Complex carbonate rock logging lithology identification method based on diffusion model

By generating lithological samples using a diffusion model and combining them with a CNN-Transformer model, the problem of small sample sizes and low-quality logging data in complex carbonate reservoirs was solved, achieving high-precision lithological identification and stability prediction.

CN121167516APending Publication Date: 2025-12-19CHINA UNIV OF GEOSCIENCES (WUHAN)
0 Cites 4 Cited by

Patent Information

Application Number
CN202511026128.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-24
Publication Date
2025-12-19

AI Technical Summary

Technical Problem

Existing lithology identification methods struggle to effectively handle small sample sizes and low-quality logging data in complex carbonate reservoirs, leading to decreased prediction accuracy and robustness, especially in accurately identifying rare lithology types under complex geological conditions.

Method used

Supplementary lithological samples were generated using a diffusion model-based approach, and a hybrid model combining a convolutional neural network (CNN) and a Transformer encoder was used for lithological identification. The hyperparameters were adjusted using a Bayesian optimization algorithm to improve the robustness and generalization ability of the model.

Benefits of technology

It significantly improves the accuracy and stability of lithology identification in complex carbonate reservoirs, better captures local features and global correlations, and enhances the accuracy and robustness of lithology prediction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention belongs to the technical field of carbonate rock oil-gas exploration, and particularly discloses a complex carbonate rock logging lithology identification method based on a diffusion model, and the method comprises the following steps: determining the lithology types of a plurality of observation wells based on the on-site rock core observation and slice analysis, and synchronously obtaining the logging data of the corresponding observation wells, constructing a lithology training data set in combination with a depth corresponding relationship between the lithology category and the logging data; a diffusion model is adopted to generate and supplement lithology categories with insufficient samples; logging data is adopted as an input feature, the lithology category is adopted as an output label, and a convolutional neural network fused with a Bayesian optimization algorithm and a Transformer hybrid model are utilized to train a lithology identification model; and inputting to-be-identified logging data into the trained lithology identification model, and outputting a lithology identification result. According to the method, high-precision lithology identification can be realized under the conditions of deep layers and complex stratums.
Need to check novelty before this filing date? Find Prior Art