A physics-informed machine learning approach for scalable seismic-to-well tying using bulk time shifts
The Leading Edge · 01.08.2026 · 45 (8) · 607-614
DOI: 10.1190/tle-2026-1085 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Leading Edge, online erschienen am 31.07.2026. Verfasst von Hesham Hasan und 2 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben.
Abstract (Originalsprache)
Seismic-to-well tying remains a critical yet time-intensive component of seismic interpretation workflows. Although automated approaches have reduced manual effort, many rely on dynamic stretch-and-squeeze adjustments that maximize trace similarity at the expense of distorting the time–depth relationship. In large multiwell projects, maintaining efficiency and geophysical consistency remained challenging. This paper presented a physics-informed machine-learning workflow that jointly estimated the seismic wavelet and an optimal bulk time shift while explicitly avoiding dynamic warping of the time–depth relationship. The model was trained on a large synthetic data set constructed from randomly generated reflectivity series convolved with analytical wavelets of varying phase and bandwidth, with known bulk shifts applied. Realistic seismic variability was introduced through controlled augmentation, including additive noise, smooth low-frequency distortion, multiples, phase perturbations, and nonlinear time warping. The workflow was demonstrated on multiple wells from the publicly available F3 Netherlands offshore field data set. Results showed improved temporal alignment at zero lag, preservation of velocity plausibility, and rapid scalability. The method illustrated how machine learning can be integrated into interpretation workflows while maintaining physical realism.
Zitieren
APA
Hasan, H., Mabrouk, W., & Metwally, A. (2026). A physics-informed machine learning approach for scalable seismic-to-well tying using bulk time shifts. The Leading Edge, 45(8), 607-614. https://doi.org/10.1190/tle-2026-1085
Vancouver
Hasan H, Mabrouk W, Metwally A. A physics-informed machine learning approach for scalable seismic-to-well tying using bulk time shifts. The Leading Edge. 2026;45(8):607-614. doi:10.1190/tle-2026-1085
BibTeX
@article{Hasan2026,
author = {Hasan, Hesham and Mabrouk, Walid and Metwally, Ahmed},
title = {A physics-informed machine learning approach for scalable seismic-to-well tying using bulk time shifts},
journal = {The Leading Edge},
year = {2026},
volume = {45},
number = {8},
pages = {607--614},
doi = {10.1190/tle-2026-1085}
}
EUVIMED