In the oil industry, undesirable events in oil wells can cause economic losses, environmental accidents, and human casualties. In 2019, recognizing the importance and the lack of public datasets related to undesirable events in oil wells, Petrobras developed and publicly released the first version of the 3W Dataset, which is essentially a set of Multivariate Time Series labeled by experts. Since then, the 3W Dataset has been developed collaboratively and has become a foundational reference for numerous works in the field. This data article describes the current publicly available version of the 3W Dataset, which contains additional instances, more variables, and a new label. Furthermore, a new data structure has been developed to make data access more robust and efficient. The detailed description we provide encourages and supports the 3W community and new 3W users to improve previous published results and to develop new robust methodologies, digital products and services capable of detecting undesirable events in oil wells with enough anticipation to enable corrective or mitigating actions.

Monitoring bottom-hole pressure (BHP) is critical for reservoir management and flow assurance, especially in offshore fields where challenging conditions and production losses are more impactful. However, reliability issues and high installation costs of Permanent Downhole Gauges (PDGs) often limit access to this vital data. Soft sensors offer a cost-effective and reliable alternative, serving as backups or replacements for physical sensors. This study proposes a novel data-driven methodology for estimating flowing BHP using wellhead and topside measurements from plant monitoring systems. The framework employs ensemble methods combined with clustering techniques to partition datasets, enabling tailored supervised training for diverse production conditions. Aggregating results from sub-models enhances performance, even with simpler machine learning algorithms. We evaluated Linear Regression, Neural Networks, and Gradient Boosting (XGBoost and LightGBM) as base models. A case study of a Brazilian Pre-Salt offshore oilfield, using data from 60 wells across nine platforms, demonstrated the methodology’s effectiveness. Error metrics remained consistently below 2% across varying production conditions and reservoir lifecycle stages, confirming its reliability. This solution provides a practical, economical alternative for studies and monitoring in wells lacking PDG data, improving operational efficiency and supporting reservoir management decisions.

Reliable monitoring of bottom-hole pressure (BHP) in gas injection wells is essential for reservoir management, operational safety, and the success of Enhanced Oil Recovery (EOR) and Carbon Capture, Utilization, and Storage (CCUS) projects. Particularly in offshore oilfields where the carbon dioxide content in the production is relevant, its reinjection mixed with hydrocarbon gases presents unique difficulties arising from the complex physical behavior, since flow often occurs in supercritical state. Additionally, measurements from permanent downhole gauges (PDGs) may be absent. Traditional mechanistic models and purely data-driven machine learning (ML) approaches each have limitations in handling the nonlinearities and uncertainties inherent in these systems. In this work, we address these limitations by developing a Physics-Guided Neural Network (PGNN) that combines first-principles modeling with supervised learning through a hybrid loss formulation. The methodology is validated using a comprehensive dataset from an offshore oilfield in the Brazilian Pre-salt, encompassing multiple injection cycles and varying gas compositions. Results demonstrate that the hybrid approach achieves robust BHP estimation, with error metrics around 1%, outperforming both conventional physical models and standard neural networks, especially when dealing with limited or noisy datasets. The proposed virtual sensor solution enables reliable BHP monitoring in injector wells, minimizing operational expenditures and supporting safe, efficient, and sustainable reservoir management and CO₂ storage.

Monitoring bottom-hole pressure (BHP) is critical for reservoir management and flow assurance, especially in offshore fields where challenging conditions and production losses are more impactful. However, reliability issues and high installation costs of Permanent Downhole Gauges (PDGs) often limit access to this vital data. Soft sensors offer a cost-effective and reliable alternative, serving as backups or replacements for physical sensors. This study proposes a novel data-driven methodology for estimating flowing BHP using wellhead and topside measurements from plant monitoring systems. The framework employs ensemble methods combined with clustering techniques to partition datasets, enabling tailored supervised training for diverse production conditions. Aggregating results from sub-models enhances performance, even with simpler machine learning algorithms. We evaluated Linear Regression, Neural Networks, and Gradient Boosting (XGBoost and LightGBM) as base models. A case study of a Brazilian Pre-Salt offshore oilfield, using data from 60 wells across nine platforms, demonstrated the methodology’s effectiveness. Error metrics remained consistently below 2% across varying production conditions and reservoir lifecycle stages, confirming its reliability. This solution provides a practical, economical alternative for studies and monitoring in wells lacking PDG data, improving operational efficiency and supporting reservoir management decisions.

Monitoring bottom-hole variables in petroleum wells is essential for production optimization, safety, and emissions reduction. Permanent Downhole Gauges (PDGs) provide real-time pressure data but face reliability and cost issues. We propose a machine learning-based soft sensor to estimate flowing Bottom-Hole Pressure (BHP) using wellhead and topside measurements. A Long Short-Term Memory (LSTM) model is introduced and compared with Multi-Layer Perceptron (MLP) and Ridge Regression. We also pioneer Transfer Learning for adapting models across operational environments. Tested on real offshore datasets from Brazil's Pre-salt basin, the methodology achieved Mean Absolute Percentage Error (MAPE) consistently below 2\%, outperforming benchmarks. This work offers a cost-effective, accurate alternative to physical sensors, with broad applicability across diverse reservoir and flow conditions.