Salah Eddine ZARITA

Developed machine-learning models and data pipelines for real-time well performance prediction, validated against PROSPER surrogates achieving R²=0.986 and reducing RMSE by 50.8%, improving production surveillance and reducing engineering overhead.

Implemented data-driven workflows and EDA for reservoir performance, achieving R²=0.968 in decline curve modeling and identifying incremental production increases of 3.83×10⁷ SCM.

Collaborated with application and remote engineers on real-time data workflows and LWD services, developed an application to automate tabular data extraction and gained familiarity with WellArchitect and JewelSuite.

Built a reservoir engineering toolkit and dashboard web application for well log processing and 3D visualization, produced documentation and a GUI to improve academic usability.

Activities and societies: End-of-studies project: Machine Learning For Real Time Well Performance Modeling; Student Chapter activities with Association Ourhoud and SPE; internships with Sonatrach, Baker Hughes, and JV projects.

Pursuing petroleum engineering studies at the Faculty of Hydrocarbons and Chemistry with coursework and projects in reservoir and petroleum engineering, data-driven production analysis, and upstream operations.

Activities and societies: Projects and internships in production and reservoir engineering, participation in student society SMSD, and hands-on field observations and interventions.

Completed Licence (Bachelor) level studies in Petroleum Engineering at the Faculty of Hydrocarbons and Chemistry with emphasis on subsurface and reservoir engineering and production data analysis.