Detecting hydrocarbons in carbonates: joint interpretation of CSEM and seismic

This article investigates bypassing the inversion steps involved in a standard litho-type classification pipeline and performing the litho-type classification directly from imaged seismic data. We consider a set of deep learning methods that map the seismic data directly into litho-type classes, trained on two variants of synthetic seismic data: (i) one in which we image the seismic data using a local Radon transform to obtain angle gathers, (ii) and another in which we start from the subsurface-offset gathers, based on correlations over the seismic data. Our results indicate that this single-step approach provides a faster alternative to the established pipeline while being convincingly accurate. We observe that adding the background model as input to the deep network optimization is essential in correctly categorizing litho-types. Also, starting from the angle gathers obtained by imaging in the Radon domain is more informative than using the subsurface offset gathers as input.

show abstract

“…Our considered baseline approaches follow [4,31] and rely on a full Bayesian classifier and a Naive Bayes classifier.…”

Section: Bayesian Classificationmentioning

confidence: 99%

Seismic inversion with deep learning

et al. 2021

View full text Add to dashboard Cite

show abstract

Challenges of carbonate platform identification and characterization from seismic data in frontier exploration – evaluating a possible Miocene example from the SE Caribbean

Berrocoso

Masini

Salazar³

et al. 2021

View full text Add to dashboard Cite

The purpose of this study is to demonstrate that the identification of carbonate platforms in frontier exploration using seismic data remains challenging despite the variety of attributes that can be extracted from the data and their integration with other sources of information. A Miocene example from offshore Tobago (Southern Caribbean) is evaluated using 3D seismic data integrated with regional geology, potential fields, analogues, and structural restoration. The data are compatible with interpreting the target as shallow-marine carbonates, and a conceptual model is presented. However, far fewer of the seismic characteristics are diagnostic of a carbonate platform, and despite the intensive approach and the use of published criteria for subsurface carbonate interpretation, it was impossible to conclusively identify the target as a shallow-marine carbonate. Alternative explanations such as volcaniclastics, eroded remnants of siliciclastics and basement highs are considered. The study illustrates that it is common to find situations where the origin of a prospective geobody cannot be determined beyond significant levels of uncertainty unless it is drilled. If other elements of the petroleum system are favourable, this irreducible risk has to be accepted to avoid overlooking attractive carbonate reservoirs, provided all available data are used and all possible alternative interpretations considered.

show abstract

Detecting hydrocarbons in carbonates: joint interpretation of CSEM and seismic

Cited by 2 publications

References 4 publications

Seismic inversion with deep learning

Seismic inversion with deep learning

Challenges of carbonate platform identification and characterization from seismic data in frontier exploration – evaluating a possible Miocene example from the SE Caribbean

Contact Info

Product

Resources

About