Turbidite Fan Interpretation in 3D Seismic Data by Point Cloud Segmentation Using Machine Learning

Abstract See how application of a fully trained Artificial Intelligence (AI) / Machine Learning (ML) technology applied to 3D seismic data volumes delivers an unbiased data driven assessment of entire volumes or corporate seismic data libraries quickly. Whether the analysis is undertaken using onsite hardware or a cloud based mega cluster, this automated approach provides unparalleled insights for the interpretation and prospectivity analysis of any dataset. The Artificial Intelligence (AI) / Machine Learning (ML) technology uses unsupervised genetics algorithms to create families of waveforms, called GeoPopulations, that are used to derive Amplitude, Structure (time or depth depending on the input 3D seismic volume) and the new seismic Fitness attribute. We will show how Fitness is used to interpret paleo geomorphology and facies maps for every peak, trough and zero crossing of the 3D seismic volume. Using the Structure, Amplitude and Fitness attribute maps created for every peak, trough and zero crossing the Exploration and Production (E&P) team can evaluate and mitigate Geological and Geophysical (G&G) risks and uncertainty associated with their petroleum systems quickly using the entire 3D seismic data volume.

Download Full-text

Unsupervised machine learning using 3D seismic data applied to reservoir evaluation and rock type identification

Interpretation ◽

10.1190/int-2020-0108.1 ◽

2021 ◽

pp. 1-69

Author(s):

Marwa Hussein ◽

Robert R. Stewart ◽

Deborah Sacrey ◽

Jonny Wu ◽

Rajas Athale

Keyword(s):

Machine Learning ◽

Seismic Data ◽

Rock Type ◽

Seismic Attributes ◽

Reservoir Quality ◽

3D Seismic ◽

Reservoir Properties ◽

Unsupervised Machine Learning ◽

Amplitude Data ◽

3D Seismic Data

Net reservoir discrimination and rock type identification play vital roles in determining reservoir quality, distribution, and identification of stratigraphic baffles for optimizing drilling plans and economic petroleum recovery. Although it is challenging to discriminate small changes in reservoir properties or identify thin stratigraphic barriers below seismic resolution from conventional seismic amplitude data, we have found that seismic attributes aid in defining the reservoir architecture, properties, and stratigraphic baffles. However, analyzing numerous individual attributes is a time-consuming process and may have limitations for revealing small petrophysical changes within a reservoir. Using the Maui 3D seismic data acquired in offshore Taranaki Basin, New Zealand, we generate typical instantaneous and spectral decomposition seismic attributes that are sensitive to lithologic variations and changes in reservoir properties. Using the most common petrophysical and rock typing classification methods, the rock quality and heterogeneity of the C1 Sand reservoir are studied for four wells located within the 3D seismic volume. We find that integrating the geologic content of a combination of eight spectral instantaneous attribute volumes using an unsupervised machine-learning algorithm (self-organizing maps [SOMs]) results in a classification volume that can highlight reservoir distribution and identify stratigraphic baffles by correlating the SOM clusters with discrete net reservoir and flow-unit logs. We find that SOM classification of natural clusters of multiattribute samples in the attribute space is sensitive to subtle changes within the reservoir’s petrophysical properties. We find that SOM clusters appear to be more sensitive to porosity variations compared with lithologic changes within the reservoir. Thus, this method helps us to understand reservoir quality and heterogeneity in addition to illuminating thin reservoirs and stratigraphic baffles.

Download Full-text