神经网络在CB油田储层预测和储层厚度计算中的应用

APPLICATION OF NEURAL NETWORK TO PREDICTING RESERVOIR AND CALCULATING THICKNESS IN CB OILFIELD

根据ＣＢ油田的特点提出了利用神经网络进行储层预测和计算地层厚度的方法。将传统的储层预测方法与人工神经网络相结合，能较好地解决ＣＢ油田的储层预测问题。利用神经网络的非线性映射特点实现了地震特征与地层厚度之间的映射，从而可以准确地求取地层厚度。用该方法设计了２口探井，实际钻井结果表明，这种方法的预测结果准确、可靠。

This paper discusses the methods for predicting oil and gas reservoir and calculating thickness of reservoir from seismic data by using neural network. Combination of neural network with traditional seismic predicting methods can resolve the problem of reservoir prediction of CB oilfield. Neural network can be used to realize any continuous function or mapping. Using neural network to calculate the thickness of reservoir is to set up the relationship of seismic attributes and thickness. According to the prediction result, two evaluated wells have been drilled. The results from the drilled evaluation wells have kept consistence with its prediction.