With the expanding size of 3D seismic data, manual seismic interpretation becomes time-consuming and labor-intensive. For automating this process, recent progress in machine learning, in particular the convolutional neural network (CNN), has been introduced into the seismic community and successfully implemented for interpreting seismic structural and stratigraphic features. In principle, such automation aims at mimicking the intelligence of experienced seismic interpreters to annotate subsurface geology accurately and efficiently. However, most of the implementations and applications are relatively simple in their CNN architectures, which primary rely on the seismic amplitude but undesirably fail to fully use the preknown geologic knowledge and/or solid interpretational rules of an experienced interpreter who works on the same task. We have developed a generally applicable framework for integrating a seismic interpretation CNN with such commonly used knowledge and rules as constraints. Three example use cases, including relative geologic time-guided facies analysis, layer-customized fault detection, and fault-oriented stratigraphy mapping, are provided for illustrating how one or more constraints can be technically imposed and demonstrating what added values such a constrained CNN can bring. It is concluded that the imposition of interpretational constraints is capable of improving CNN-assisted seismic interpretation and better assisting the tasks of subsurface mapping and modeling.

中文翻译：

---

在地震解释卷积神经网络上施加解释约束

随着3D地震数据规模的扩大，人工地震解释变得既费时又费力。为了使这一过程自动化，机器学习，特别是卷积神经网络（CNN）的最新进展已被引入地震界，并成功地用于解释地震的结构和地层特征。原则上，这种自动化旨在模仿经验丰富的地震解释员的情报，以准确，高效地注释地下地质。但是，大多数实现和应用程序的CNN体​​系结构相对简单，它们主要依赖于地震振幅，但不合需要地却无法充分利用先前从事地质工作的地质知识和/或从事同一任务的有经验的口译员的扎实解释规则。我们已经开发了一种通用的框架，用于将地震解释CNN与约束等常用知识和规则集成在一起。提供了三个示例用例，包括相对的地质时间导向相分析，层定制的故障检测和面向故障的地层映射，以说明如何从技术上施加一个或多个约束条件，并说明这种受约束的CNN可以提供哪些附加值。带来。结论是，施加解释性约束能够改善CNN辅助的地震解释，并更好地辅助地下测绘和建模的任务。包括相对的地质时间导向相分析，层定制的断层检测和断层导向的地层制图，目的是说明如何从技术上施加一个或多个约束条件，并说明这种受约束的CNN可以带来什么附加值。结论是，施加解释性约束能够改善CNN辅助的地震解释，并更好地辅助地下测绘和建模的任务。包括相对的地质时间导向相分析，层定制的断层检测和断层导向的地层制图，目的是说明如何从技术上施加一个或多个约束条件，并说明这种受约束的CNN可以带来什么附加值。结论是，施加解释性约束能够改善CNN辅助的地震解释，并更好地辅助地下测绘和建模的任务。