Our Team

Erlon Santos is a Ph.D. Petroleum Engineer specializing in multiphase flow, flow assurance, and machine learning for the oil and gas industry. His doctoral research at the University of Tulsa's TUFFP consortium combines high-pressure experimental work with predictive modeling to characterize liquid entrainment in gas-liquid pipe flow, a key driver of pressure drop and flow assurance risk in production systems. His AI/ML expertise spans the full model development lifecycle: exploratory data analysis, data explainability (including SHAP analysis), rigorous feature selection, predictive modeling across traditional algorithms and symbolic regression, hyperparameter optimization, and model evaluation focused on physical consistency and extrapolation robustness. He has used this framework to build interpretable, closed-form models that outperform black-box approaches when applied beyond their training domain.
Combining deep domain expertise in multiphase flow physics with rigorous, reproducible machine learning workflows, Erlon brings a rare hybrid skill set suited to roles spanning flow assurance, production optimization, computational engineering, and applied data science in the energy sector.