Unsupervised Analysis of Optical Imaging Data for the Discovery of Reactivity Patterns in Metal Alloy

Abstract

Operando wide-field optical microscopy imaging yields a wealth of information about the reactivity of metal interfaces, yet the data are often unstructured and challenging to process. In this study, we harness the power of unsupervised machine learning (ML) algorithms to analyze chemical reactivity images obtained dynamically by reflectivity microscopy in combination with ex situ scanning electron microscopy to identify and cluster the chemical reactivity of particles in Al alloy. The ML analysis uncovers three distinct clusters of reactivity from unlabeled datasets. A detailed examination of representative reactivity patterns confirms the chemical communication of generated OH- fluxes within particles, as supported by statistical analysis of size distribution and finite element modelling (FEM). The ML procedures also reveal statistically significant patterns of reactivity under dynamic conditions, such as pH acidification. The results align well with a numerical model of chemical communication, underscoring the synergy between data-driven ML and physics-driven FEM approaches.

Deciphering the Interplay Between Local and Global Dynamics of Anodic Metal Oxidation

“…The central concept underpinning our data processing is that the light reflectivity (R) is proportional to both the thickness (δ) and the composition (via its refractive index n) of surface films on metal substrates. 23,29,31,36,37 This principle, rooted in the notion of light interference reflected from the metal interface and surface films (Fig. 1a), has already been substantiated for flat Fe 29 and Al-based substrates.…”

“…1a), has already been substantiated for flat Fe 29 and Al-based substrates. 23,36 It is derived from the Fresnel equations, the specifics of which can be found in another sources. 23,29,31,37 Among all phases of Fe oxides reported during Fe oxidation, we considered the most thermodynamically stable phases, Fe3O4 and Fe2O3 (Fig.…”

“…23,25,26 These parameters are central to our understanding of metal passivation and corrosion protection. When augmented with machine vision methodologies, 35,36 RM evolves into an automated, robust, and flexible approach. Its versatility and efficacy are further demonstrated in this work through the examination of corrosion in pure polycrystalline Fe metal in NaCl medium.…”