CNN Prediction Enhancement by Post-Processing for Hydrocarbon Detection in Seismic Images

Jose Fabricio L Souza,Leonardo V Batista,Gustavo P Oliveira,Moises D Santos,Eduardo Roemers-Oliveira,Gabriel L Santana

doi:10.1109/access.2020.3005916

Jose Fabricio L Souza, Leonardo V Batista + Show 4 more

Open Access

https://doi.org/10.1109/access.2020.3005916

Copy DOI

Abstract

Seismic image interpretation is indispensable for oil and gas industry. Currently, artificial intelligence has been undertaken to increase the level of confidence in exploratory activities. Detecting potentially recoverable hydrocarbon zones (leads) under the viewpoint of computer vision is an emerging problem that demands thorough examination. This paper introduces a processing workflow to recognize geologic leads in seismic images that resorts to encoder-decoder architectures of a convolutional neural network (CNN) accompanied by segmentation maps and post-processing operations. We have used seismic images collected at offshore sites of the Sergipe-Alagoas Basin (northeast of Brazil) as input. After performing a patch-based data augmentation, a total of 29600 patches were achieved. Out of these, 24000 were used for training, 5000 for validation, and 600 for testing. Each image generated for the training set was post-processed through reconstruction, thresholding – binarization and deblurring –, and outlier removal. By using the dice loss function, intersection-over-union index, and relative areal residual computed after intense cross-validation training rounds, we have shown that the accuracy of the network to detect leads was higher than 80%. Furthermore, the validation error limits were found stable within 5% - 10% in all validation rounds, thereby resulting in a fairly accurate prediction of the pre-labelled hydrocarbon spots.

Highlights

Spotting hydrocarbon reservoirs accurately is one of the leading problems faced by geologists who have the tricky responsibility to read and interpret seismic images
Five supersequences can be recognized: i) Paleozoic, represented by permo-carboniferous sediments; ii) Pre-Rift, made up of sandstones; iii) Rift, composed by shale and lacustrine sandstones; iv) Post-Rift, formed by coarse-grained siliciclastics, evaporites, carbonates, and shale; v) Drift, comprised by an interval predominantly carbonatic which is followed by a second interval mainly clastic formed by sandstones, carbonates, and shales with turbiditic sandstones
We have proposed a workflow for identification of potential hydrocarbon-bearing accumulations recognized as geological leads in seismic images

Summary

Introduction

Spotting hydrocarbon reservoirs accurately is one of the leading problems faced by geologists who have the tricky responsibility to read and interpret seismic images. When seeking some evidence that spurs exploratory activities to achieve successful prospects, much effort and time are spent with the acquisition, analysis, and interpretation of geophysical and geological data [1]. Well drilling is costly and strongly dependent on human decisions. Exhaustive rounds of image interpretation are undertaken [2] to minimize potential failures that eventually are caused by subjective judgments [3]. The traditional seismic interpretation evolved from essential qualitative analyses to consistent quantitative methods, such as post-stack amplitude analysis

Objectives

Methods

Results

Conclusion