基于双向长短期记忆神经网络的储层孔隙度预测方法研究

Research on reservoir porosity prediction method based on bidirectional longshort-term memory neural network

孔隙度作为重要的储层物性参数之一,在储层评价中发挥着重要作用,因此,寻找一种低成本、高效的方法获取高精度的孔隙度成为了储层评价的重要课题.由于测井参数和孔隙度之间复杂的非线性映射关系和时序性特点,本文提出了一种基于双向长短期记忆(BiLSTM)神经网络的储层孔隙度预测方法,通过建立BiLSTM孔隙度预测模型,并在模型中使用Nadam自适应优化算法提高模型训练效率和准确率,引入Dropout正则化技术防止训练过程中发生过拟合,采用ReLU激励函数提高网络的鲁棒性和稳定性,最后利用实际测井数据验证其性能.研究结果表明,相较于长短期记忆循环神经网络(LSTM)、常规循环神经网络(RNN)和全连接深度神经网络(DNN),BiLSTM模型具有更高的预测精度,在储层参数预测方向具有广阔的应用前景.

As one of the important reservoir physical parameters, porosity plays an important role in reservoir evaluation. Therefore, finding a low-cost and efficient method to obtain high-precision porosity has become an important issue in reservoir evaluation. Due to the complex nonlinear mapping relationship and temporal characteristics between logging parameters and porosity, this paper proposes a reservoir porosity prediction method based on Bidirectional Long Short-Term Memory(BiLSTM) neural network. By establishing a BiLSTM porosity prediction model, and using the Nadam adaptive optimization algorithm in the model to improve the model training efficiency and accuracy, the Dropout regularization technology is introduced to prevent overfitting during the training process, and the ReLU excitation function is used to improve the robustness and stability of the network, and finally use actual logging data to verify its performance. The research results show that, compared with Long and Short-Term Memory Recurrent Neural Network(LSTM), conventional Recurrent Neural Network(RNN), and fully connected Deep Neural Network(DNN), the BiLSTM model has higher prediction accuracy, and it has broad application prospects in the direction of reservoir parameter prediction.