arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.07232physics.geo-phphysics.comp-ph
收藏

使用深度学习工具和技术进行地震全波形反演

Seismic Full-Waveform Inversion Using Deep Learning Tools and Techniques

Alan Richardson

摘要:

我证明了传统的地震全波形反演算法可以构建为递归神经网络,并使用TensorFlow等深度学习软件实现。应用另一个深度学习概念,即使用小批量数据的Adam优化器,比随机梯度下降和使用整个训练数据集计算成本函数和梯度的L-BFGS-B优化器更快地收敛到2D数据集上的真实波速模型。我还表明,使用反向模式自动微分的成本函数梯度计算是相同的伴随状态方法中使用的。

英文摘要:

I demonstrate that the conventional seismic full-waveform inversion algorithm can be constructed as a recurrent neural network and so implemented using deep learning software such as TensorFlow. Applying another deep learning concept, the Adam optimizer with minibatches of data, produces quicker convergence toward the true wave speed model on a 2D dataset than Stochastic Gradient Descent and than the L-BFGS-B optimizer with the cost function and gradient computed using the entire training dataset. I also show that the cost function gradient calculation using reverse-mode automatic differentiation is the same as that used in the adjoint state method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑