Meta‐Learning‐Enhanced Implicit Full Waveform Inversion

Abstract

ABSTRACT Implicit full waveform inversion (IFWI) introduces implicit neural representations to parameterize the subsurface velocity model as a continuous function of spatial coordinates, which alleviates the dependence on the initial model and improves inversion flexibility. However, IFWI still requires a large number of iterative updates for each new exploration area, leading to slow convergence, high computational cost and a lack of mechanisms to share prior knowledge across different geological settings, thereby limiting its efficiency and generalization capability. To further accelerate convergence and enhance cross‐area generalization, we propose a meta‐learning‐based IFWI method, referred to as meta‐learning‐enhanced implicit full waveform inversion (Meta‐IFWI). In this framework, the subsurface velocity model is represented using an implicit neural network with periodic activation functions (SIREN), while a meta‐learning strategy is employed to pretrain a single network on multiple velocity inversion tasks. Through this process, the network learns shared inversion priors and rapid adaptation strategies across different geological scenarios. For a new inversion task, the meta‐trained initialization enables Meta‐IFWI to adapt to the observed seismic data with fewer gradient updates than randomly initialized IFWI. Numerical experiments conducted on the in‐distribution layered and Overthrust models and the out‐of‐distribution Marmousi 2 model demonstrate that Meta‐IFWI achieves higher final reconstruction accuracy under the same iteration budget and substantially reduces the online inversion time required to reach the velocity‐model error obtained by IFWI. Additional experiments conducted at three Gaussian‐noise levels further demonstrate that Meta‐IFWI consistently retains higher reconstruction accuracy and structural fidelity than IFWI for both in‐distribution and out‐of‐distribution models.