A bedrock buried hill oil reservoir rock type identification method based on machine learning

Abstract

The invention discloses a bedrock buried hill oil reservoir rock type identification method based on machine learning in order to solve the problem that an existing oil reservoir rock type identification method cannot give consideration to both cost and accuracy, and the method comprises the following steps: carrying out rock core geology description on a key well of a target block; Analyzing thetypes and contents of oxides and rock-making minerals of the main oil-containing rock; Establishing a three-dimensional lithology discrimination chart of the main oxide content and the rock type through a KNN algorithm; Obtaining an element content curve continuously distributed along the shaft in the target layer of the key well by applying an oxide closed model interpretation technology; Establishing a comprehensive histogram of conventional logging, mineral content and rock type of the key well of the target block; Establishing an elemental oxide content prediction model, and predicting theelemental content of the development well which is not cored and is not subjected to ECS capture logging; And substituting into the established three-dimensional lithology discrimination chart of therock type to realize automatic identification and division of the rock type. The identification method is low in cost and high in accuracy.

Description

technical field [0001] The invention belongs to the field of rock type identification methods for oil reservoirs, in particular to a machine learning-based rock type identification method for bedrock buried hill oil reservoirs. Background technique [0002] In recent years, with the continuous increase of people's demand for oil, conventional oil reservoirs can no longer meet the needs of people's life and industrial production. Subtle oil reservoirs have become one of the important directions of oil and gas exploration, and buried hill oil reservoirs are just one of them. An important concealed oil reservoir. Affected by sedimentary discontinuity, formation uplift, denudation, etc., bedrock buried hill reservoir rocks are characterized by many types of rocks, complex lithology, and large changes in distribution rules. The bedrock buried hill reservoir lithology controls the development degree of fractures and vugs in the reservoir, and then controls the distribution, seepa...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned problem that the existing methods for identifying rock types in oil reservoirs cannot balance both cost and accuracy, the present invention provides a method for identifying rock types in bedrock buried hill oil reservoirs based on machine learning, which has the advantages of low cost, The advantages of wide application range, high accuracy and fast recognition speed

Images