Reservoir prediction method based on bidirectional recurrent neural network

Abstract

The invention relates to a reservoir prediction method based on a bidirectional recurrent neural network. The reservoir prediction method includes: generating well seismic data, generating well markeddata, generating a marked dataset, building and training the bidirectional recurrent neural network, storing a trained model, extracting seismic data corresponding to all geographic positions in a region, and performing prediction on the seismic data to acquire probability distribution of reservoirs below the whole region. A one-to-one corresponding relation between each sampling point and reservoirs and non-reservoirs is established, wherein input of each time step is n-dimension seismic data of each sampling point while output of the same is corresponding reservoir or non-reservoir marks. An optimal model is acquired by training marked samples and adjusting hyper-parameters, in this way, unmarked data can be predicted to finally generate a predicted seismic body of same dimension, and value of each sampling point is prediction probability between 0 and 1, so that the method has good effect on reservoir prediction.

Description

technical field [0001] The invention belongs to the technical field of geophysical exploration seismic data interpretation, and mainly relates to a reservoir prediction method based on a bidirectional cyclic neural network. Background technique [0002] Petroleum exploration methods are mainly divided into geological method, geophysical method, geochemical method and drilling method, among which the seismic physical exploration in the geophysical method is mainly used in each oil and gas field. Seismic exploration method is the application of artificial methods to make the earth's crust vibrate, such as artificial earthquakes produced by explosives. Then use sophisticated instruments to record the vibration of seismic waves at various points on the ground, and analyze these seismic waves and their derived data to determine whether there are oil fields below the formation. [0003] Reservoir seismic description is an important technology in oil and gas exploration and develo...

AI Technical Summary

Problems solved by technology

[0005] To sum up, the previous methods did not consider the depth (time) information of seismic waves in the formation process, failed to take multi-seismic attributes as model input, and used reservoir and non-reservoir information as labels to make the relationship between the two Establish a mapping relationship between them, so there are still limitations in the prediction of underground reservoirs in other areas

Images