Self-adaptive multi-modal feature fusion well logging interpretation method based on multi-task joint learning

By proposing an adaptive multimodal feature fusion model based on multi-task joint learning in oil and gas exploration, combined with technologies such as graph convolution network and multi-head attention mechanism, the problem of difficulty in dealing with multiple logging indicators at the same time in the existing technology is solved, and high-precision joint prediction of permeability, porosity, formation saturation and lithologic classification is achieved, which significantly improves the prediction accuracy and reliability.

CN119760633APending Publication Date: 2025-04-04LIAONING UNIVERSITY OF PETROLEUM AND CHEMICAL TECHNOLOGY
0 Cites 15 Cited by

Patent Information

Application Number
CN202411807538.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-10
Publication Date
2025-04-04

AI Technical Summary

Technical Problem

The prior art is difficult to deal with multiple logging indicators at the same time in oil and gas exploration, and cannot fully utilize the intrinsic correlation between logging indicators, and it is difficult to capture the spatial relationship and geological similarity between wells, resulting in limited comprehensiveness and accuracy of the prediction results.

Method used

An adaptive multimodal feature fusion model based on multitasking joint learning is proposed, combining graph convolution network, multi-head attention mechanism, gating mechanism and adaptive loss weight adjustment algorithm to achieve high-precision joint prediction of permeability, porosity, formation saturation and lithology classification. This model integrates logging data and geological structure information through the shared feature extraction layer, and introduces a regularization module for physical constraints to ensure that the prediction results comply with geological physical laws.

Benefits of technology

It significantly improves the prediction accuracy and reliability of key logging indicators in oil and gas exploration, and can effectively capture the spatial and geological relationships between wells, ensuring the statistical accuracy and geological rationality of the prediction results.

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

Abstract

The invention provides an adaptive multi-modal feature fusion well logging interpretation method based on multi-task joint learning, and the model comprehensively employs a graph convolution network, a multi-head attention mechanism, a gating mechanism and an adaptive loss weight adjustment algorithm, and effectively integrates multi-well group well logging data and geological structure information. And the complex spatial relationship and geological similarity between the wells are fully captured. The model can process multi-source data in a unified manner, extracts high-level feature representation containing spatio-temporal correlation, avoids repeated feature learning, reduces calculation complexity, and ensures the consistency and complementarity of prediction task features at the same time. The self-adaptive loss weight adjustment mechanism dynamically optimizes weight distribution according to the loss change of each task, realizes balance optimization among different tasks, and comprehensively improves the prediction precision of each task. The physical constraint regularization module ensures that the prediction result not only has statistical accuracy, but also conforms to the actual geological physical law, so that the reasonability and reliability of the prediction result are improved.
Need to check novelty before this filing date? Find Prior Art