Mapping The Layers of The Ocean Floor With a Convolutional Neural Network

TL;DR

This paper explores using convolutional neural networks, specifically UNet, to efficiently map ocean floor layers, offering a promising alternative to traditional, complex seismic methods for the oil industry.

Contribution

It validates and compares two neural network architectures for velocity model inversion, demonstrating their effectiveness in ocean floor mapping.

Findings

Neural networks achieved Sørensen-Dice coefficients above 70%.

The study shows neural networks can be a stable and efficient alternative to traditional seismic methods.

Comparison indicates differences in stability metrics between architectures.

Abstract

The mapping of ocean floor layers is a current challenge for the oil industry. Existing solution methods involve mapping through seismic methods and wave inversion, which are complex and computationally expensive. The introduction of artificial neural networks, specifically UNet, to predict velocity models based on seismic shots reflected from the ocean floor shows promise for optimising this process. In this study, two neural network architectures are validated for velocity model inversion and compared in terms of stability metrics such as loss function and similarity coefficient, as well as the differences between predicted and actual models. Indeed, neural networks prove promising as a solution to this challenge, achieving S{\o}rensen-Dice coefficient values above 70%.