Carbonate reservoir sedimentary facies identification method and device, electronic equipment and medium

Abstract

The invention discloses a carbonate reservoir sedimentary facies identification method and device, electronic equipment and a medium. The method comprises the following steps: dividing a reservoir into a plurality of sedimentary facies, and preprocessing logging data to obtain preprocessed logging data; establishing a standard training library according to the preprocessed logging data of the plurality of sedimentary facies; constructing a long-short-term memory neural network model, and setting initial parameters of a neural network; inputting the samples of the standard training library into the long and short term memory neural network model for learning and training, and adjusting neural network parameters to obtain a final long and short term memory neural network model; and inputting the preprocessed logging data of the target well into the final long-short term memory neural network model, and predicting the reservoir sedimentary facies type of the target well. The method for automatically dividing the reservoir sedimentary facies is achieved through the long and short term memory network, the automatic recognition precision is high, the manual workload can be reduced, and the working efficiency can be improved.

Description

technical field [0001] The invention relates to the field of intelligent interpretation of well logging curves of oil reservoirs, and more specifically, to a method, device, electronic equipment and medium for identifying sedimentary facies of carbonate rock reservoirs. Background technique [0002] Carbonate reservoir is a hot field of oil and gas exploration and development at home and abroad. With the expansion of exploration and development to deep layers and deep seas, the number of drilling wells has decreased and the quality of data has deteriorated. In geological modeling and reserve calculation of carbonate reservoirs, the accuracy of sedimentary facies of conditionally constrained wells is higher, and core data are limited. , the standards for manually identifying sedimentary facies of uncored wells are not uniform, which brings challenges to the traditional method of identifying carbonate sedimentary facies. [0003] Logging curves can provide reservoir informati...

AI Technical Summary

Problems solved by technology

[0005] To sum up, the existing methods for classifying and identifying reservoir sedimentary facies based on well logging curves mainly have the following disadvantages: (1) The lithology identification accuracy of the existing methods is not high, and all identification methods rely heavily on data. (2) The current logging lithology automatic identification method cannot reflect that the sedimentary facies has a certain continuity at depth

Images