Investigating Shelf Margin Delta Exploration Plays Using Successful Machine Learning Techniques: Columbus Basin, Trinidad and Tobago

Abstract

Shelf margin deltas remain some of the most complex depositional systems for defining reservoir systems and hydrocarbon traps owing to inherent risk for exploration. In combination with structure (tectonic influences), hydrocarbon traps, mainly stratigraphic in nature remain challenging and there is a need to employ different approaches geared towards delineation and reducing risk in exploration. Machine Learning techniques, in the form of unsupervised seismic facies evaluations, both on a regional and sub-regional scale, have been applied to a study in the Columbus Basin, Trinidad. In combination with drilled well reservoir parameters, tectonic contribution and shallower stratigraphic analogs, the depositional history of the shelf to slope transition may be analyzed and potential areas for stratigraphic trap delineation can be identified. This topic is relevant to the workshop owing to risks associated with exploration of stratigraphic traps, identification and delineation, on the shelf and along the shelf to slope to basin transition in the northeast Atlantic basin area.

AAPG Datapages/Search and Discovery Article #90361 © 2019 AAPG Latin America & Caribbean Region Geosciences Technology Workshop, Recent Discoveries and Exploration and Development Opportunities in the Guiana Basin, Paramaribo, Suriname, November 6-7, 2019