陆相页岩储层薄片超分辨率增强方法

Super-resolution imaging of thin sections for lacustrine shale reservoirs

郭超 赵谦平 刘刚 郝世彦 高潮 孙建博 刘超 陈奕奕

Chao Guo Qianping Zhao Gang Liu Shiyan Hao Chao Gao Jianbo Sun Chao Liu Yiyi Chen

近年来页岩油气的勘探与开发在全世界领域都取得了很大进展。然而在储层的矿物组分以及孔喉分布等微观物性研究中，经常受困于页岩储层微观尺度的限制，使得传统岩石薄片研究难以满足页岩储层精细化分析的需要。为了能够从原始页岩薄片图像中挖掘出更多储层微观特征，解决传统薄片精细图像在分辨率方面存在的限制与不足的问题，通过引入超分辨率增强技术来提高薄片图像对页岩储层微观特性的描述能力。针对页岩储层特点开发了一套基于生成对抗网络的超分辨率模型，建立了对应的薄片图像损失函数。最后以鄂尔多斯盆地延长组陆相页岩气储层的实际资料作为测试对象，进一步定性、定量地验证并确认了该方法的可用性、准确性以及可靠性。

Despite a great progress made in the exploration and development of shale gas and oil in recent years, the study on the pores, organic matter and mineral composition of shale reservoirs at a microscopic scale is still a challenge with thin section analysis for conventional reservoirs. In order to solve this problem, this study introduces a super-resolution technology to improve thin section image quality for revealing micro-characteristics of shale reservoirs. A set of super-resolution models are established based on generative adversarial networks and corresponding content loss functions are also set up for thin-section images. Application of the technology to the processing of actual data from lacustrine shale gas reservoirs in the Yanchang Formation in Ordos Basin has yielded positive results, demonstrating quantitatively and qualitatively its applicability, accuracy and reliability for unconventional reservoir assessment.

10.11743/ogg20210517