Learning velocity model for complex media with deep convolutional neural networks

TL;DR

This paper presents a deep learning approach using modified UNet architectures to accurately reconstruct velocity models of complex media from boundary measurements, demonstrating improved similarity to ground truth data.

Contribution

The paper introduces modifications to the UNet architecture for better velocity model reconstruction in complex media, validated with an open-source dataset.

Findings

Enhanced UNet models show statistically significant improvements.

Deep convolutional neural networks effectively solve the inverse velocity problem.

Results outperform previous methods in velocity profile accuracy.

Abstract

The paper considers the problem of velocity model acquisition for a complex media based on boundary measurements. The acoustic model is used to describe the media. We used an open-source dataset of velocity distributions to compare the presented results with the previous works directly. Forward modeling is performed using the grid-characteristic numerical method. The inverse problem is solved using deep convolutional neural networks. Modifications for a baseline UNet architecture are proposed to improve both structural similarity index measure quantitative correspondence of the velocity profiles with the ground truth. We evaluate our enhancements and demonstrate the statistical significance of the results.