Well-to-seismic joint adaptive multi-parameter intelligent lithofacies identification method

Abstract

The invention provides a well-to-seismic joint adaptive multi-parameter intelligent lithofacies identification method. The well-to-seismic joint adaptive multi-parameter intelligent lithofacies identification method comprises the steps of 1 taking two maximum wave troughs and a maximum wave crest as a seismic reflection unit; 2 extracting seismic reflection units according to a certain sequence; 3 determining characteristic parameters of the seismic reflection units; and 4 classifying the seismic reflection units with the multi-dimensional features according to the characteristic parameters. According to the well-to-seismic joint adaptive multi-parameter intelligent lithofacies identification method, seismic waveform parameter characteristics of different lithofacies are established by massively analyzing logging curves, lithologic characteristics and seismic waveform multi-parameter data in a single seismic reflection unit and by utilizing an artificial intelligence analysis method; according to the waveform parameter characteristics, an earthquake lithofacies identification mode is established; according to the method, the lithology identification problem is solved, and the method is of great significance to improvement of reservoir prediction precision and realization of rapid and effective exploration.

Description

technical field [0001] The invention relates to the technical field of oil and gas exploration geophysics, in particular to a well-seismic joint self-adaptive multi-parameter intelligent lithofacies identification method. Background technique [0002] In the field of seismic exploration, lithofacies identification is an important step in oil and gas exploration, which is of great significance to the success of exploration. At present, lithofacies identification mainly adopts seismic waveform classification technology. This technology is to classify seismic waveforms within a certain time window by using technologies such as fuzzy data and simple neural networks. This method can better solve lithofacies identification with large thickness and single and stable depositional environment. Many scholars at home and abroad have successfully applied this technology to the lithology identification and corresponding sedimentary facies of clastic rocks and carbonate reefs and banks. ...

AI Technical Summary

Problems solved by technology

The shortcoming of this application mainly lies in the limitation and singleness of the identification method, which largely depends on the logging data, core data and core analysis data of exploratory wells

When evaluating the diagenetic facies of the reservoir by core analysis, the core analysis process takes a lot of time and is expensive, the description of the reservoir is not complete, and the analysis data also has different degrees of differences due to different analysts, and there is no quantitative analysis. evaluation criteria, relying more on qualitative observation

In particular, the diagenetic facies identification method of this patent relies on the plane point distribution of a single well, and the lithofacies judgment in areas without well control is mainly based on non-quantitative sedimentary facies distribution prediction, which is difficult to achieve horizontal continuity and vertical Quantitative

Images