Data Science MS Thesis Defense by Raksha Mohan
Title: "Predicting Microbiologically Influenced Corrosion Severity from Electrochemical Impedance Spectroscopy Using Interpretable Machine Learning"
by Raksha Mohan
Thesis Advisor: Maricris Mayes, Associate Professor, Chemistry & Biochemistry
Thesis Committee:
Firas Khatib, Associate Professor, Computer & Information Science
Donghui Yan, Associate Professor, Mathematics
Abstract:
Microbiologically influenced corrosion (MIC) accounts for an estimated 20-30% of global corrosion losses, yet reliable quantitative prediction of MIC severity remains unsolved. Electrochemical measurements combined with interpretable machine learning provide a promising framework for addressing this challenge. MIC depends on coupled microbial, biofilm, and interfacial electrochemical processes, and charge-transfer resistance (Rct) is a useful proxy for corrosion severity, as expressed in log₁₀(Rct) from electrochemical impedance spectroscopy (EIS). However, physically interpretable predictive models for MIC remain limited. Here, we show that machine learning regressors can predict log₁₀(Rct) in MIC systems involving Pseudomonas and Vibrio across varying environmental conditions.
A dataset of 116 EIS and 83 potentiodynamic polarization observations was compiled from ten peer-reviewed sources. Random forest and Gradient Boosting Machine (GBM) regressors were compared using stratified five-fold cross-validation, and Shapley additive explanations (SHAP) were used to interpret model behavior in physically meaningful terms. GBM outperformed Random Forest, achieving a higher cross-validated R². SHAP analysis identified double-layer CPE admittance as the dominant predictor of corrosion severity, consistent with its role as a reporter of biofilm-induced interfacial disorder, while genomic species descriptors contributed modest but interpretable signals consistent with known difference in metabolic versatility between the two organisms.
This work establishes a reproducible and interpretable baseline for quantitative MIC prediction and, to our knowledge, provides the first application of SHAP analysis to EIS-derived features in MIC while demonstrating the value of integrating genomic descriptors with electrochemical features for corrosion modeling.
Zoom Meeting ID: 922 3504 5299
Passcode: 941562
SENG 311
: Zoom
Maricris Mayes
maricris.mayes@umassd.edu
https://umassd.zoom.us/j/92235045299?pwd=gOpd6QBNGaNhrJaTwjQXCEkGjk8iSb.1