Mechanistic CO2 corrosion model optimization supported by machine learning (C2026-00164)
Wednesday, March 18, 2026
10:30 AM - 11:00 AM Central
Location: 362 DE
Earn .5 PDH
Interested in reading the entire paper? Click on the "Paper" button below to read on the AMPP Knowledge Hub!
*Please note, if your registration came with access to the conference proceedings don't forget to login to your AMPP Knowledge Hub account to access the paper for free. If you login and don't have access to the paper, you can purchase the individual paper or purchase the entire conference proceedings on your Knowledge Hub account.
Jonas Sa, Richard Woollam, Michael Jones, Richard Barker, Brahim Aissa, Kamal Mroue
In this work, we investigated the optimization of a mechanistic model of aqueous carbon dioxide (CO2) corrosion. Parametric studies were conducted over an extensive range of bulk pH, fluid velocity, temperature, pipe diameter, CO2 partial pressure and Reynolds number. The output responses were fed into an established machine learning model to identify outliers in the dataset. Considerable discrepancies were observed between the results generated by both models, particularly in the low fluid velocity regime and lower Reynolds number range. To address this, we revised the mechanistic model, updating its mesh structure and optimizing solver parameters to enhance numerical convergence and solution stability. The output from the revised mechanistic model and the machine learning model were subsequently compared, the improvement in model convergence was detailed and the source of improvement was discussed.
