Method for identifying geological anomalies and its model training method and device

Abstract

The invention provides a method for identifying geological anomalies and its model training method and device, and relates to the technical field of seismic exploration. The model training method includes: acquiring seismic diffraction wave data and seismic reflection wave data in a sample area; Wave data and seismic diffraction wave data are rendered to obtain training sample images; the sample images are input into the preset neural network model for training to obtain a model for geological anomaly prediction. By inputting the seismic wave data image to be identified into the pre-trained geological anomaly identification model, the result of geological anomaly identification can be output. This method uses the separated diffraction wave seismic data, adopts superimposed display technology to superimpose and display the seismic reflection wave section and the seismic diffraction wave section, and then completes the training of the neural network model based on the known geological anomaly data, and finally passes the input The actual superimposed display of seismic data enables high-precision prediction of geological anomalies in the study area.

Description

technical field [0001] The invention relates to the technical field of seismic exploration, in particular to a method for identifying geological anomalies and its model training method and device. Background technique [0002] Geological anomalies refer to geological bodies or combinations of geological bodies that are significantly different from the surrounding environment in terms of composition, structure, structure or genetic sequence. It is also often manifested as differences in geophysical fields, geochemical fields, and remote sensing image anomalies. It is mainly used for mineral prediction, and then used to summarize the regional mineralization law. The concealed disaster-causing geological anomalies are easy to be ignored due to their strong concealment, and there are great potential safety hazards. Therefore, there is an urgent need for an effective method that can finely describe the concealed disaster-causing geological anomalies. [0003] At present, the fi...

AI Technical Summary

Problems solved by technology

The concealed disaster-causing geological anomalies are easy to be ignored due to their strong secrecy, and have great potential safety hazards. Therefore, there is an urgent need for an effective method that can finely describe the concealed disaster-causing geological anomalies

[0003] At present, the fine characterization of geological anomalies includes fine seismic processing and fine seismic interpretation, etc. The auxiliary seismic interpretation methods include seismic attribute analysis, automatic tracking of ant bodies, artificial intelligence geological structure interpretation, etc., but the artificial intelligence recognition methods currently used , are based on reflected wave seismic data, and there is still room for improvement in the prediction effect

Images