Novel machine learning workflow for rock property prediction in the geologically complex presalt Santos basin, Brazil

Clarke, Dan; Blaauw, Martijn; Guha, Jaydip; Sansal, Altay; Unaldi, Muhlis; Zhang, Barry

doi:10.1190/segam2021-3594813.1

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To better understand and characterize these reservoirs, several authors have published studies with different focuses, such as unsupervised seismic facies classification (Ferreira et al, 2019), supervised artificial neural networks to predict rock property parameters such as porosity and acoustic impedance (Clarke et al, 2021), stepped machine learning algorithm to create mineralogical models from geochemical and mineralogical data (de Oliveira et al, 2021), thin sections analysis in the nonreservoir section focusing the identification of distinct magnesian clays and the processes of preservation and transformation of these minerals (da Silva et al, 2021), and clay and water saturation volumes through a hybrid method which combines Nuclear Magnetic Resonance (NMR) and conventional logs (Castro and Lupinacci, 2022).…”

Section: Introductionmentioning

confidence: 99%

Depth-variant pore type modeling in a pre-salt carbonate field offshore Brazil

et al. 2022

View full text Add to dashboard Cite

Brazilian pre-salt carbonates encompass more than 70% of the total oil and gas produced in the country nowadays and yet, present several challenges such as heterogeneous composition in mineralogy with the presence of Mg-clays, a complex pore network and diagenetic processes, e.g., dolomitization, silicification and cementation. Rock physics provides a powerful route to understand the elastic behavior of rocks by connecting geology and geophysics. It is known that pore type determination is crucial to understand this behavior. In this paper, we propose a workflow that integrates several methods to obtain depth-variant distribution of pore types and their respective volumes for seven wells in the carbonate-bearing Barra Velha Formation interval. We compared the modeling results with thin sections, performed sensitivity analysis with several parameters (e.g., mineral content, saturation, different aspect ratios) to verify the impact of each one and, analyzed results with hydraulic flow units to search for favorable porosity-permeability scenarios and their relationship with the different pore types. Results suggest that the key parameters impacting the elastic behavior are mineralogy and pore types. Also, compliant pore type may act as connectors between pores with bigger storage capacity, such as reference and stiff pore types. The proposed workflow contributes to understand these complex carbonates, by providing a feasible path to obtain three pore type distributions for each depth point. Calibration with fluid data and especially mineralogy, is essential for the predictions to be as trustworthy as possible and should be applied for each well with available information.

show abstract

Section: Introductionmentioning

confidence: 99%

Depth-variant pore type modeling in a pre-salt carbonate field offshore Brazil

et al. 2022

View full text Add to dashboard Cite

show abstract

Estimating Rock Typing in Uncored Wells Using Machine Learning Techniques for Brazilian Pre-Salt Carbonate Reservoir

Allahham,

Botechia,

Davólio

et al. 2024

SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

Accurate rock typing in uncored wells is essential for enhancing reservoir models, particularly in complex geological formations like the Brazilian pre-salt carbonate reservoirs. This study explores the application of machine learning (ML) techniques to estimate rock types in uncored wells. The research leveraged core data from 11 cored wells to calculate the Rock Quality Index (RQI) and Flow Zone Indicator (FZI), identifying 14 distinct rock types through the Discrete Rock Typing (DRT) method, along with well log data such as gamma ray, density, neutron, permeability, and porosity. Various machine learning models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Gradient Boosting, Naive Bayes, XGBoost, and Random Forest were tested, where XGBoost achieved the highest accuracy of 73.3%. Applying XGBoost to all wells resulted in accuracy ranging from 0.6 to 0.91 and the model was subsequently used to estimate rock types in over 20 uncored wells to generate reservoir simulation models. This study highlights the efficacy of machine learning (particularly XGBoost) in addressing reservoir complexities and offering significant improvements in the understanding and development of carbonate reservoirs.

show abstract

Novel machine learning workflow for rock property prediction in the geologically complex presalt Santos basin, Brazil

Cited by 2 publications

References 2 publications

Depth-variant pore type modeling in a pre-salt carbonate field offshore Brazil

Depth-variant pore type modeling in a pre-salt carbonate field offshore Brazil

Estimating Rock Typing in Uncored Wells Using Machine Learning Techniques for Brazilian Pre-Salt Carbonate Reservoir

Contact Info

Product

Resources

About