. 29, 2547–2573. https://doi.org/10.1007/s11053-019-09582-6.

Crossref Google Scholar
 

Li, J., Jiang, C., Wang, M., et al., 2020b. Adsorbed and free hydrocarbons in unconventional shale reservoir: a new insight from NMR T1-T2 maps. Mar. Petrol. Geol. 116, 104311. https://doi.org/10.1016/j.marpetgeo.2020.104311.

Crossref Google Scholar
 

Liu, J., Pereira, G.G., Liu, Q., et al., 2016. Computational challenges in the analyses of petrophysics using microtomography and upscaling: a review. Comput. Geosci. 89, 107–117. https://doi.org/10.1016/j.cageo.2016.01.014.

Crossref Google Scholar
 

Liu, K., Mirzaei-Paiaman, A., Liu, B., et al., 2020a. A new model to estimate permeability using mercury injection capillary pressure data: application to carbonate and shale samples. J. Nat. Gas Sci. Eng. 84, 103691. https://doi.org/10.1016/j.jngse.2020.103691.

Crossref Google Scholar
 

Liu, K., Jin, Z., Zeng, L., et al., 2021a. Determination of clay bound water in shales from NMR signals: the fractal theory. Energy Fuels 35, 18406–18413. https://doi.org/10.1021/acs.energyfuels.1c02285.

Crossref Google Scholar
 

Liu, X., Jin, Z., Lai, J., et al., 2021b. Fractal behaviors of nmr saturated and centrifugal T2 spectra in oil shale reservoirs: the paleogene funing formation in subei basin, China. Mar. Petrol. Geol. 129, 105069. https://doi.org/10.1016/j.marpetgeo.2021.105069.

Crossref Google Scholar
 

Liu, Z., Liu, D., Cai, Y., et al., 2020b. Application of nuclear magnetic resonance (NMR) in coalbed methane and shale reservoirs: a review. Int. J. Coal Geol. 218, 103261. https://doi.org/10.1016/j.coal.2019.103261.

Crossref Google Scholar
 

Lopes, R., Betrouni, N., 2009. Fractal and multifractal analysis: a review. Med. Image Anal. 13, 634–649. https://doi.org/10.1016/j.media.2009.05.003.

Crossref Google Scholar
 
Mai, A., Kantzas, A., 2002. An evaluation of the application of low field NMR in the characterization of carbonate reservoirs. In: SPE Annual Technical Conference and Exhibition. OnePetro. https://doi.org/10.2118/77401-ms.
Crossref
 

Mehmani, A., Verma, R., Prodanović, M., 2020. Pore-scale modeling of carbonates. Mar. Petrol. Geol. 114, 104141. https://doi.org/10.1016/j.marpetgeo.2019.104141.

Crossref Google Scholar
 

Meng, J., Zhou, Y.-J., Ye, T.-R., et al., 2022. Hybrid data-driven framework for shale gas production performance analysis via game theory, machine learning, and optimization approaches. Petrol. Sci. 20, 277–294. https://doi.org/10.1016/j.petsci.2022.09.003.

Crossref Google Scholar
 

Morriss, C., Rossini, D., Straley, C., et al., 1997. Core analysis by low-field NMR. Log. Anal. 38.

Google Scholar
 

Nicot, B., Ligneul, P., Akbar, M., 2016. T2-cutoff determination using magnetic susceptibility measurements. Google Patents.

Google Scholar
 
Oraby, M., Chafai, N., Hussing, R., et al., 1997. A new NMR interpretation technique using error minimization with variable T2 cutoff. In: SPE Annual Technical Conference and Exhibition. OnePetro. doi:10.2118/38734-ms.
Crossref
 

Peduzzi, P., Concato, J., Kemper, E., et al., 1996. A simulation study of the number of events per variable in logistic regression analysis. J. Clin. Epidemiol. 49, 1373–1379. https://doi.org/10.1016/S0895-4356(96)00236-3.

Crossref Google Scholar
 

Saxena, N., Day-Stirrat, R.J., Hows, A., et al., 2021. Application of deep learning for semantic segmentation of sandstone thin sections. Comput. Geosci. 152, 104778. https://doi.org/10.1016/j.cageo.2021.104778.

Crossref Google Scholar
 
Shapley, L., 1953. Quota Solutions Op N-Person Games1. Emil Artin and Marston Morse, p. 343. https://doi.org/10.1515/9781400881970-021.
Crossref
 

Sigal, R.F., 2015. Pore-size distributions for organic-shale-reservoir rocks from nuclear-magnetic-resonance spectra combined with adsorption measurements. SPE J. 20, 824–830. https://doi.org/10.2118/174546-pa.

Crossref Google Scholar
 

Stanley, H.E., Meakin, P., 1988. Multifractal phenomena in physics and chemistry. Nature 335, 405–409. https://doi.org/10.1038/335405a0.

Crossref Google Scholar
 

Sun, Y., Zhai, C., Zhao, Y., et al., 2021. Multifractal analysis and neural network prediction of pore structures in coal reservoirs based on NMR T2 spectra. Energy Fuels 35, 11306–11318. https://doi.org/10.1021/acs.energyfuels.1c01409.

Crossref Google Scholar
 

Tang, M., Wang, C., Yang, H., et al., 2022. Experimental investigation on plugging performance of nanospheres in low-permeability reservoir with bottom water. Adv. Geo-Energy Res. 6, 95–103. https://doi.org/10.46690/ager.2022.02.02.

Crossref Google Scholar
 

Testamanti, M.N., Rezaee, R., 2017. Determination of NMR T2 cut-off for clay bound water in shales: a case study of Carynginia Formation, Perth Basin, Western Australia. J. Petrol. Sci. Eng. 149, 497–503. https://doi.org/10.1016/j.petrol.2016.10.066.

Crossref Google Scholar
 

Wang, F., Yang, K., Cai, J., 2018a. Fractal characterization of tight oil reservoir pore structure using nuclear magnetic resonance and mercury intrusion porosimetry. Fractals 26, 1840017. https://doi.org/10.1142/s0218348x18400170.

Crossref Google Scholar
 

Wang, F., Yang, K., You, J., et al., 2019. Analysis of pore size distribution and fractal dimension in tight sandstone with mercury intrusion porosimetry. Results Phys. 13, 102283. https://doi.org/10.1016/j.rinp.2019.102283.

Crossref Google Scholar
 

Wang, G., Han, D., Qin, X., et al., 2020. A comprehensive method for studying pore structure and seepage characteristics of coal mass based on 3D CT reconstruction and NMR. Fuel 281, 118735. https://doi.org/10.1016/j.fuel.2020.118735.

Crossref Google Scholar
 

Wang, Z.H., Zhang, C.G., Xiao, C.W., et al., 2004. Experimental study of T2-cutoff values in low-permeability reservoirs. Prog. Geophys. 19, 652–655. https://doi.org/10.1016/S0960-0779(03)00420-X.

Crossref Google Scholar
 

Wang, Z., Pan, M., Shi, Y., et al., 2018b. Fractal analysis of Donghetang sandstones using NMR measurements. Energy Fuels 32, 2973–2982. https://doi.org/10.1021/acs.energyfuels.7b03463.

Crossref Google Scholar
 

Westphal, H., Surholt, I., Kiesl, C., et al., 2005. NMR measurements in carbonate rocks: problems and an approach to a solution. Pure Appl. Geophys. 162, 549–570. https://doi.org/10.1007/s00024-004-2621-3.

Crossref Google Scholar
 

Wu, B., Xie, R., Wang, X., et al., 2020. Characterization of pore structure of tight sandstone reservoirs based on fractal analysis of NMR echo data. J. Nat. Gas Sci. Eng. 81, 103483. https://doi.org/10.1016/j.jngse.2020.103483.

Crossref Google Scholar
 

Xiao, L., Li, J., Mao, Z., et al., 2018. A method to determine nuclear magnetic resonance (NMR) T2 cutoff based on normal distribution simulation in tight sandstone reservoirs. Fuel 225, 472–482. https://doi.org/10.1016/j.fuel.2018.03.178.

Crossref Google Scholar
 

Yan, J., He, X., Zhang, S., et al., 2020. Sensitive parameters of NMR T2 spectrum and their application to pore structure characterization and evaluation in logging profile: a case study from Chang 7 in the Yanchang Formation, Heshui area, Ordos Basin, NW China. Mar. Petrol. Geol. 111, 230–239. https://doi.org/10.1016/j.marpetgeo.2019.08.025.

Crossref Google Scholar
 

Yan, W., Sun, J., Golsanami, N., et al., 2019. Evaluation of wettabilities and pores in tight oil reservoirs by a new experimental design. Fuel 252, 272–280. https://doi.org/10.1016/j.fuel.2019.04.130.

Crossref Google Scholar
 

Yao, Y., Liu, D., Che, Y., et al., 2010. Petrophysical characterization of coals by low-field nuclear magnetic resonance (NMR). Fuel 89, 1371–1380. https://doi.org/10.1016/j.fuel.2009.11.005.

Crossref Google Scholar
 

Zhang, M.-L., Zhou, Z.-H., 2007. ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn. 40, 2038–2048. https://doi.org/10.1016/j.patcog.2006.12.019.

Crossref Google Scholar
 

Zhang, Y., Li, Q., Hu, Q., et al., 2022. Pore wetting process characterization of Equal-Sized granular coals by using LF-NMR technology. Fuel 313, 122670. https://doi.org/10.1016/j.fuel.2021.122670.

Crossref Google Scholar
 

Zhao, P., Wang, Z., Sun, Z., et al., 2017. Investigation on the pore structure and multifractal characteristics of tight oil reservoirs using NMR measurements: permian Lucaogou Formation in Jimusaer Sag, Junggar Basin. Mar. Petrol. Geol. 86, 1067–1081. https://doi.org/10.1016/j.marpetgeo.2017.07.011.

Crossref Google Scholar
 

Zhao, P., Wang, X., Cai, J., et al., 2019. Multifractal analysis of pore structure of Middle Bakken formation using low temperature N2 adsorption and NMR measurements. J. Petrol. Sci. Eng. 176, 312–320. https://doi.org/10.1016/j.petrol.2019.01.040.

Crossref Google Scholar
 

Zhao, X., Yao, G., Chen, X., et al., 2022a. Diagenetic facies classification and characterization of a high-temperature and high-pressure tight gas sandstone reservoir: a case study in the Ledong area, Yinggehai Basin. Mar. Petrol. Geol. 140, 105665. https://doi.org/10.1016/j.marpetgeo.2022.105665.

Crossref Google Scholar
 

Zhao, X., Chen, X., Huang, Q., et al., 2022b. Logging-data-driven permeability prediction in low-permeable sandstones based on machine learning with pattern visualization: a case study in Wenchang A Sag, Pearl River Mouth Basin. J. Petrol. Sci. Eng. 214, 110517. https://doi.org/10.1016/j.petrol.2022.110517.

Crossref Google Scholar
 

Zhao, Y., Lin, B., Liu, T., et al., 2021. Multifractal analysis of coal pore structure based on NMR experiment: a new method for predicting T2 cutoff value. Fuel 283, 119338. https://doi.org/10.1016/j.fuel.2020.119338.

Crossref Google Scholar
 

Zheng, S., Yao, Y., Liu, D., et al., 2019. Nuclear magnetic resonance T2 cutoffs of coals: a novel method by multifractal analysis theory. Fuel 241, 715–724. https://doi.org/10.1016/j.fuel.2018.12.044.

Crossref Google Scholar
 

Zhong, J., Yan, R., Zhang, H., et al., 2020. A decomposition method of nuclear magnetic resonance T2 spectrum for identifying fluid properties. Petrol. Explor. Dev. 47, 740–752. https://doi.org/10.1016/S1876-3804(20)60089-1.

Crossref Google Scholar
Petroleum Science
Volume 20 Issue 6,
December 2023
Pages 3411-3427
DOI: 10.1016/j.petsci.2023.08.001
Cite this article:
Chen X-J, Zhang R-X, Zhao X-B, et al. Multifractal estimation of NMR T2 cut-off value in low-permeability rocks considering spectrum kurtosis: SMOTE-based oversampling integrated with machine learning. Petroleum Science, 2023, 20(6): 3411-3427. https://doi.org/10.1016/j.petsci.2023.08.001
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return