Direct Hydrocarbon Indicators Mapping via Joint Cluster Analysis: A Two-Step Approach over 3D Seismic Data

Direct Hydrocarbon Indicators Mapping via Joint Cluster Analysis: A Two-Step Approach over 3D Seismic Data

Authors

DOI:

https://doi.org/10.21680/2447-3359.2024v10n2ID35149

Abstract

This paper presents a novel methodology developed in Python to map direct hydrocarbon indicators anomalies in 3D seismic data using the unsupervised machine learning algorithms K-Means and Gaussian Mixture Models. The joint cluster analysis consists of implementing the spatial density-based filtering after clustering analysis and investigates the groups interpreted as DHI aiming to distinguish sparsely dense samples and noisy information from samples that are, in fact, areas of interest for hydrocarbon exploration. The experiments were performed on the 3D seismic data F3 Block from Central Graben Basin, Dutch North Sea. To conduct the experiments, the following seismic attributes were extracted: Spectral Decomposition of 25 and 45 Hz, Relative Acoustic Impedance, Coherence, Logarithm of Sweetness, and Reflection Strength. The working flowchart took advantage of good artificial intelligence practices to train the models, such as seismic attributes preconditioning, dimensionality reduction via Principal Component Analysis (PCA), and model validation through statistical tests. Despite the initial challenges faced in isolating DHI anomalies through the K-Means algorithm, the two-step approach ultimately succeeded in accurately mapping them

Downloads

Download data is not yet available.

Author Biographies

Vinicius Carneir Santana, GAIA/UFBA

BS em geofísica e MS em geofísica aplicada na UFBA. Tem experiência em diversos projetos de pesquisa nas bacias do São Francisco, Recôncavo, Camamu-Almada e Campos. Durante dois anos, ele foi professor de Perfilagem Geofísica de Poços e Geologia do Petróleo na UFBA. Atualmente é candidato ao Ph.D em geofísica aplicada na UFBA, com foco em geomorfologia sísmica dos depósitos de fluxos de gravidade em águas profundas, e nas bacias da Margem Equatorial Brasileira. Ele também atua como Pesquisador Geofísico no LAGESED-UFRJ onde desenvolve pesquisa no intervalo do pré-sal.

Alexsandro Guerra Cerqueira, GAIA/UFBA

Bacharel em Geofísica, Mestre e Ph.D. em Geofísica Aplicada pela UFBA, sou professor na Universidade Federal da Bahia desde Maio de 2019. Atualmente, sou pesquisador no INCT - Geofísica do Petróleo/CNPq, líder do Grupo de Estudo e Aplicação de Inteligência Artificial em Geofísica (GAIA/UFBA), com foco em algoritmos de aprendizado de máquina aplicado à dados sísmicos e de perfis geofísicos de poço.

Published

30-09-2024

How to Cite

BARBOSA, M. R. S.; SANTANA, V. C.; CERQUEIRA, A. G. Direct Hydrocarbon Indicators Mapping via Joint Cluster Analysis: A Two-Step Approach over 3D Seismic Data : Direct Hydrocarbon Indicators Mapping via Joint Cluster Analysis: A Two-Step Approach over 3D Seismic Data . Notheast Geoscience Journal, [S. l.], v. 10, n. 2, p. 298–315, 2024. DOI: 10.21680/2447-3359.2024v10n2ID35149. Disponível em: https://periodicos.ufrn.br/revistadoregne/article/view/35149. Acesso em: 21 nov. 2024.

Issue

Section

Artigos