Machine Learning-Enhanced Optimization of Nanoscale Phytochemical Synergistic Films for High-Temperature Industrial Corrosion Protection: A Review

Department of Chemical Sciences, Ajayi Crowther University, Oyo, Nigeria

^*Corresponding author: Emmanuel Oladeji Oyetola, Department of Chemical Sciences, Ajayi Crowther University, Oyo, Nigeria, E-mail: [email protected]

Received Date: February 07, 2026

Publication Date: April 10, 2026

Citation: Oyetola EO, et al. (2026). Machine Learning-Enhanced Optimization of Nanoscale Phytochemical Synergistic Films for High-Temperature Industrial Corrosion Protection: A Review. Nanoparticle. 7(1):21.

Copyright: Oyetola EO, et al. © (2026).

ABSTRACT

Background: Conventional industrial corrosion inhibitors often rely on toxic synthetic compounds that lead to severe ecological degradation. This study investigates the shift toward sustainable alternatives, specifically focusing on the mechanism by which plant-derived phytochemicals assemble into protective nanostructured films on metal surfaces.

Methods: Integrated "nanoinformatics" approach was employed, utilizing ensemble machine learning (ML) architectures—specifically Random Forest (RF) and XGBoost to navigate the complex chemical space of multi-component plant extracts. These models were trained to optimize the ratios of active secondary metabolites. Computational predictions were validated through thermodynamic modeling and high-resolution surface characterization to quantify the stability of the adsorbed layers.

Results: The study identifies a powerful synergistic effect in blended formulations. Specifically, a rosemary-carrot extract complex achieved a peak inhibition efficiency of 99.6%, maintaining structural integrity even under accelerated thermal stress. The ML models demonstrated exceptional reliability, yielding a Coefficient of Determination (R²) of 0.99 and a Root Mean Square Error (RMSE) below 0.05, effectively predicting the transition from sporadic adsorption to dense, coherent film formation at the nanoscale.

Conclusion: Merging green chemistry with predictive ML modeling removes the "trial-and-error" bottleneck in bio-based inhibitor design. This framework provides a scalable, high-performance pathway for protecting industrial infrastructure without the environmental footprint of traditional chemical treatments.

Keywords: Corrosion Inhibition, Green Inhibitors, Plant Extracts, Phytochemicals, Synergistic Effects, Machine Learning, Adsorption Thermodynamics

ABBREVIATIONS

Ag-NP: Silver Nanoparticles

AFM: Atomic Force Microscopy

DLS: Dynamic Light Scattering

EIS: Electrochemical Impedance Spectroscopy

FTIR: Fourier-Transform Infrared Spectroscopy

GC–MS: Gas Chromatography–Mass Spectrometry

ML: Machine Learning

SAMs: Self-Assembled Monolayers

SEM: Scanning Electron Microscopy

XRD: X-Ray Diffraction