# Accelerated Full Waveform Inversion by Deep Compressed Learning

## TL;DR

This paper introduces a deep learning method to reduce the computational cost of Full Waveform Inversion by selecting the most relevant seismic data.

## Contribution

The novel approach uses a deep neural network with compressed learning to efficiently select seismic data for inversion.

## Key findings

- The proposed method outperforms random sampling in 2D FWI using only 10% of the data.
- The approach enables efficient hierarchical selection of relevant seismic data for inversion.
- Results suggest potential for accelerating large-scale 3D FWI.

## Abstract

We propose and test a method to reduce the dimensionality of Full Waveform Inversion (FWI) inputs as a computational cost mitigation approach. Given modern seismic acquisition systems, the data (as an input for FWI) required for an industrial-strength case is in the teraflop level of storage; therefore, solving complex subsurface cases or exploring multiple scenarios with FWI becomes prohibitive. The proposed method utilizes a deep neural network with a binarized sensing layer that learns by compressed learning seismic acquisition layouts from a large corpus of subsurface models. Thus, given a large seismic data set to invert, the trained network selects a smaller subset of the data, then by using representation learning, an autoencoder computes latent representations of the shot gathers, followed by K-means clustering of the latent representations to further select the most relevant shot gathers for FWI. This approach can effectively be seen as a hierarchical selection. The proposed approach consistently outperforms random data sampling, even when utilizing only 10% of the data for 2D FWI, and these results pave the way to accelerating FWI in large scale 3D inversion.