Although there are plenty of approaches proposed for addressing seismic volumetric dip estimation, it still suffers from several limitations, for example, the expensive computation cost, the perturbations from sequence stratigraphic anomalies, and the difficulty for handling the complicated geologic structures. Recently, deep learning (DL)-based models have been proposed for seismic dip estimation, which use seismic dips calculated using the traditional methods as the training labels. Apparently, these DL-based models can effectively improve the computational efficiency; however, it still subjects to the limitations of the traditional algorithms. We propose a multichannel deep learning (MCDL) model for implementing seismic volumetric dip estimation, mainly including share module (SM), particular module (PM), and fused module (FM). First, we calculate seismic dips using several traditional methods based on 3-D real seismic data as the training labels, which are used to pretrain SM and PM. Then, we propose a workflow to create synthetic seismic data and ground-truth dip labels, which are used to fine-tune SM/PM and train FM. In this way, we can obtain a DL model by considering both the features of synthetic ground-truth dips and the calculated dips from real data. Moreover, we can effectively enhance the generalization ability of MCDL by pretraining with the estimated dip volumes from real data. To demonstrate its validity and availability, we apply MCDL to synthetic data and two 3-D real seismic volumes. The qualitative and quantitative comparisons illustrate the superiority of the proposed model over the traditional methods.

中文翻译：

---

通过多通道深度学习模型进行地震体积倾角估计


尽管已经提出了很多解决地震体积倾角估计的方法，但它仍然受到一些限制，例如昂贵的计算成本、层序地层异常的扰动以及处理复杂地质结构的困难。最近，人们提出了基于深度学习（DL）的地震倾角估计模型，该模型使用传统方法计算的地震倾角作为训练标签。显然，这些基于深度学习的模型可以有效提高计算效率；然而，它仍然受到传统算法的限制。我们提出了一种用于实现地震体积倾角估计的多通道深度学习（MCDL）模型，主要包括共享模块（SM）、特定模块（PM）和融合模块（FM）。首先，我们使用基于3D真实地震数据作为训练标签的几种传统方法计算地震倾角，用于预训练SM和PM。然后，我们提出了一个创建合成地震数据和地面真实倾角标签的工作流程，用于微调 SM/PM 和训练 FM。这样，我们就可以通过考虑合成地面真实倾角的特征和根据真实数据计算的倾角的特征来获得深度学习模型。此外，我们可以通过使用实际数据估计的倾角体积进行预训练，有效增强 MCDL 的泛化能力。为了证明其有效性和可用性，我们将 MCDL 应用于合成数据和两个 3-D 真实地震体。定性和定量比较说明了所提出的模型相对于传统方法的优越性。