Seismic Prediction Method of Reservoir Physical Parameters Based on Artificial Intelligence Algorithm

Abstract

The invention provides a method for seismic prediction of reservoir physical parameters based on artificial intelligence algorithm, comprising: step 1, using seismic data to invert the compressional wave impedance, shear wave impedance and density of oil and gas reservoirs; step 2, performing rock physics model analysis, and Reservoir physical parameters such as porosity, oil and gas saturation, and permeability are linked with seismic data inversion results; step 3, based on rock physics model analysis, artificial intelligence algorithms are used to invert reservoir physical parameters. The seismic prediction method of reservoir physical parameters based on artificial intelligence algorithm makes use of the advantages of artificial intelligence algorithms such as hybrid genetic algorithm and the ability of seismic data to cover a large area of ​​oil reservoirs, which not only increases the calculation efficiency by 30%, but more importantly It increases the convergence of the inversion results to 100%, thereby greatly improving the accuracy of seismic prediction of reservoir physical parameters.

Description

technical field [0001] The invention relates to the field of seismic data processing and interpretation, in particular to an artificial intelligence algorithm-based seismic prediction method for reservoir physical parameters. Background technique [0002] When seismic waves propagate in complex oil and gas reservoirs, fluid flow in rock pores will be excited, and the static environment where fluid pressure is balanced everywhere will be broken, which will be reflected in the received seismic data. Inversion of seismic data to deduce various parameters of rocks has always been the direction of exploration efforts. Oil and gas reservoirs are becoming more and more complex, structure, lithology, and fluid properties are becoming heterogeneous, and the scale of oil and gas is becoming smaller and more complex. All of these put forward higher requirements for exploration technology. Recently, more and more public studies in the world have shown that the seismic response characte...

AI Technical Summary

Problems solved by technology

Due to the problems of strong nonlinearity and many local optimal solutions in reservoir parameter inversion, traditional local search algorithms, such as interior point method, steepest descent method, and conjugate gradient method, are difficult to obtain the global optimal solution.

Images