Reservoir feature prediction method and model based on deep learning

Abstract

The invention discloses a reservoir feature prediction method based on deep learning. The method comprises the following steps: acquiring a logging data training set; constructing a convolutional neural network and a forward-backward long-short term memory neural network added with an attention layer, and performing sequence modeling by combining the convolutional neural network and the forward-backward long-short term memory neural network to generate a multimode Bi-LSTM model; inputting the training set into a multi-mode Bi-LSTM model, training the multi-mode Bi-LSTM model by adopting a joint training mode, and performing joint optimization on parameters of a convolutional neural network and a forward-backward long-short term memory neural network added with an attention layer; and inputting actual logging data into the trained multimode Bi-LSTM model, and performing prediction through the model to obtain a prediction result of reservoir characteristics. According to the method, the advantage that bidirectional long and short time memory can efficiently and accurately perform time sequence prediction is utilized, and the attention mechanism layer is added, so that the defect that the convolutional neural network processes data with sequence correlation is made up, and reservoir characteristics such as porosity and permeability of reservoirs with different depths can be accurately predicted.

Description

technical field [0001] The invention relates to the technical field of reservoir transformation, in particular to a method and model for predicting reservoir characteristics based on deep learning. Background technique [0002] With the continuous expansion of human society's demand for clean energy, the development and production of low-grade oil and gas reserves such as low-permeability and ultra-low-permeability, and the shale gas revolution and tight oil breakthrough in the United States since the 21st century, the traditional reservoir stimulation technology has changed from An auxiliary process in the oil recovery process has developed into a system engineering that is as important as geophysical prospecting and drilling. Currently, two types of reservoir stimulation technologies commonly used are fracturing stimulation technology and acidizing stimulation technology. When using fracturing or acidizing technology for reservoir stimulation, in order to improve the poro...

AI Technical Summary

Problems solved by technology

[0007] The object of the present invention is to provide a method and model for predicting reservoir characteristics based on deep learning, so as to at least solve the technical problem of low prediction accuracy in the prior art when using convolutional neural networks to predict reservoir characteristics at different depths

Images