摘要
采用人工神经网络(ANN)进行油气藏横向预测,只需给网络提供叠偏地震剖面数据和标定井油气信息。对川南、川西南碳酸盐岩储层以及川中薄层储层进行了预测、尝试。实验结果表明:这种方法可行、效果良好、成功率高,ANN以其特点将为油气描述提供新的手段。
All one has to do in lateral prediction for reservoir is to input stacked migrated seismic data and calibrated well data into a network. The tests on real data from carbonate reservoir in Sichuan South DangFengchang structure and thin layer reservoir in Sichuan middle Liangchi structure. The predication re- sult says that this technique will be an auxiliary means and will be more importante action for hydrocarbon description using seismic data because of its good performance and high success rate.
引文
1 肖强源等.综合多种地震信息预测油气富集区的模糊数学方法.石油地球物理勘探,1990,25(2) :1991~2000
2 Hecht,Nielgen R.Theory of the back-propagation neural network.IJCNN,1989:539~606