METHODS FOR THE AUTOMATED PRELIMINARY PROCESSING OF 3D SEISMIC DATA
DOI:
https://doi.org/10.34185/1991-7848.itmm.2026.01.024Keywords:
3D seismic data, pre-processing, machine learning, noise filtering, interpolation, neural networks, AutoMLAbstract
This paper examines modern methods of automated pre-processing of 3D seismic data, aimed at improving the quality of geophysical interpretation. It examines in detail the characteristic features of such data that necessitate pre-processing: the presence of strong noise, the heterogeneity of the physical properties of the medium, and the processing of large data sets. Traditional approaches to pre-processing are described, in particular filtering, normalisation, interpolation, signal alignment and methods for their amplification. Considerable attention is focused on innovative machine learning technologies, including the use of convolutional neural networks, autoencoders and generative models. The prospects for automating pre-processing workflows using optimisation algorithms and AutoML platforms are examined. The conclusions highlight key advantages, existing limitations and outline opportunities for the further development of hybrid approaches in this field.
References
Bacon M., Simm R., Redshaw T. 3-D Seismic Interpretation. Cambridge University Press, 2004. DOI:10.1017/S001675680422917X
Wrona T. et al. Seismic facies analysis using machine learning // Geophysics. s 83(5):1-34. DOI:10.1190/geo2017-0595.1
Anjom F.K. et al. Machine Learning for Seismic Exploration: where are we and how far are we from the Holy Grail? / Khosro Anjom, Farbod; Vaccarino, Francesco; Socco, Laura Valentina. - In: GEOPHYSICS. - ISSN 0016-8033. - 89:(2024), pp. 1-111. DOI:10.1190/geo2023-0129.1
Sebai D. et al. Seismic data compression: an overview // Multimedia Systems, 2024. DOI:10.1007/s00530-023-01233-4
Dmitriieva I., Dmytrenko A. Artificial intelligence methods for predicting hydrocarbon deposits // System Technologies, 2025. DOI 10.34185/1562-9945-4-159-2025-16
Wrona, T., I. Pan, R. E. Bell, R. L. Gawthorpe, H. Fossen, and S. Brune, 2021, 3-D seismic interpretation with deep learning: A set of Python tutorials, Version 0.1: GFZ Data Services, doi.org/10.5880/ GFZ.2.5.2021.001.
Dmitriieva I., Dmytrenko A. Application of machine learning methods in the processing of 3D seismic images // System Technologies, 2026. DOI: https://doi.org/10.34185/1562-9945-5-162-2026-25
