NEURAL NETWORK-BASED SEISMIC RESOLUTION ENHANCEMENT TECHNOLOGY
DOI:
https://doi.org/10.15407/dopovidi2024.03.011Keywords:
machine learning model, neural network, U-net architecture, loss functionAbstract
The paper contains description of a U-net architecture-based machine learning model created for seismic resolution enhancement and noise reduction. The presentation includes a brief explanation of the choice of publicly available synthetic data for training and verification purposes. Apart from architecture blocks description, the author describes variations of the loss functions used as metrics to verify the model’s performance.
Downloads
References
Nabhan, M. Hauzan. (2024). Analysis of Geological Structure based on 3D Virtual Outcrop Model and Physical Properties of Rocks in Wringinanom District, Gresik Regency, IOP Conference Series Earth and Environmental Science, 1307, No. 1. https://doi.org/10.1088/1755-1315/1307/1/012024
Nascimento, A. et all. (2023). Well-velocity variogram sensibility analysis when building geologically constrained velocity models for onshore seismic data. Conference: 18th Int. Congress of the Brazilian Geophysical Society.
Zhang, Y.-G., Wang, Y. & Yin, J.-J. (2010). Single point high density seismicdata processing analysis and initial evaluation. Shiyou Diqiu Wuli Kantan (Oil Geophys. Prospecting), 45, No. 2, pp. 201-207.
Xiao, F. et al. (2014). High-density 3D point receiver seismic acquisition andprocessing—a case study from the Sichuan Basin, China. Firs t Break, 32, No. 1. https://doi.org/10.3997/1365-2397.32.1.72598
Rebert, T., Sablon, R., Vidal, N., Charrier, P. & Soubaras, R. (2012). Improving pre-salt imaging with variable-depth streamer data. Proc. SEG Tech. Program Expanded Abstr., Sep., pp. 1-5.
Yang, J., Zhang, Y., Yu, Y. (2021). Nested U-Net Architecture Based Image Segmentation for 3D Neuron Reconstruction. J. Medical Imaging and Health Informatics. https://doi.org/10.1166/jmihi.2021.3379
Lu, P., Morris, M., Brazell, S., Comiskey, C. & Xiao, Y. (2018). Using generative adversarial networks to improve deep-learning fault interpretation networks. Lead. Edge, 37, No. 8, pp. 578-583. https://doi.org/10.1190/ tle37080578.1
Lim, B., Son, S., Kim, H., Nah, S. & Lee, K. M. (2017). Enhanced deepresidual networks for single image super-resolution. Proc. IEEEConf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), pp. 136-144.
Wu, X., Liang, L., Shi, Y. & Fomel, S. (2019). FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation. Geophysics, 84, No. 3, pp. IM35—IM45. https://doi.org/10.1190/geo2018-0646.1
Wu, X., Geng, Z., Shi, Y., Pham, N., Fomel, S. & Caumon, G. (2020). Building realistic structure models to train convolutional neural net-works for seismic structural interpretation. Geophysics, 85, No. 4, pp. WA27-WA39. https://doi.org/10.1190/geo2018-0646.1
Nedzelskyi, O. Y. & Lashchevska, N. O. (2023) Super-Resolution Image Restoration Using Convolutional Neural Network. Visnyk NTUU KPI Seriia — Radiotekhnika Radioaparatobuduvannia, 91, pp. 79-86 (in Ukrainian). https://doi.org/10.20535/RADAP.2023.91.79-86
Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V. & Garcia-Rodriguez, J. (2017). A review on deep learning techniques applied to semantic segmentation. arXiv:1704.06857. https://doi.org/10.48550/ arxiv.org/abs/1704.06857
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Reports of the National Academy of Sciences of Ukraine
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.