We have adopted a method to understand uncertainty and interpretability of a Bayesian convolutional neural network for detecting 3D channel geobodies in seismic volumes. We measure heteroscedastic aleatoric uncertainty and epistemic uncertainty. Epistemic uncertainty captures the uncertainty of the network parameters, whereas heteroscedastic aleatoric uncertainty accounts for noise in the seismic volumes. We train a network modified from U-Net architecture on 3D synthetic seismic volumes, and then we apply it to field data. Tests on 3D field data sets from the Browse Basin, offshore Australia, and from Parihaka in New Zealand prove that uncertainty volumes are related to geologic uncertainty, model mispicks, and input noise. We analyze model interpretability on these data sets by creating saliency volumes with gradient-weighted class activation mapping. We find that the model takes a global-to-local approach to localize channel geobodies as well as the importance of different model components in overall strategy. Using channel probability, uncertainty, and saliency volumes, interpreters can accurately identify channel geobodies in 3D seismic volumes and also understand the model predictions.

中文翻译：

---

用于信道检测的编码器-解码器架构的不确定性和可解释性分析

我们采用了一种方法来理解贝叶斯卷积神经网络的不确定性和可解释性，用于检测地震体中的 3D 通道地质体。我们测量异方差的任意不确定性和认知不确定性。认知不确定性捕获网络参数的不确定性，而异方差随机不确定性解释了地震体积中的噪声。我们在 3D 合成地震体上训练从 U-Net 架构修改的网络，然后将其应用于现场数据。对来自澳大利亚近海的 Browse 盆地和新西兰 Parihaka 的 3D 现场数据集进行的测试证明，不确定性体积与地质不确定性、模型错误选择和输入噪声有关。我们通过使用梯度加权类激活映射创建显着体积来分析这些数据集的模型可解释性。我们发现该模型采用全局到局部的方法来定位通道地质体以及不同模型组件在整体策略中的重要性。使用通道概率、不确定性和显着体积，解释人员可以准确识别 3D 地震体积中的通道地质体，并了解模型预测。