A machine learning tool for interpretation of Mass Transport Deposits from seismic data

Abstract

Machine learning is a tool that allows machines or intelligent systems to learn and get equipped to solve complex problems in predicting reliable outcome. the learning process consists of a set of computer algorithms that are employed to a small segment of data with a view to speed up realistic interpretation from entire data without extensive human intervention. Here we present an approach of supervised learning based on artificial neural network to automate the process of delineating structural distribution of Mass Transport Deposit (MTD) from 3D reflection seismic data. The responses, defined by a set of individual attributes, corresponding to the MTD, are computed from seismic volume and amalgamated them into a hybrid attribute. this generated new attribute, called as MTD Cube meta-attribute, does not only define the subsurface architecture of MTD distinctly but also reduces the human involvement thereby accelerating the process of interpretation. the system, after being fully trained, quality checked and validated, automatically delimits the structural geometry of MTDs within the Karewa prospect in northern Taranaki Basin off New Zealand, where MtDs are evidenced. Mass Transport Deposits (MTDs), occurring in different tectonic and depositional settings, are defined as gravity induced slope failure deposits that include creeps, slides, slumps and debris flows 1−6. These deposits are internally deformed and associated with variable shape and size. During slope failure, masses tend to flow downslope over a shearing surface, called the basal shear surface (BSS) that forms the base of the MTDs. BSS preserves the record of all erosional and deformational activities experienced by these deposits or masses during their translation. Their interpretation is crucial, as such deposits during translation over the instable slope may lead to several catastrophic submarine events e.g., landslides, tsunamis, avalanches and thus possess precursory threats for subsea installations 7−15. Several authors 16−25 attempted to study the MTDs in order to understand their evolution, geomorphic character and possible trigger mechanisms responsible for slope failure. The use of modern techniques e.g., reflection seismic (2D/3D), side scan sonar, bathymetry etc. added value for their detailed investigation. In reflection seismic, the MTDs are first identified by mapping their top and BSS, and then interpreted from cross-sections and attribute maps 23−27. For this, the seismic attributes such as the root-mean square (RMS) amplitude, dip magnitude and coherency have been used for the interpretation of this geologic feature 23−26. Though the single attribute technology has been successful in interpreting MTDs from seismic data, several authors 28−29 demonstrated the downside of such approach, where a single attribute hardly ever responds to a particular geological target (see sections "Initial Interpretation" and "From Seismic Attributes to Meta-attributes" in the Supplementary Note for detailed explanation). The Taranaki Basin (TB) is a we...

Energy Recovery from Natural Gas Hydrate and Shallow Gas Reservoirs: Exploring the Impact of Interlayer Gas Cross-Flow Behaviors

“…MTDs, occurring in different tectonic and depositional settings, are defined as gravity induced slope failure deposits that include creeps, slides, slumps and debris flow. 27 This combination of factors leads to the trapping and accumulation of significant quantities of free gas, forming shallow gas reservoirs. 28 Due to the formation of upper gas chimneys resulting from overpressure release in a shallow gas reservoir, larger-scale NGH reservoir is gradually developed in the hydrate stability zone.…”

“…These sand layers are often capped by mass transport deposits (MTDs) characterized by low internal porosity, low pore ratio, and low permeability. MTDs, occurring in different tectonic and depositional settings, are defined as gravity induced slope failure deposits that include creeps, slides, slumps and debris flow . This combination of factors leads to the trapping and accumulation of significant quantities of free gas, forming shallow gas reservoirs .…”

Structural elements characterization using tridimensional seismic data analysis in Brazilian pre-salt reservoir, Santos Basin

“…Recently, multi-attribute analyses through ANN have gained even more acceptance due to the efficient recognition of geological discontinuities. The ANN might provide fault probability maps in which the probable locations of discontinuities are defined from the seismic data and estimations of connectivity of the fracture networks (e.g., Ashraf et al, 2020;Kumar and Sain, 2020).…”