We have built convolutional neural networks (CNNs) to obtain petrophysical properties in the depth domain from prestack seismic data in the time domain. We compare two workflows — end-to-end and cascaded CNNs. An end-to-end CNN, referred to as PetroNet, directly predicts petrophysical properties from prestack seismic data. Cascaded CNNs consist of two CNN architectures. The first network, referred to as ElasticNet, predicts elastic properties from prestack seismic data followed by a second network, referred to as ElasticPetroNet, that predicts petrophysical properties from elastic properties. Cascaded CNNs with more than twice the number of trainable parameters as compared to end-to-end CNN demonstrate similar prediction performance for a synthetic data set. The average correlation coefficient for test data between the true and predicted clay volume (approximately 0.7) is higher than the average correlation coefficient between the true and predicted porosity (approximately 0.6) for both networks. The cascaded workflow depends on the availability of elastic properties and is three times more computationally expensive than the end-to-end workflow for training. Coherence plots between the true and predicted values for both cases show that maximum coherence occurs for values of the inverse wavenumber greater than 15 m, which is approximately equal to 1/4 the source wavelength or λ/4. The network predictions have some coherence with the true values even at a resolution of 10 m, which is half of the variogram range used in simulating the spatial correlation of the petrophysical properties. The Monte Carlo dropout technique is used for approximate quantification of the uncertainty of the network predictions. An application of the end-to-end network for prediction of petrophysical properties is made with the Stybarrow field located in offshore Western Australia. The network makes good predictions of petrophysical properties at the well locations. The network is particularly successful in identifying the reservoir facies of interest with high porosity and low clay volume.

中文翻译：

---

利用卷积神经网络从叠前地震数据预测岩石物理性质

我们已经建立了卷积神经网络（CNN），以便从时域的叠前地震数据获得深度域的岩石物性。我们比较了两个工作流程-端到端和级联CNN。端到端的CNN（称为PetroNet）可根据叠前地震数据直接预测岩石物理特性。级联的CNN由两个CNN体系结构组成。第一个网络称为ElasticNet，可从叠前地震数据预测弹性特性，然后第二个网络称为ElasticPetroNet，可从弹性特性预测岩石物理特性。与端对端CNN相比，级联CNN的可训练参数数量多出两倍，对合成数据集显示出相似的预测性能。对于这两个网络，真实和预测的粘土体积之间的测试数据的平均相关系数（大约为0.7）高于真实和预测的孔隙率之间的平均相关系数（大约为0.6）。级联的工作流程取决于弹性属性的可用性，并且其计算量是用于训练的端到端工作流程的三倍。两种情况下真实值和预测值之间的相干图表明，对于大于15 m的逆波数值（大约等于源波长的1/4或 级联的工作流程取决于弹性属性的可用性，并且其计算量是用于训练的端到端工作流程的三倍。两种情况下真实值和预测值之间的相干图表明，对于大于15 m的逆波数值（大约等于源波长的1/4或 级联的工作流程取决于弹性属性的可用性，并且其计算量是用于训练的端到端工作流程的三倍。两种情况下真实值和预测值之间的相干图表明，对于大于15 m的逆波数值（大约等于源波长的1/4或λ / 4。网络预测即使在10 m的分辨率下也与真实值具有一定的一致性，这是模拟岩石物理特性的空间相关性所使用的方差图范围的一半。蒙特卡洛辍学技术用于网络预测不确定性的近似量化。端对端网络用于预测岩石物性是由位于澳大利亚西部近海的Stybarrow油田实现的。该网络可以很好地预测井位置的岩石物理特性。该网络在识别高孔隙度和低粘土体积的感兴趣的储层方面特别成功。