General Earth and Planetary Sciences, Geology, Geophysics, Stratigraphy
33
Scopus Publications
Scopus Publications
A data-driven approach to predict fracture intensity using machine learning for presalt carbonate reservoirs: A feasibility study in the Mero Field, Santos Basin, Brazil Eberton Rodrigues de Oliveira Neto, Fábio Júnior Damasceno Fernandes, Tuany Younis Abdul Fatah, Raquel Macedo Dias, Zoraida Roxana Tejada da Piedade, Antonio Fernando Menezes Freire, Wagner Moreira Lupinacci Energy Geoscience, 2025 Predicting fracture intensity is essential for optimising reservoir production and mitigating drilling risks in the Brazilian pre-salt layer. However, previous studies rely excessively on conceptual models and typically do not integrate multiple types of data to perform such task. Moreover, to date, no feasibility-like studies have assessed the reasonableness of such approaches. We propose a data-driven approach that utilises upscaled well logs (Young's modulus, Poisson's ratio, and silica content) alongside seismic attributes (curvature, distance to fault) to predict fracture intensity. The distance to fault is measured using the fault probability volume estimated by a pre-trained convolutional neural network (CNN). We evaluate the effectiveness of this data-driven approach employing two tree-ensemble models, eXtreme Gradient Boosting (XGBoost) and Random Forest, to estimate the volumetric fracture intensity (P32) in the wells. Regression and residual analyses indicate that XGBoost outperforms Random Forest. Results from feature importance methods, such as permutation importance and Shapley Additive explanations (SHAP), highlight curvature as the most important feature, followed by distance to fault, Young's modulus (or P-Impedance), silica content, and Poisson's ratio. The approach has been validated with rock sampling information and two blind tests. Consequently, we believe this workflow can be applied to other wells in nearby fields. The study offers a valuable tool for quantitatively estimating fracture intensity in pre-salt reservoirs. Future research may use this study as a reference for estimating fracture intensity within a seismic volume. The predicted fracture intensity estimates can enhance the reliability of reservoir porosity models and serve as a geohazard indicator to mitigate drilling risks. • Evaluate two tree-ensemble methods to predict fracture intensity in the Barra Velha Fm. • XGBoost outperformed Random Forest regarding regression metrics. • k1 curvature is most important for the prediction, especially in highly deformed regions. • For less deformed regions, P-Impedance holds vital information for estimating fractures. • P-Impedance can replace Young's modulus as an indicator of rock brittleness.
Stochastic seismic inversion and Bayesian facies classification applied to porosity modeling and igneous rock identification Fábio Júnior Damasceno Fernandes, Leonardo Teixeira, Antonio Fernando Menezes Freire, Wagner Moreira Lupinacci Petroleum Science, 2024 We apply stochastic seismic inversion and Bayesian facies classification for porosity modeling and igneous rock identification in the presalt interval of the Santos Basin. This integration of seismic and well-derived information enhances reservoir characterization. Stochastic inversion and Bayesian classification are powerful tools because they permit addressing the uncertainties in the model. We used the ES-MDA algorithm to achieve the realizations equivalent to the percentiles P10, P50, and P90 of acoustic impedance, a novel method for acoustic inversion in presalt. The facies were divided into five: reservoir 1, reservoir 2, tight carbonates, clayey rocks, and igneous rocks. To deal with the overlaps in acoustic impedance values of facies, we included geological information using a priori probability, indicating that structural highs are reservoir-dominated. To illustrate our approach, we conducted porosity modeling using facies-related rock-physics models for rock-physics inversion in an area with a well drilled in a coquina bank and evaluated the thickness and extension of an igneous intrusion near the carbonate-salt interface. The modeled porosity and the classified seismic facies are in good agreement with the ones observed in the wells. Notably, the coquinas bank presents an improvement in the porosity towards the top. The a priori probability model was crucial for limiting the clayey rocks to the structural lows. In Well B, the hit rate of the igneous rock in the three scenarios is higher than 60%, showing an excellent thickness-prediction capability.
PETROPHYSICAL EVALUATION OF ARKOSES RESERVOIRS BASED ON WELL LOGS AND PLUG SAMPLES: A CASE STUDY FROM ALAGAMAR FORMATION, SOUTHEASTERN PORTION OF ONSHORE POTIGUAR BASIN, BRAZIL Victor Ferreira, Antonio Fernando Menezes Freire, Wagner Moreira Lupinacci Revista Brasileira De Geofisica, 2024 The Potiguar Basin is a sedimentary basin located in northeastern Brazil. It covers about 48,000 km² and extends from onshore to offshore. The onshore basin is thought to have formed during the Late Cretaceous, as a result of the opening of the Equatorial South Atlantic Ocean, filled with a thick sequence of sedimentary rocks, including sandstones, shales, and limestones, which were deposited in a variety of processes, including marine, deltaic, and fluvial. The study area is in the southern portion of the basin and the reservoir is composed of arkose sandstones deposited by alluvial fan and fluvial systems of the Upanema Member of the Alagamar Formation, which belongs to the post-rift phase of the Potiguar Basin. Recently, new drilling campaigns revealed a reservoir heterogeneity in these deposits, which requested a new petrophysical approach. Using conventional well logs and petrophysical laboratory analysis of plug samples, this study evaluated the best way to calculate the effective porosity, and shale volume and to understand the stratigraphic controls in the distribution of these properties. Three reservoir zones were mapped: the basal one, Zone 3, has disconnected sand bodies, low porosity, and high shale content; Zone 2 has better petrophysical properties, lateral distribution, and connectivity between the fans and Zone 1 is the better reservoir zone with larger sand bodies, higher porosity values, and well-connected fans.
A multi-proxy approach for paleoenvironmental insights and operational improvements: A study case in Campos Basin, Brazil 85th Eage Annual Conference and Exhibition 2024, 2024
Controls of fracturing on porosity in pre-salt carbonate reservoirs Wagner Moreira Lupinacci, Tuany Younis Abdul Fatah, Maria Cordeiro do Carmo, Antonio Fernando Menezes Freire, Luiz Antonio Pierantoni Gamboa Energy Geoscience, 2023 This work aims to improve the understanding of how fracture zones affect carbonate reservoir properties based on observations of a pre-salt well located in the Santos Basin, Brazil. The identification of fracture zones allowed for the observation of a relationship between the occurrence of rock fractures and the silicification, as the latter plays an important role in determining porosity (higher silica content may increase brittleness of the rocks therefore increasing the likelihood of creating fractures zones and fractures may be filled up reducing the total porosity). To support the proposed observation, an integrated study was conducted using borehole imaging, spectroscopy logs, and sidewall core samples. The porosities were defined using nuclear magnetic resonance log analysis, alongside sidewall core samples, and thin sections. The integration of rock samples and well data with seismic analysis was performed to analyze the presence of a regional fault system that could explain high fracture densities as well as observed silica content characteristics. The results show how different types of cement filling up the formation pores affect fracture densities and total porosity. Furthermore, it was possible to infer that the amount of silica content observed in well logs and thin sections relates to hydrothermal fluids reaching out the reservoir through regional fault systems detected in the seismic section. Therefore, this paper supports the comprehension of how diagenetic processes can significantly affect the properties of pre-salt reservoirs.
The importance of a priori models in the Bayesian facies classification in carbonate reservoirs 84th Eage Annual Conference and Exhibition, 2023
Discovery of a chemosynthesis-based community in the western South Atlantic Ocean Adriana Giongo, Taiana Haag, Taiz L. Lopes Simão, Renata Medina-Silva, Laura R.P. Utz, Maurício R. Bogo, Sandro L. Bonatto, Priscilla M. Zamberlan, Adolpho H. Augustin, Rogério V. Lourega, Luiz F. Rodrigues, Gesiane F. Sbrissa, Renato O. Kowsmann, Antonio F.M. Freire, Dennis J. Miller, Adriano R. Viana, João M.M. Ketzer, Eduardo Eizirik Deep Sea Research Part I Oceanographic Research Papers, 2016
Natural gas hydrates in the Rio Grande Cone (Brazil): A new province in the western South Atlantic Dennis J. Miller, João Marcelo Ketzer, Adriano R. Viana, Renato O. Kowsmann, Antonio Fernando M. Freire, Sergio G. Oreiro, Adolpho H. Augustin, Rogerio V. Lourega, Luiz F. Rodrigues, Roberto Heemann, Adriane G. Preissler, Claudia X. Machado, Gesiane F. Sbrissa Marine and Petroleum Geology, 2015
Structural-stratigraphic control in the distribution of gas hydrate and free-gas at the umitaka anticline, Joetsu Basin, eastern margin of the Japan Sea Boletim De Geociencias Da Petrobras, 2012