Fluvial facies reservoir step-by-step seismic facies prediction method based on geological information constraint

Abstract

The invention discloses a fluvial facies reservoir step-by-step seismic facies prediction method based on geological information constraint. The method includes following steps: assessing geological data; establishing an analysis column chart, and comprehensively analyzing the column chart and a work area river channel sand body to obtain a superposition relation; abstracting a seismic response model; constructing a seismic sensitive attribute set; recognizing a seismic mode by employing a probabilistic neural network; performing related preprocessing operation on the seismic attribute; and performing seismic facies prediction to obtain a seismic facies map. The method is advantageous in that geological information is converted to monitoring information of the seismic scale and added to mode recognition of the seismic facies so that prediction results are more accurate, and clearer geological significance is achieved; the seismic facies prediction is performed by employing the probabilistic neural network so that clear indication significance is achieved for final seismic facies prediction results; the training time is greatly saved by employing the network training method; and the reservoir seismic facies in the range of the seismic scale can be fully predicted through the step-by-step prediction method without setting a classification number in advance.

Description

technical field [0001] The invention relates to the field of earthquake prediction, in particular to a step-by-step seismic facies prediction method for fluvial facies reservoirs based on geological information constraints. Background technique [0002] Today, the oil exploration industry effectively utilizes modern science and technology, thus promoting the rapid development of the oil industry and bringing huge benefits to the national economy. However, with the continuous improvement of oil exploration level, it is more and more difficult to find new oil and gas fields. This requires people to continuously improve their understanding and use scientific methods to understand and grasp the unknown conditions of oil and gas existence. More new information is excavated from data such as , oil reservoir development, etc. to predict oil and gas. [0003] In this process, the study of sedimentary facies is of great significance. It can not only analyze sedimentary microfacies a...

AI Technical Summary

Problems solved by technology

Its disadvantages are as follows: 1. The multilayer perceptron neural network uses the error back propagation algorithm to train the network. This training method has a slow convergence speed and usually takes a lot of computing time; When the network divides the seismic facies, it is usually "one step in place", that is, the existing supervision information is divided into several types, and the seismic facies of the reservoir is predicted at one time. This operation often leads to inaccurate classification

Images