Theory-guided Pseudo-spectral Full Waveform Inversion via Deep Neural Networks
Christopher Zerafa, Pauline Galea, Cristiana Sebu
TL;DR
This paper introduces a theory-guided pseudo-spectral full waveform inversion framework implemented via a recurrent neural network (RNN) with Long Short-Term Memory units to emulate forward wave propagation. By recasting FWI as a physics-informed DNN, the authors achieve improved low-frequency content and stable convergence, demonstrated on synthetic data and the Marmousi model, and compare performance against classical time-domain FWI using adjoint-state methods. Key findings include faster convergence and better edge detection with the RNN, particularly in the frequency-domain formulation, along with insights into gradient behavior, hyper-parameter tuning, and practical considerations for data volume and computational power. The work suggests that theory-guided neural approaches can enhance inversion performance in challenging subsurface environments and outlines future directions such as alternative architectures, transfer learning, and real-data training strategies.
Abstract
Full-Waveform Inversion seeks to achieve a high-resolution model of the subsurface through the application of multi-variate optimization to the seismic inverse problem. Although now a mature technology, FWI has limitations related to the choice of the appropriate solver for the forward problem in challenging environments requiring complex assumptions, and very wide angle and multi-azimuth data necessary for full reconstruction are often not available. Deep Learning techniques have emerged as excellent optimization frameworks. Data-driven methods do not impose a wave propagation model and are not exposed to modelling errors. On the contrary, deterministic models are governed by the laws of physics. Seismic FWI has recently started to be investigated as a Deep Learning framework. Focus has been on the time-domain, while the pseudo-spectral domain has not been yet explored. However, classical FWI experienced major breakthroughs when pseudo-spectral approaches were employed. This work addresses the lacuna that exists in incorporating the pseudo-spectral approach within Deep Learning. This has been done by re-formulating the pseudo-spectral FWI problem as a Deep Learning algorithm for a theory-driven pseudo-spectral approach. A novel Recurrent Neural Network framework is proposed. This is qualitatively assessed on synthetic data, applied to a two-dimensional Marmousi dataset and evaluated against deterministic and time-based approaches. Pseudo-spectral theory-guided FWI using RNN was shown to be more accurate than classical FWI with only 0.05 error tolerance and 1.45\% relative percent-age error. Indeed, this provides more stable convergence, able to identify faults better and has more low frequency content than classical FWI. Moreover, RNN was more suited than classical FWI at edge detection in the shallow and deep sections due to cleaner receiver residuals.