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; charge-transfer resistance (Rct) and corrosion current density (icorr) serve as complementary proxies for corrosion severity, expressed as log₁₀(Rct) from electrochemical impedance spectroscopy (EIS) and log₁₀(icorr) from potentiodynamic polarization. However, physically interpretable predictive models for MIC remain limited. Here, we show that machine learning regressors can predict both log₁₀(Rct) and log₁₀(icorr) 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 crossvalidation, 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 capacitance admittance as the dominant predictor of corrosion severity in the EIS model, consistent with its role as a reporter of biofilm-induced interfacial disorder, while primer-derived organism-level descriptors contributed modest but interpretable signals consistent with known differences in metabolic versatility between the two organisms. This work establishes a reproducible and interpretable baseline for quantitative MIC prediction and, to our knowledge, represents one of the first applications of SHAP analysis to EIS-derived features in MIC while demonstrating the value of integrating organism-level descriptors with electrochemical features for corrosion modeling.
- Predicting microbiologically influenced corrosion severity from electrochemical impedance spectroscopy using interpretable machine learning
- Raksha Mohan
- 0009-0000-0142-4452
- Maricris Lodriguito Mayes (Advisor) - University of Massachusetts Dartmouth, Department of Chemistry and BiochemistryFiras Khatib (Committee Member) - University of Massachusetts Dartmouth, Department of Computer and Information ScienceDonghui Yan (Committee Member) - University of Massachusetts Dartmouth, Department of Mathematics
- xvii,146 pages
- color illustrations
- List of figures -- List of tables -- Abbreviations -- Chapter 1. Introduction -- Background and motivation -- Problem statement -- Research objectives and scope -- Overview of the thesis -- Chapter 2. Background and theoretical framework -- Fundamentals of corrosion -- Microbiologically influenced corrosion (MIC) -- Electrochemical characterization techniques -- Data-driven approaches in corrosion science -- Chapter 3. Data mining and computational methodology -- Data collection strategy and experimental context -- Microbial strains and environmental conditions -- EIS dataset construction and impedance analysis -- Polarization dataset construction and analysis -- Genomic and microbial descriptor dataset -- Integrated dataset summary and electrochemical correlations -- Chapter 4. Data-driven prediction and interpretability -- Feature engineering and selection -- Machine learning model development -- SHAP explainability framework -- Model performance -- Feature importance and SHAP analysis -- Discussion -- Chapter 5. Conclusions and prospects -- Summary of key findings -- Original contributions -- Recommendations for future research -- Concluding remarks -- References.
- Includes bibliographical references (pages 118-123).
- University of Massachusetts Dartmouth
- Master of Science (MS)
- Data Science
- Department of Computer and Information Science
- English
- Thesis
- Copyright 2026 Raksha Mohan
- https://doi.org/10.62791/20612
- 9914540278001301