A good understanding of different rock types and their distribution is critical to locate oil and gas accumulations in the subsurface. Traditionally, rock core samples are used to directly determine the exact rock facies and what geological environments might be present. Core samples are often expensive to recover and, therefore, not always available for each well. Wireline logs provide a cheaper alternative to core samples, but they do not distinguish between various rock facies alone. This problem can be overcome by integrating limited core data with largely available wireline log data with machine learning. Here, we presented an application of machine learning in rock facies predictions based on limited core data from the Umiat Oil Field of Alaska. First, we identified five sandstone reservoir facies within the Lower Grandstand Member using core samples and mineralogical data available for the Umiat 18 well. Next, we applied machine learning algorithms (ascendant hierarchical clustering, self-organizing maps, artificial neural network, and multi-resolution graph-based clustering) to available wireline log data to build our models trained with core-driven information. We found that self-organizing maps provided the best result among other techniques for facies predictions. We used the best self-organizing maps scheme for predicting similar reservoir facies in nearby uncored wells—Umiat 23H and SeaBee-1. We validated our facies prediction results for these wells with observed seismic data.
The Nenana basin of interior Alaska forms a segment of the diffuse plate boundary between the Bering and North American plates and is located within a complex zone of crustalscale strike-slip deformation that accommodates compressional stresses due to oblique plate convergence to the south. The basin is currently the focus of new oil and gas exploration.Integration of seismic reflection and well data, fracture data and apatite fission track analyses with regional data improves our understanding of the tectonic development of this continental strike-slip basin.The Nenana basin formed during the Late Paleocene as a 13-km-wide halfgraben, affected by regional intraplate magmatism and localized crustal thinning across the Minto fault in south-central Alaska. The basin was uplifted and exhumed along this faulted margin in Early Eocene through to Late Oligocene time in response to oblique subduction along the southern Alaska margin. This event resulted in the removal of up to 1.5 km of Late Paleocene strata from the basin. Renewed rifting and subsidence during Early Miocene time widened the basin to the west resulting in deposition of Miocene nonmarine clastic rocks in reactivated and newly-formed extensional half-grabens. In Middle to Late Miocene time, left lateral strike-slip faulting was superimposed on this half-graben system, with rapid subsidence beginning in Pliocene time and continuing to the present-day. At present, the Nenana basin is in a zone of transtensional deformation that accommodates compressional stresses due to oblique plate convergence and allows tectonic subsidence by oblique-extension along major basin-bounding strike-slip faults.
Central Interior Alaska is one of the most seismically active regions in North America, exhibiting a high concentration of intraplate earthquakes approximately 700 km away from the southern Alaska subduction zone. Seismological evidence suggests that intraplate seismicity in the region is not uniformly distributed, but concentrated in several discrete seismic zones, including the Nenana basin and the adjacent Tanana basin. Although the location and magnitude of the seismic activity in both basins are well defined by a network of seismic stations in the region, the tectonic controls on these intraplate earthquakes and the heterogeneous nature of Alaska’s continental interior remain poorly understood. We investigated the crustal structure of the Nenana and Tanana basins using available seismic reflection, aeromagnetic and gravity anomaly data, supplemented by geophysical well logs and outcrop data. We developed nine new two-dimensional forward models to delineate internal geometries and the crustal structure of Alaska’s interior. The results of our study demonstrates a strong crustal heterogeneity beneath both basins. The Tanana basin is a relatively shallow (up to 2 km) asymmetrical foreland basin with its southern, deeper side controlled by the northern foothills of the Central Alaska Range. Northeast-trending left lateral strike-slip faults within the Tanana basin are interpreted as a zone of clockwise crustal block rotation. The Nenana basin has a fundamentally different geometry. It is a deep (up to 8 km), narrow transtensional pull-apart basin that is deforming along the left-lateral Minto Fault. This study identifies two distinct modes of current tectonic deformation in Central Interior Alaska and provides a basis for modeling the interplay between intraplate stress fields and major structural features that potentially influence the generation of intraplate earthquakes in the region.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.