Method, device and system for determining content of organic carbon

Abstract

The embodiment of the invention discloses a method, device and system for determining the content of organic carbon. The method comprises the steps of obtaining logging data of a preset logging data type of a to-be-measured work area; inputting the logging data into a constructed organic carbon content integrated prediction model to perform organic carbon content prediction to obtain organic carbon content data of the to-be-measured work area, the organic carbon content integrated prediction model being pre-constructed by adopting the following mode: obtaining logging data corresponding to thepreset logging data type and corresponding actually measured organic carbon content data as first sample data; utilizing a support vector machine model and a delta logR model to process the logging data in the first sample data to obtain a first prediction result and a second prediction result; and taking the first prediction result, the second prediction result and the actually measured organiccarbon content data as second sample data, and training a decision tree model by utilizing the second sample data to obtain the organic carbon content integrated prediction model.

Description

technical field [0001] The invention relates to the technical field of petroleum exploration, in particular to a method, device and system for determining organic carbon content. Background technique [0002] Tight oil is the key field of unconventional oil and gas exploration in the world today. The development of tight oil is characterized by the integration of source and reservoir. High-quality source rocks are the prerequisite for its enrichment. At present, it is believed that areas with organic carbon content greater than 2% are potential favorable areas for tight oil development. Therefore, accurate prediction of organic carbon content in unknown areas Significant. [0003] At present, the prediction of organic carbon is mainly calculated by using the well logging data which is easy to obtain. However, the magnitude of the correlation relationship of each curve in different regions is not the same, and it is difficult to form a unified calculation method. Methods us...

AI Technical Summary

Problems solved by technology

[0004]The multiple linear regression method is a linear model, which considers the linear correlation between the logging data and the organic carbon content, which is too simple and the accuracy is too low

The neural network method is sensitive to parameter selection, easy to overfit, affects the accuracy of the results, and the calculation speed is too slow

Images