通过提取井旁地震道的特征参数 ,利用神经网络建立其与测井声波时差的非线性映射 ,进而外推井底以下声波曲线 ,从而实现地震、测井联合预测井底以下的地层压力。该方法克服了单纯地震层速度或单纯声波时差预测地层压力的局限性。经 NH地区实际资料模拟预测 ,效果良好 By extracting the characteristic parameters of the seismic trace next to the well, a neural network is used to establish a nonlinear mapping of the time difference between it and the well logging, and then extrapolation of the acoustic curve below the bottom of the well so as to realize seismic and well logging combined prediction of formation pressure below the bottom of the well. This method overcomes the limitations of the prediction of formation pressure by simply the velocity of seismic layer or purely acoustic time lag. After the actual data in the NH area are simulated and predicted, the result is good