当前位置: X-MOL 学术Geophysics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Progressive transfer learning for low-frequency data prediction in full-waveform inversion
Geophysics ( IF 3.3 ) Pub Date : 2021-06-01 , DOI: 10.1190/geo2020-0598.1
Wenyi Hu 1 , Yuchen Jin 2 , Xuqing Wu 2 , Jiefu Chen 2
Affiliation  

To effectively overcome the cycle-skipping issue in full-waveform inversion (FWI), we have developed a deep neural network (DNN) approach to predict the absent low-frequency (LF) components by exploiting the hidden physical relation connecting the LF and high-frequency (HF) data. To efficiently solve this challenging nonlinear regression problem, two novel strategies are proposed to design the DNN architecture and to optimize the learning process: (1) the dual data feed structure and (2) progressive transfer learning. With the dual data feed structure, not only the HF data, but also the corresponding beat tone data, are fed into the DNN to relieve the burden of feature extraction. The second strategy, progressive transfer learning, enables us to train the DNN using a single evolving training data set. Within the framework of progressive transfer learning, the training data set continuously evolves in an iterative manner by gradually retrieving the subsurface information through the physics-based inversion module, progressively enhancing the prediction accuracy of the DNN and propelling the inversion process out of the local minima. The synthetic numerical experiments suggest that, without any a priori geologic information, the LF data predicted by the progressive transfer learning are sufficiently accurate for an FWI engine to produce reliable subsurface velocity models free of cycle-skipping artifacts.

中文翻译:

全波形反演中低频数据预测的渐进式迁移学习

为了有效克服全波形反演 (FWI) 中的跳周期问题,我们开发了一种深度神经网络 (DNN) 方法,通过利用连接低频和高频的隐藏物理关系来预测缺少的低频 (LF) 分量。 -频率(HF)数据。为了有效地解决这个具有挑战性的非线性回归问题,提出了两种新的策略来设计 DNN 架构和优化学习过程:(1) 双数据馈送结构和 (2) 渐进式迁移学习。采用双数据馈送结构,不仅将高频数据,还将相应的拍音数据馈入 DNN,以减轻特征提取的负担。第二种策略,渐进式迁移学习,使我们能够使用单个不断发展的训练数据集来训练 DNN。在渐进式迁移学习的框架内,训练数据集通过基于物理的反演模块逐渐检索地下信息,以迭代的方式不断演化,逐步提高DNN的预测精度,推动反演过程脱离局部最小值. 综合数值实验表明,在没有任何先验地质信息的情况下,渐进式转移学习预测的 LF 数据对于 FWI 引擎来说足够准确,可以生成可靠的地下速度模型,而不会出现跳周期伪影。逐步提高 DNN 的预测精度并推动反演过程脱离局部最小值。综合数值实验表明,在没有任何先验地质信息的情况下,渐进式转移学习预测的 LF 数据对于 FWI 引擎来说足够准确,可以生成可靠的地下速度模型,而不会出现跳周期伪影。逐步提高 DNN 的预测精度并推动反演过程脱离局部最小值。综合数值实验表明,在没有任何先验地质信息的情况下,渐进式转移学习预测的 LF 数据对于 FWI 引擎来说足够准确,可以生成可靠的地下速度模型,而不会出现跳周期伪影。
更新日期:2021-06-02
down
wechat
bug