Reservoir parameter determination method and device, electronic equipment and storage medium

Abstract

An embodiment of the invention discloses a reservoir parameter determination method and device, electronic equipment and a storage medium. The reservoir parameter determination method comprises the steps of: calculating an initial stratum elastic parameter body according to a constructed target rock physical model and obtained elan interpretation data of a target region; based on the acquired seismic data of the target area and the initial elastic parameter body, determining a target stratum elastic parameter body in a pre-stack elastic parameter inversion mode; constructing an inverse function model of the target rock physical model based on a neural network learning method, wherein the inverse function model is used for converting the stratum elastic parameter body into reservoir parameters; and inputting the target stratum elastic parameter body into the inverse function model, and determining reservoir parameters of the target area according to the output of the inverse function model. According to the reservoir parameter determination method and the device, rock physical modeling and neural network deep learning are combined, the inverse function of the rock physical model is determined through deep learning, the reservoir parameters are predicted through the inverse function, and the prediction efficiency and precision of the reservoir parameters are improved.

Description

technical field [0001] The present application relates to the field of oil and gas exploration and development, in particular to a reservoir parameter determination method, device, electronic equipment and storage medium. Background technique [0002] Reservoir parameters are important evaluation parameters in research fields such as oil and gas prediction, reservoir description, reserve estimation and oil and gas exploration. How to obtain reservoir parameters accurately is an important issue. [0003] At present, the commonly used methods for predicting reservoir parameters in 3D formation space mainly include the statistical relationship method. Since the functional relationship between reservoir physical and fluid saturation parameters and formation elastic parameters is not clear, the statistical law is not strong (the relationship between porosity and impedance of different lithologies is relatively scattered), and there are different statistical relationships between ...

AI Technical Summary

Problems solved by technology

Since the functional relationship between reservoir physical and fluid saturation parameters and formation elastic parameters is not clear, the statistical law is not strong (the relationship between porosity and impedance of different lithologies is relatively scattered), and there are different statistical relationships between different lithologies and their physical properties If a unified porosity-impedance relationship conversion is adopted, the prediction results and the actual drilling results will have large errors and poor predictability; if the conversion is performed according to different statistical relationships according to different lithologies of the formation, it will lead to sudden changes in porosity between different lithologies , which is obviously inconsistent with the actual situation of uniform change of formation porosity

Therefore, the current reservoir parameter prediction method cannot meet the demand for reservoir parameter prediction accuracy in current fine oil and gas exploration

Images