操作员(生物学)
反演(地质)
有限元法
算法
傅里叶变换
计算机科学
地震反演
人工神经网络
地震勘探
有限差分
卷积神经网络
波形
反问题
地质学
忠诚
快速傅里叶变换
地震波
地球物理成像
区域地质
有限差分法
高保真
噪音(视频)
水文地质学
傅里叶分析
波动方程
数据处理
加速度
工程地质
反变换采样
声波方程
数值分析
按位运算
作者
Li‐Min Wang,Zhe Wei,Yinhe Luo,Aifei Bian,Xianhai Song,Chao Chen
摘要
Abstract Solving the elastic or acoustic wave equation is essential for seismic imaging and inversion techniques. Although conventional methods, like finite difference or finite element schemes, are widely used, they suffer from low computational efficiency, especially in large‐scale applications. To overcome this limitation, we propose a novel deep learning‐based framework using Fourier neural operators (FNOs), which learn mappings from geological parameters to wavefield solutions. By integrating finite difference simulations with stochastic medium modelling, we generated training datasets encompassing diverse geological conditions. The neural operator was iteratively optimized through targeted training trials to enhance its predictive capability. The resulting operator achieves high accuracy ( L 2 error: 0.05–0.30) while preserving numerical fidelity comparable to traditional methods. More notably, the operator offers significant speedups, 170‐fold for acoustic and 260‐fold for elastic wave equations. Validated through comprehensive experiments, this operator serves as an efficient and reliable input for downstream seismic processing workflows, enabling end‐to‐end acceleration in seismic waveform inversion and imaging systems.
科研通智能强力驱动
Strongly Powered by AbleSci AI