Absorption attenuation compensation is an important part of seismic data processing. It enhances the resolution of nonstationary seismic data by compensating the amplitude energy and correcting phase distortion. The stabilized inverse $Q$ -filter method, a widely used attenuation compensation method, constructs compensation operators based on stratigraphy-related assumptions and compensates seismic data using time-window analysis, which is computationally complex and sensitive to noise. The essence of attenuation compensation lies in the establishment of a nonlinear mapping relationship between attenuated and nonattenuated seismic traces, which strongly benefits from deep learning. This article proposes a new method for attenuation compensation based on an end-to-end deep neural network to reduce the handcrafted step of time-window analysis. Instead, the convolutional blocks of the network automatically learn and process seismic data features to achieve simultaneous amplitude and phase compensation. We have constructed two end-to-end network architectures for attenuation compensation: a fully convolutional network (FCN) and a U-Net. As an effective spectrum-broadening method, the compensation method based on the U-Net is shown to enhance vertical resolution with good lateral continuity, to provide reliable compensation results without complex calculations, and to exhibit high noise robustness. Synthetic data tests indicate that the compensation results from the U-Net are better than those from either the FCN or the stabilized inverse $Q$ -filter method at different noise levels. Moreover, the correlation coefficient (CC) between the U-Net compensation results of the synthetic profile and the reference nonattenuated profile is higher than that of the FCN and the stabilized inverse $Q$ -filter method. A field data application further verifies the effectiveness of this method.

中文翻译：

---

使用端到端深度神经网络的吸收衰减补偿

吸收衰减补偿是地震资料处理的重要组成部分。它通过补偿振幅能量和校正相位失真来提高非平稳地震数据的分辨率。稳定的逆 $Q$滤波法是一种广泛使用的衰减补偿方法，它基于地层相关假设构造补偿算子，利用时间窗分析对地震数据进行补偿，计算复杂且对噪声敏感。衰减补偿的本质在于建立衰减和非衰减地震道之间的非线性映射关系，这极大地受益于深度学习。本文提出了一种基于端到端深度神经网络的衰减补偿新方法，以减少时间窗分析的手工步骤。相反，网络的卷积块会自动学习和处理地震数据特征，以实现同时幅度和相位补偿。我们为衰减补偿构建了两个端到端的网络架构：一个全卷积网络（FCN）和一个 U-Net。作为一种有效的频谱展宽方法，基于U-Net的补偿方法被证明可以提高垂直分辨率，具有良好的横向连续性，无需复杂计算即可提供可靠的补偿结果，并表现出较高的噪声鲁棒性。综合数据测试表明，U-Net 的补偿结果优于 FCN 或稳定逆的补偿结果 并表现出高噪声鲁棒性。综合数据测试表明，U-Net 的补偿结果优于 FCN 或稳定逆的补偿结果 并表现出高噪声鲁棒性。综合数据测试表明，U-Net 的补偿结果优于 FCN 或稳定逆的补偿结果 $Q$-不同噪声水平下的过滤方法。此外，合成剖面的 U-Net 补偿结果与参考非衰减剖面的相关系数 (CC) 高于 FCN 和稳定逆 $Q$-过滤方法。现场数据应用程序进一步验证了该方法的有效性。