A method and system for intelligent prediction of reservoir parameters of volcanic rock reservoirs

Abstract

The invention relates to a method and system for intelligently predicting reservoir parameters of volcanic rock reservoirs. In the method, the known logging information of volcanic rock reservoirs is firstly processed according to the characteristics of the logging curve, and the volcanic rock oil is extracted from the data preprocessing results. The well logging curve data whose reservoir parameter correlation reaches a certain threshold forms the training set data and the rest forms the test set data. Based on the training set data, several regression algorithms are used combined with the big data machine learning algorithm to automatically establish the volcanic rock reservoir reservoir parameters and Regression estimation model between well logging curve features, at the same time based on several regression algorithms to automatically optimize the model parameters of the regression estimation model, use the test set data to test and evaluate the optimized regression estimation model, and unqualified models to automatically optimize the model parameters until regression The estimation model has passed the inspection and evaluation, and finally the regression estimation model that has passed the inspection and evaluation is used to carry out intelligent prediction of unknown reservoir parameters. The prediction results have high precision and small error.

Description

Technical field [0001] The present invention relates to the field of geological reservoir parameters, and specifically, there is a case of a volcanic reservoir reservoir parameter intelligent prediction method and system. Background technique [0002] At present, in the reservoir exploration and development technology, the reservoir parameters (also referred to as reservoir properties, including porosity, permeability, saturation, pore structure, etc.) are the core, and also reservoir parameters It is also an important parameter and basis in the reservoir evaluation study, so the reservoir parameters are predicted in the exploration and development of reservoirs. However, in the current reservoir exploration and development technology, all existing reservoir parameters predictive methods have certain limitations, and there is a low precision and large error. If you look at mathematics, the main problem with the lateral prediction of reservoir parameters and reservoir identificati...

AI Technical Summary

Problems solved by technology

[0016] To sum up, the existing technologies and methods for predicting reservoir parameters of volcanic reservoirs still face key problems: the application of technical methods is single, and there is no complete, comprehensive and applicable reservoir parameter prediction method for volcanic reservoirs. The method of reasonably processing reservoir logging information, the accuracy of prediction results is still low

Images