一种层序地层对比方法、装置、电子设备及存储介质
By standardizing historical geological data and constructing a sequence stratigraphic correlation model, and utilizing deep learning technology and multimodal fusion methods, the problems of strong subjectivity and low efficiency in existing sequence correlation results have been solved, achieving high-precision automated sequence interface identification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- YANGTZE UNIVERSITY
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing sequence stratigraphy relies on manual qualitative interpretation, resulting in highly subjective and inefficient stratigraphic results. It is difficult to effectively integrate multi-dimensional geological information and achieve effective spatial closure, thus affecting the reliability and accuracy of sequence stratigraphy results.
By standardizing historical geological data, a sequence stratigraphic correlation model is constructed. Feature extraction and multimodal dynamic fusion are performed using a bidirectional long short-term memory network and a graph convolutional neural network. Combined with a contrastive learning mechanism and physical constraints, the sequence stratigraphic correlation model is trained to achieve automated sequence interface recognition.
It improves the accuracy and efficiency of stratigraphic correlation, solves the problem of spatial closure, and ensures the reliability and accuracy of stratigraphic correlation results.
Smart Images
Figure CN122412911A_ABST