A Reservoir Prediction Method Based on Bidirectional Recurrent Neural Network

Abstract

The invention relates to a reservoir prediction method based on a bidirectional cyclic neural network. Including: generation of well seismic data, generation of well label data, generation of label data set, construction and training of bidirectional cyclic neural network, saving the trained model, extracting seismic data corresponding to all geographical locations in the area, and It makes predictions and obtains a probability distribution of reservoirs under the entire region. The present invention establishes a one-to-one correspondence between each sampling point and reservoirs and non-reservoirs, wherein the input of each time step is the n-dimensional seismic data of each sampling point, and the output is the corresponding reservoir or non-reservoir marker . Through the training of labeled samples and hyperparameter adjustment, the optimal model is obtained, so that unlabeled data can be predicted, and finally a predicted seismic volume of the same dimension is generated, where the value of each sampling point is between 0 and 1 Prediction probability has achieved good results in 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