An unsupervised clustering method for nuclear magnetic resonance transverse relaxation spectrums based on the Gaussian mixture model and its application

Petroleum Exploration and Development

Zong’an XUE¹  Shuolong WANG²  Jiangtao LI³  Ji’er ZHAO⁴  Jun ZHOU⁵  Hengrong ZHANG⁶  Falong HU⁷  Shenyuan NIU⁸  Xinmin GE⁹ 

[1] CNPC Key Well Logging Laboratory, Xi’an 710077, China;China Petroleum Logging Co. Ltd., Xi’an 710077, China;Corresponding author;Development, Beijing 100083, China;Laboratory for Marine Mineral Resources, Qingdao National Laboratory for Marine Science and Technology, Qingdao 266071, China;CNPC Key Well Logging Laboratory, Xi’an 710077, China;Oil and Gas Survey Center of China Geological Survey, Beijing 100083, China;;PetroChina Research Institute of Petroleum Exploration &School of Geosciences, China University of Petroleum, Qingdao 266580, China;

关键词: NMR T2 spectrum;    Gaussian mixture model;    expectation-maximization algorithm;    Akaike information criterion;    unsupervised clustering method;    quantitative pore structure evaluation;   

DOI  :  

来源: DOAJ

【 摘 要 】

To make the quantitative results of nuclear magnetic resonance (NMR) transverse relaxation (T2) spectrums reflect the type and pore structure of reservoir more directly, an unsupervised clustering method was developed to obtain the quantitative pore structure information from the NMR T2 spectrums based on the Gaussian mixture model (GMM). Firstly, We conducted the principal component analysis on T2 spectrums in order to reduce the dimension data and the dependence of the original variables. Secondly, the dimension-reduced data was fitted using the GMM probability density function, and the model parameters and optimal clustering numbers were obtained according to the expectation-maximization algorithm and the change of the Akaike information criterion. Finally, the T2 spectrum features and pore structure types of different clustering groups were analyzed and compared with T2 geometric mean and T2 arithmetic mean. The effectiveness of the algorithm has been verified by numerical simulation and field NMR logging data. The research shows that the clustering results based on GMM method have good correlations with the shape and distribution of the T2 spectrum, pore structure, and petroleum productivity, providing a new means for quantitative identification of pore structure, reservoir grading, and oil and gas productivity evaluation.

【 授权许可】

Unknown