Geologia Croatica, Vol. 78 No. 2, 2025.
Izvorni znanstveni članak
https://doi.org/10.4154/gc.2025.12
Shale Volume, Seismic Attributes, and Proper Data Preparation: Critical Components for Modelling Subsurface Lithology Distribution
Ana Kamenski
orcid.org/0000-0002-1237-1007
; Croatian Geological Survey, Zagreb, Croatia
Iva Kolenković Močilac
; Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb, Croatia
*
Marko Cvetković
orcid.org/0000-0002-4555-6083
; Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb, Croatia
*
* Dopisni autor.
Sažetak
The scarcity of well data and the inherent subjectivity of geological interpretations often leads to imprecise or oversimplified subsurface models. Traditional interpretation methods struggle with sparse datasets, necessitating the application of advanced machine learning techniques to enhance subsurface characterization. This study leverages artificial neural networks to predict lithology distribution using seismic attributes in the northern Croatian part of the Pannonian Basin System, an area with numerous exploratory wells. Seismic data, long employed as a supplementary interpretation tool, was used to generate a predictive lithological model, overcoming data limitations inherent to well-based methods. A key focus was the volume of shale, a lithological indicator, which was estimated using an extensive set of seismic attributes and processed through innovative data preparation techniques for artificial neural network analysis. A comprehensive artificial neural network based modelling approach was implemented over a 4365 km² 3D seismic dataset, targeting Pannonian (Late Miocene–Early Pliocene) sediments deposited in deltaic, turbiditic, and lacustrine environments. Results show that standardization of input data significantly improved model accuracy, particularly in capturing key geological features such as meandering sandstone-filled channels. In contrast, normalization led to unreliable predictions, while raw data substantially underestimated sandstone volumes. Despite its advantages, the method’s limitations stem from the inherent uncertainty in the volume of shale estimation and interpreter subjectivity. The approach is well-suited for geological settings with two or three dominant lithologies distinguishable on geophysical well logs. While applicable to coalbearing strata and shale-rich carbonates, its effectiveness in more complex geological settings requires further refinement. The findings highlight the untapped potential of legacy seismic data for geo-energy applications, including hydrocarbon exploration, geothermal studies, and carbon storage.
Ključne riječi
volume of shale; artificial neural networks; lithology mapping; geo-energy exploration
Hrčak ID:
333036
URI
Datum izdavanja:
28.4.2025.
Posjeta: 315 *