Using multi-attribute neural networks classification for seismic carbonate fades mapping: a workflow example from mid-Cretaceous Persian Gulf deposits

Abstract

Seismic facies mapping in large seismic surveys can be time consuming, even if only a basic overview of the facies distribution is needed. Therefore this study outlines an approach for the use of volume-based seismic attributes from 2D surveys for automated seismic facies mapping within carbonate settings. The study area is located in the central Persian Gulf, offshore Iran. The interval of interest is the mid-Cretaceous Sarvak Formation, which is part of the extensive Cretaceous shallow-water carbonate platform of the eastern Arabian Plate. A set of nine volume-based seismic attributes, calculated from time, amplitude and frequency information of post-stacked 2D seismic data, was chosen to characterize geological information within the interval of interest. The volume-based attributes were supplemented by two grid-based attributes to highlight structural elements. The geological significance of each attribute was evaluated by comparing it with results of seismic sedimentological/geomorphological studies. Furthermore, statistical methods were applied to highlight direct relationships amongst the attributes. The results of these tests were then used to choose a limited set of attributes for neural network-based multi-attribute classifications. The results show that seismic attributes derived from 2D surveys can be used to map basic seismic facies types in carbonate settings and that the outlined, general approach might be applied in other studies.

Late Cretaceous to Recent deformation related to inherited structures and subsequent compression within the Persian Gulf: a 2D seismic case study

“…At depth beneath the K-structure faults, chaotic reflectors may be indicative of a salt body. We therefore concur with Baaske et al (2007) that the K and E structures are salt-cored, and suggest further that movement on the Kazerun Fault during the Early Cretaceous formed pull-apart basins between the fault strands. This dilation of the overburden triggered the initial development of the salt diapir ("passive diapirism"; Vendeville & Jackson 1992;Hudec & Jackson 2007).…”

“…west-dipping) and timing (i.e. Cretaceous) of movement on this fault trend are consistent with those of other NNE-SSW-trending faults such as the Izeh Fault as determined from onshore exposures and seismic studies of salt movement (Sherkati & Fard et al 2006;Ahmadhadi et al 2007;Baaske et al 2007;Soleimani & Sabat 2010). Discontinuous variations in thickness (e.g.…”

“…Below 1.9 s TWT, reflectors become more chaotic and the exact nature of the structure at depth is unclear. Lowamplitude, chaotic reflections events at 7 s TWT may indicate that the Golshan structure and associated faults are underlain by a deep-seated, Hormuz Complex-related salt structure (see Baaske et al 2007).…”

“…The isochron map in Figure 8a indicates a slight thinning of the Jurassic sedimentary package over the South Pars Field structure. Within the Early Cretaceous package, there is thickening to the SW of the A and B fault structures (Figure 13), and further over the South Pars Field (Figure 8b) although the overall trend is that this package thins to the east, towards the Qatar-Fars Arch (Baaske et al 2007). During the Middle Cretaceous, the graben formed by the antithetic faults of the A systems is infilled by the sediments deposited during this period, causing a thickness increase of 30 ms TWT between these faults.…”

Classification of Seismic Windows Using Artificial Neural Networks

“…A variety of types of ANNs were explored in this research. Baaske et al [24] and Williamson et al [25] both successfully applied ANNs for automated seismic facies mapping. ANNs have been quite popular for discriminating natural earthquakes from manmade explosions.…”