How should the “quality” of seismic well ties and predictions of rock properties using machine learning be assessed?
The Leading Edge · 01.05.2026 · 45 (5) · 378-390
DOI: 10.1190/tle-2025-1058 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Leading Edge, online erschienen am 22.05.2026. Verfasst von John Castagna und 2 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben.
Abstract (Originalsprache)
The correlation coefficient has inadequacies as a metric for comparison of seismic data to presumed truth in the form of synthetic seismograms or well logs. It is not a direct measure of the information content of a prediction, nor the shared information between the prediction and perfect data. All else being equal, the information content (useful or not) of seismic data decreases monotonically with decreasing bandwidth, but the correlation coefficient may vary differently. Quantities from information theory, such as cross entropy, variation of information, and channel capacity, are measures that can aid in the assessment of the information content of a prediction and are amenable for use as loss functions in machine learning and other applications. These ideas were demonstrated on real and synthetic data.
Zitieren
APA
Castagna, J., Kronberg, V., & Gil, G. (2026). How should the “quality” of seismic well ties and predictions of rock properties using machine learning be assessed?. The Leading Edge, 45(5), 378-390. https://doi.org/10.1190/tle-2025-1058
Vancouver
Castagna J, Kronberg V, Gil G. How should the “quality” of seismic well ties and predictions of rock properties using machine learning be assessed?. The Leading Edge. 2026;45(5):378-390. doi:10.1190/tle-2025-1058
BibTeX
@article{Castagna2026,
author = {Castagna, John and Kronberg, Vì and Gil, Gabriel},
title = {How should the “quality” of seismic well ties and predictions of rock properties using machine learning be assessed?},
journal = {The Leading Edge},
year = {2026},
volume = {45},
number = {5},
pages = {378--390},
doi = {10.1190/tle-2025-1058}
}
EUVIMED