The Coqueiros Formation, a strategic stratigraphic unit within the Lagoa Feia Group (LFG) in the Campos Basin offshore Brazil, is known for its lacustrine carbonate deposits, which include both organic-rich shales and economically important “coquina” reservoirs. While coquina facies are widely recognized as reservoirs, the source-rock potential of the intercalated shales remains relatively underexplored. This study aims to characterize the mineralogy and thermal maturity of the Coqueiros Formation to assess its potential as a source rock, using a multi-technique approach integrating X-ray Diffraction (XRD), Scanning Electron Microscopy (SEM), and Raman spectroscopy analyses of shale samples from two wells: 3-BP-11-RJS and 6-DEV-18P-RJS. XRD analyses revealed a heterogeneous mineralogy dominated by carbonates (calcite and dolomite) and quartz, with significant contributions from clay minerals and trace minerals such as pyrite and barite. SEM imaging revealed a heterogeneous fabric with grain size, morphology, and porosity variations, reflecting a dynamic lacustrine depositional setting influenced by storm events and fluctuations in terrigenous input. The presence of authigenic minerals, as reported in other studies, such as saddle dolomite, mega-quartz, and various sulfides, provides evidence for hydrothermal alteration, likely related to Late Cretaceous magmatic activity in the Campos Basin. Raman spectroscopy yielded equivalent vitrinite reflectance (Ro%) values consistently exceeding 1.00, ranging from 1.03 to 1.40, indicating that the organic matter in the Coqueiros Formation shales has attained a high thermal maturity level, surpassing the oil window and reaching the condensate wet gas zone. The mineralogical and equivalent maturation data presented herein provide a valuable foundation for future studies, highlighting the complexity and heterogeneity of the Coqueiros Formation and its potential significance as a source rock within the Campos Basin petroleum system.

The objective of this work is to propose a simulation strategy for production planning that is compatible with the dynamism of natural gas processing, especially under an open-market arrangement, in which several scheduling simulations must be performed within short time horizons. In such contexts, traditional first-principles-based approaches, although accurate, require prohibitive computational times, motivating the need for an alternative simulation strategy. This work thus proposes a data-driven model built with the aid of machine learning and applied in a case study with historical data from the largest gas processing site in Brazil: Cabiúnas Petrobras asset. Main plant flowrates were selected: 18 targets and 44 input candidates—1282 observations from three and a half years of operation. Principal Component Analysis was used for order reduction, keeping the 22 main principal components. A forward neural network (2 hidden layers and 225 neurons per layer) was built from training/test sets randomly selected and optimized hyperparameters—learning rate (0.001533) and batch size (8). Training converged in roughly 200 epochs (Adam optimizer), with early stop triggered by the validation set. A mean absolute error of 0.0017 (test set) and R² = 0.72 were found, a promising result considering plant complexity and data simplicity. Results showed a particularly good fit for lighter products (sales gas and natural gas liquid), also indicating an opportunity for further work by including inputs related to liquid fractionation.

The objective of this work is to propose a simulation strategy for production planning that is compatible with the dynamism of natural gas processing, especially under open-market arrangement, in which several scheduling simulations must be performed within short time horizons. In such contexts, traditional first-principles-based ap-proaches, although accurate, require prohibitive computational times, motivating the need for an alternative simulation strategy. This work thus proposes a data-driven model built with the aid of machine learning and applied in a case study with historical data from the largest gas processing site in Brazil: Cabiúnas Petrobras asset. Main plant flowrates were selected: 18 targets and 44 input candidates – 1282 observations from three and a half years of operation. Principal Component Analysis was used for order reduction, keeping the 22 main principal components. A forward neural network (2 hidden layers and 225 neurons per layer) was built from training/test sets randomly selected and optimized hyperparameters – learning rate (0.001533) and batch size (8). Training converged in roughly 200 epochs (Adam optimizer), with early stop triggered by validation set. A mean absolute error of 0.0017 (test set) and R2=0.72 were found, a promising result considering plant complexity and data simplicity. Results showed particularly good fit for lighter products (sales gas, natural gas liquid), also indicating an opportunity for further work by including inputs related to liquid fractionation.