Deep learning enhanced initial model prediction in elastic FWI: application to marine streamer data

TL;DR

This paper introduces a deep learning method using FusionNET CNN to generate initial low-wavenumber models for elastic FWI from high-frequency data, improving convergence in marine streamer data applications.

Contribution

The study presents a novel DL-based approach to estimate low-wavenumber models in elastic FWI, enhancing initial model quality without low-frequency data.

Findings

DL-fused initial models improve FWI convergence

Method generalizes to unrelated synthetic models

Enhanced imaging results on real marine data

Abstract

Low-frequency data are essential to constrain the low-wavenumber model components in seismic full-waveform inversion (FWI). However, due to acquisition limitations and ambient noise it is often unavailable. Deep learning (DL) can learn to map from high frequency model updates of elastic FWI to a low-wavenumber model update, producing an initial model estimation as if it was available from low-frequency data. We train a FusionNET-based convolutional neural network (CNN) on a synthetic dataset to produce an initial low-wavenumber model from a set of model updates produced by FWI on the data with missing low frequencies. We validate this DL-fused approach using a synthetic benchmark with data generated in an unrelated model to the training dataset. Finally, applying our trained network to estimate an initial low-wavenumber model based on field data, we see that elastic FWI starting from such a 'DL-fused' model update shows improved convergence on real-world marine streamer data.