在欧洲地球科学家与工程师协会 (EAGE) 旗下期刊《First Break》第二期中，Ciaran Collins 和 Abdulqadir Cader 介绍了一种利用多个三维深度学习卷积神经网络 (CNN) 的集成断层解释工作流程。

准确的断层解释仍然是地下特征描述的关键组成部分，尤其是在构造复杂的环境中，断层的存在和几何形态会直接影响井位部署和储层性能。传统的工作流程虽然可靠，但速度较慢且往往带有主观性，尤其是在成像质量差或断层位移细微的情况下。在复杂的构造环境中（如下所示），即使断层几何形态上的微小误差也可能导致钻井过程中出现代价高昂的意外。

在本文中，Geoteric 的客户支持地球科学家 Ciaran 和首席地球科学家 Abdulqadir 展示了 Geoteric 的三维深度学习 CNN 如何针对地震数据中不同的断层表现形式进行优化，从而实现对地下结构的稳健而全面的理解，进而指导井位规划。

In Issue 2 of the European Association of Geoscientists and Engineers (EAGE) First Break magazine, Ciaran Collins and Abdulqadir Cader present an integrated fault interpretation workflow using multiple 3D deep learning convolutional neural networks (CNNs).

Accurate fault interpretation remains a critical component of subsurface characterisation, particularly in structurally complex settings where fault presence and geometry directly influence well placement and reservoir performance. Traditional workflows, while trusted, are slow and often subjective, especially when imaging is poor or faults exhibit subtle displacement. In challenging structural settings (as shown below) even small errors in fault geometry can lead to costly surprises during drilling.

In this paper Ciaran, Customer Support Geoscientist and Abdulqadir, Lead Geoscientist at Geoteric demonstrate how Geoteric 3D deep learning CNNs, optimised to detect different fault expressions in seismic data, enable a robust and comprehensive understanding of subsurface structure for well planning.