Log interpretation method of resistivity low-contrast oil pays in Chang 8 tight sandstone of Huanxian area, Ordos Basin by support vector machine

Ze Bai,Xingning Guan,Yanhui Huang,Haibo Wu,Yujiang Shi,Maojin Tan

doi:10.1038/s41598-022-04962-0

Abstract

Resistivity low-contrast oil pays are a kind of unconventional oil resource with no obvious difference in physical and electrical properties from water layers, which makes it difficult to be identified based on the characteristics of the geophysical well logging response. In this study, the support vector machine (SVM) technology was used to interpret the resistivity low-contrast oil pays in Chang 8 tight sandstone reservoir of Huanxian area, Ordos Basin. First, the input data sequences of logging curves were selected by analyzing the relationship between reservoir fluid types and logging data. Then, the SVM classification model for fluid identification and SVR regression model for reservoir parameter prediction were constructed. Finally, these two models were applied to interpret the resistivity low-contrast oil pays in the study area. The application results show that the fluid recognition accuracy of the SVM classification model is higher than that of the logging cross plot method, back propagation neural network method and radial basis function neural network method. The calculation accuracy of permeability and water saturation predicted by the SVR regression model is higher than that based on the experimental fitting model, which indicates that it is feasible to carry out logging interpretation and evaluation of the resistivity low-contrast oil pays by the SVM method. The research results not only provide an important reference and basis for the review of old wells but also provide technical support for the exploration and development of new strata.

Highlights

Resistivity low-contrast oil pays are a kind of unconventional oil resource with no obvious difference in physical and electrical properties from water layers, which makes it difficult to be identified based on the characteristics of the geophysical well logging response
Guo et al.[13] predicted the water saturation at the lower limit of three water models by using the generalized neural network (GRNN) and particle swarm optimization support vector machine (PSOSVM), which is in good agreement with the core analysis results in the Sulige tight sandstone reservoir
To evaluate the reliability of the SVM classification model for fluid recognition, conventional fluid recognition method, back propagation neural network (BP) method and radial basis function neural network (RBF) method were introduced for comparison

Summary

Method and theory

Different from the neural network method to solve the number of hidden nodes of neurons, the basic idea of a support vector machine for reservoir parameter prediction is to map the input space to a high-dimensional space by introducing a kernel function and solve a linearly separable hyperplane or function in this highdimensional space, which can separate all data types in the original space. According to the oil test conclusion of the target interval in the study area, the input logging parameters are matched and combined with the numbers representing different pore fluid types to form the input training set of the model. To evaluate the reliability of the SVM classification model for fluid recognition, conventional fluid recognition method (cross plot of porosity and resistivity log), back propagation neural network (BP) method and radial basis function neural network (RBF) method were introduced for comparison.

Result

Findings

Discussion