Trust-region versus line search globalization strategies for inexact Newton method and application in full waveform inversion

In this study, we consider the inexact Newton method using the trust-region and line search globalization strategies when solving the large-scale full waveform inversion problem. An elaborate stopping criterion or forcing term is introduced in order to avoid oversolvings of Newton equation. We develop an efficient method to compute (pseudo) Hessian vector products. In addition, a diagonal preconditioner based on the pseudo-Hessian approach is employed to further accelerate the solution of Newton equation. We discuss the specific parameter choices for these present methods. Numerical experiments based on the Marmousi2, BP 2004, and Sigsbee models are conducted to show the numerical performance of proposed inexact Newton methods. Numerical experiments demonstrate that the trust-region can perform better than the line search globalization strategy in the presence of nonlinearity and nonconvexity of the full waveform problem, especially for high contrast velocity models.

Automated summary

In this study, the inexact Newton method using trust-region and line search globalization strategies is considered for solving the large-scale full waveform inversion problem. A stopping criterion and forcing term are introduced to prevent oversolversion of the Newton equation. An efficient method is developed to compute (pseudo) Hessian vector products, and a diagonal preconditioner based on the pseudo-Hessian approach is employed to accelerate the Newton equation solution. Numerical experiments on various models demonstrate that the trust-region method performs better than the line search globalization strategy, especially for high contrast velocity models.