Banca de QUALIFICAÇÃO: MAURICIO GABRIEL LACERDA MAFRA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : MAURICIO GABRIEL LACERDA MAFRA
DATE: 20/12/2023
TIME: 09:30
LOCAL: auditório do Dpto Geofísica/UFRN
TITLE:

MACHINE LEARNING APPLICATION FOR PERMEABILITY ESTIMATION USING NMR DATA OF RESERVOIR ROCKS

KEY WORDS:

Permeability; Porosity; Carbonates; Magnetic Resonance; Machine Learning.

PAGES: 77
BIG AREA: Ciências Exatas e da Terra
AREA: Geociências
SUMMARY:

This master's dissertation addresses the relevance of studies on rocks analogous to reservoirs in the oil industry, focusing on the crucial parameters of porosity and permeability. While traditional petrophysical techniques provide absolute values for these parameters, the lack of precise information about their causes emphasizes the use of more advanced techniques for a systematic analysis of reservoirs. Although Nuclear Magnetic Resonance demonstrates effectiveness in obtaining information about the reservoir, particularly in predicting permeability, existing analytical models show sensitivity limitations in specific patterns, especially in complex carbonate reservoirs. Faced with this gap, this study proposes to enhance predictions and modeling by employing machine learning models. The goal is to identify patterns in the responses of resonance data more accurately, providing significant improvements in predictions and understanding the reservoir's behavior. It was observed that the results of the Random Forest variations obtained the best response from the Resonance data.

COMMITTEE MEMBERS:
Presidente - 1506706 - MILTON MORAIS XAVIER JUNIOR
Interno - 1714488 - LEANDSON ROBERTO FERNANDES DE LUCENA
Externo ao Programa - 2411277 - MANILO SOARES MARQUES - UFRN