Quantitative Analysis Method of Semi-supervised Global Optimization Seismic Facies Based on SOM

Abstract

The invention provides a semi-supervised global optimization seismic facies quantitative analysis method based on SOM, which belongs to the field of seismic exploration. The present invention first starts from the pre-stack data, analyzes and extracts the pre-stack texture features, avoids the blurring of tiny information in the data by the superposition operation, and can better represent the actual geological conditions; at the same time, it solves the problem that a small amount of label information cannot be effectively used The problem of adding label information to the learning process of the learner can make the obtained results more in line with the actual situation; moreover, by introducing the artificial bee colony algorithm, the optimal clustering of the SOM output layer is realized, so that the output layer neural The mapping relationship between elements and seismic facies is more reasonable; the invention can calculate deterministic indexes while dividing seismic facies, and provides more accurate and reasonable result judgment basis for developers to make decisions.

Description

technical field [0001] The invention belongs to the field of seismic exploration, in particular to a semi-supervised global optimization seismic facies quantitative analysis method based on SOM. Background technique [0002] Oil and natural gas resources have always played an important role in energy supply, and their renewable products have been applied in almost every field, which greatly affects social stability and economic development. Compared with solar energy, wind energy and other energy sources, oil and natural gas resources provide a more stable and continuous guarantee for various energy needs. Oil and natural gas resources have received great attention in various countries, and various mechanisms have been actively established to deal with possible energy crises. At present, seismic exploration is the most important, most effective and most widely used method in oil and gas exploration. [0003] Seismic facies analysis is based on the seismic data collected by...

AI Technical Summary

Problems solved by technology

At present, the result obtained by the mainstream seismic facies analysis method is only a spatial layout map, and the judgment result cannot be quantitatively analyzed. By performing a quantitative re-judgment on the seismic facies analysis results, developers can make better Provide more accurate and reasonable basis for decision-making

Images