Method for predicting total organic carbon content of shale based on depth coding and decoding network

Abstract

The invention belongs to the technical field of oil-gas exploration, particularly relates to a method, a system and equipment for predicting the total organic carbon content of shale based on a deep coding and decoding network, and aims to solve the problems of low prediction accuracy and poor robustness of an existing method for predicting the total organic carbon content of shale. The method comprises the steps of obtaining a logging curve based on logging data of a to-be-predicted well position of a target shale layer; preprocessing the logging curve to obtain a preprocessed logging curve; and performing windowing processing on the preprocessed logging curve, and after windowing processing, inputting the logging curve into a pre-trained TOC prediction model to obtain TOC at the center of a window as a prediction result of the total organic carbon content of the to-be-predicted well site of the target shale bed, wherein the TOC prediction model is constructed based on an improved 1D U-Net network. According to the method, the accuracy and robustness of predicting the total organic carbon content of the shale bed are improved.

Description

technical field [0001] The invention belongs to the technical field of oil and gas exploration, and in particular relates to a method, system and equipment for predicting the total organic carbon content of shale based on a deep encoding and decoding network. Background technique [0002] In recent years, with the development of shale gas and oil, the evaluation of source rocks is of great significance. Total organic carbon (TOC) plays an important role in source rock evaluation and is also an important parameter for reservoir prediction. The total organic carbon content is generally determined in the laboratory by the rock evaluation pyrolysis method, and it is the main index for evaluating the hydrocarbon generation potential of source rocks in shale gas reservoirs. These data are often scarce due to the limited number of core samples and expensive experiments. [0003] In the prior art, it has been confirmed that conventional wireline logging parameters (ie, acoustic lo...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problems of low prediction accuracy and poor robustness of the existing shale total organic carbon content prediction method, the first aspect of the present invention proposes a deep encoding and decoding network based A method for predicting the total organic carbon content of shale, the method comprising:

Images