Reservoir Prediction by Machine Learning Methods on The Well Data and Seismic Attributes for Complex Coastal Conditions

TL;DR

This paper presents a machine learning approach that integrates well data and seismic attributes to predict reservoir spread in complex coastal conditions, utilizing data augmentation and modification techniques to enhance accuracy.

Contribution

It introduces novel data augmentation and modification methods, Spindle and Revers-Calibration, to improve reservoir prediction from spatial and geological data.

Findings

Achieved an average F1 score of 0.798 for reservoir prediction.

Data augmentation improved prediction quality by a factor of 1.56.

The approach effectively handles complex coastal geological and geophysical data.

Abstract

The aim of this work was to predict the probability of the spread of rock formations with hydrocarbon-collecting properties in the studied coastal area using a stack of machine learning algorithms and data augmentation and modification methods. This research develops the direction of machine learning where training is conducted on well data and spatial attributes. Methods for overcoming the limitations of this direction are shown, two methods - augmentation and modification of the well data sample: Spindle and Revers-Calibration. Considering the difficulties for seismic data interpretation in coastal area conditions, the proposed approach is a tool which is able to work with the whole totality of geological and geophysical data, extract the knowledge from 159-dimensional space spatial attributes and make facies spreading prediction with acceptable quality - F1 measure for reservoir class 0.798 on average for evaluation of "drilling" results of different geological conditions. It was shown that consistent application of the proposed augmentation methods in the implemented technology stack improves the quality of reservoir prediction by a factor of 1.56 relative to the original dataset.