Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Stankevich, A., Nechepurenko, I., Shevchenko, A., Gremyachikh, L., Ustyuzhanin, A., Vasyukov, A.
Format: Preprint
Veröffentlicht: 2021
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2110.08626
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929339687239680
author Stankevich, A.
Nechepurenko, I.
Shevchenko, A.
Gremyachikh, L.
Ustyuzhanin, A.
Vasyukov, A.
author_facet Stankevich, A.
Nechepurenko, I.
Shevchenko, A.
Gremyachikh, L.
Ustyuzhanin, A.
Vasyukov, A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2110_08626
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Learning velocity model for complex media with deep convolutional neural networks
Stankevich, A.
Nechepurenko, I.
Shevchenko, A.
Gremyachikh, L.
Ustyuzhanin, A.
Vasyukov, A.
Machine Learning
Sound
Audio and Speech Processing
86-10, 86A22
I.2.6
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.
title Learning velocity model for complex media with deep convolutional neural networks
topic Machine Learning
Sound
Audio and Speech Processing
86-10, 86A22
I.2.6
url https://arxiv.org/abs/2110.08626