Jean Carlos Dias DE Araujo

Jean Carlos Dias DE Araujo

Auto-generated profile, based on publicly available information

Jean Carlos Dias DE Araujo

Petróleo Brasileiro S.A. (PETROBRAS), Rio de Janeiro, Brazil

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 April 2026 in Scientific Data
Verified
Journal Article
Open access
PDF file
RVRicardo Emanuel Vaz Vargas
Ricardo Emanuel Vaz Vargas
AMAfrânio Melo
Afrânio Melo
CLClaudio Lima
Claudio Lima
JAJean Carlos Dias de Araújo
Jean Carlos Dias de Araújo
MFMateus de Araujo Fernandes
Mateus de Araujo Fernandes
JCJaime Andrés Lozano Cadena
Jaime Andrés Lozano Cadena
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.

4 September 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
JAJean Carlos Dias DE Araujo
Jean Carlos Dias DE Araujo
CMCelso Munaro
Celso Munaro
PCPatrick Marques Ciarelli
Patrick Marques Ciarelli
Well production monitoring increasingly relies on data-driven methods, yet anomaly detection during transients remains challenging. This work presents a case study on a real Petrobras well, comparing black-box and grey-box nonlinear dynamic identification approaches to develop a virtual sensor for seabed flowing pressure and event detection. Polynomial nonlinear autoregressive with exogenous inputs (NARX) and Hammerstein models were evaluated under both data-driven and physics-informed configurations, the latter incorporating steady-state priors from a calibrated first-principles multiphase flow simulator. By leveraging existing simulation workflows, the proposed framework substantially reduces the transient data required for model training. Results show that simulator-derived information improves soft-sensor accuracy and enables clear separation between normal and abnormal operation, even under strong transients, while preserving accurate multi-step-ahead prediction during normal conditions. The approach provides an effective solution for anomaly detection in offshore wells with limited dynamic data.