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

Abstract

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.

Sensing prior constraints in deep neural networks for solving exploration geophysical problems

“…However, they differ from the PINNS discussed below in that they do not utilize automatic differentiation ( 98 ) to calculate the derivatives involved in the loss. Unsupervised learning can discover hidden patterns in unlabeled data and has also been used for various tasks including seismic facies classification ( 50 , 99 , 100 ), seismic signal or waveform classification ( 11 , 101 – 103 ), lithology classification ( 104 – 106 ), seismic migration ( 37 , 39 ), and inversion ( 107 , 108 ).…”

Assessment of spectral attributes in identifying gas hydrates in seismic data from the Pegasus Basin, offshore New Zealand

“…SOMs have been applied in other seismic studies to interpret deepwater seismic facies and architectural elements (La Marca and Bedle, 2021;La Marca, et al, 2019) and characterize turbidites in seismic data (Zhao et al, 2016), to evaluate reservoir lithology and rock type changes (Hussein et al, 2021) et al, 2018), or spectral shape attributes to measure attenuation of the amplitude spectrum, and so forth.…”

Economic Management Data Envelopes Based on the Clustering of Incomplete Data

“…Although there are several clustering algorithms in the field of clustering analysis, each algorithm has its unique method for discovering the underlying data structure in a dataset. However, different algorithms processing the same dataset may produce different clustering results, and it is difficult for us to evaluate which clustering result is more consistent with the data structure of that dataset without supervised information [6]. Completely random missing means that the missing values are lost completely at random, and the tendency of the data points to be missing is independent of their hypothetical values and the values of other variables.…”