Identification of reservoir types in deep carbonates based on mixed-kernel machine learning using geophysical logging data

• Published in: Petroleum science 2024-06, Vol.21 (3), p.1632-1648
• Main Authors: Shi, Jin-Xiong, Zhao, Xiang-Yuan, Zeng, Lian-Bo, Zhang, Yun-Zhao, Zhu, Zheng-Ping, Dong, Shao-Qun
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial intelligence; Carbonates; Classification; Core sampling; Coring; Data analysis; Data logging; Datasets; Deep carbonates; Discriminant analysis; Geophysical logging data; Geophysical methods; Geophysics; Hydrocarbons; Identification; Kernel Fisher discriminant analysis; Kernel functions; Lithology; Logging; Machine learning; Methods; Mixed kernel function; Parameter identification; Particle swarm optimization; Performance evaluation; Petroleum geology; Reservoir type identification; Reservoirs; Support vector machines; Uncertainty analysis
• ISSN: 1995-8226; 1672-5107; 1995-8226
• DOI: 10.1016/j.petsci.2023.12.016

Identification of reservoir types in deep carbonates has always been a great challenge due to complex logging responses caused by the heterogeneous scale and distribution of storage spaces. Traditional cross-plot analysis and empirical formula methods for identifying reservoir types using geophysical logging data have high uncertainty and low efficiency, which cannot accurately reflect the nonlinear relationship between reservoir types and logging data. Recently, the kernel Fisher discriminant analysis (KFD), a kernel-based machine learning technique, attracts attention in many fields because of its strong nonlinear processing ability. However, the overall performance of KFD model may be limited as a single kernel function cannot simultaneously extrapolate and interpolate well, especially for highly complex data cases. To address this issue, in this study, a mixed kernel Fisher discriminant analysis (MKFD) model was established and applied to identify reservoir types of the deep Sinian carbonates in central Sichuan Basin, China. The MKFD model was trained and tested with 453 datasets from 7 coring wells, utilizing GR, CAL, DEN, AC, CNL and RT logs as input variables. The particle swarm optimization (PSO) was adopted for hyper-parameter optimization of MKFD model. To evaluate the model performance, prediction results of MKFD were compared with those of basic-kernel based KFD, RF and SVM models. Subsequently, the built MKFD model was applied in a blind well test, and a variable importance analysis was conducted. The comparison and blind test results demonstrated that MKFD outperformed traditional KFD, RF and SVM in the identification of reservoir types, which provided higher accuracy and stronger generalization. The MKFD can therefore be a reliable method for identifying reservoir types of deep carbonates.