首頁»
最新錄用
Petroleum Science > DOI: https://doi.org/10.1016/j.petsci.2025.03.039
Diffraction classification imaging using coordinate attention enhanced DenseNet Open?Access
文章信息
作者:Tong-Jie Sheng, Jing-Tao Zhao, Su-Ping Peng, Zong-Nan Chen, Jie Yang
作者單位:
投稿時(shí)間:
引用方式:Tong-Jie Sheng, Jing-Tao Zhao, Su-Ping Peng, Zong-Nan Chen, Jie Yang, Diffraction classification imaging using coordinate attention enhanced DenseNet, Petroleum Science, 2025, https://doi.org/10.1016/j.petsci.2025.03.039.
文章摘要
Abstract: In oil and gas exploration, small-scale karst cavities and faults are important targets. The former often serve as reservoir space for carbonate reservoirs, while the latter often provide migration pathways for oil and gas. Due to these differences, the classification and identification of karst cavities and faults are of great significance for reservoir development. Traditional seismic attributes and diffraction imaging techniques can effectively identify discontinuities in seismic images, but these techniques do not distinguish whether these discontinuities are karst cavities, faults, or other structures. It poses a challenge for seismic interpretation to accurately locate and classify karst cavities or faults within the seismic attribute maps and diffraction imaging profiles. In seismic data, the scattering waves are associated with small-scale scatters like karst cavities, while diffracted waves are seismic responses from discontinuous structures such as faults, reflector edges and fractures. In order to achieve classification and identification of small-scale karst cavities and faults in seismic images, we propose a diffraction classification imaging method which classifies diffracted and scattered waves in the azimuth-dip angle image matrix using a modified DenseNet. We introduce a coordinate attention module into DenseNet, enabling more precise extraction of dynamic and azimuthal features of diffracted and scattered waves in the azimuth-dip angle image matrix. Leveraging these extracted features, the modified DenseNet can produce reliable probabilities for diffracted/scattered waves, achieving high-accuracy automatic classification of cavities and faults based on diffraction imaging. The proposed method achieves 96% classification accuracy on the synthetic dataset. The field data experiment demonstrates that the proposed method can accurately classify small-scale faults and scatterers, further enhancing the resolution of diffraction imaging in complex geologic structures, and contributing to the localization of karstic fracture-cavern reservoirs.
關(guān)鍵詞
-
Keywords: diffraction imaging; diffraction classification; azimuth-dip angle image matrix; coordinate attention; DenseNet