Original data and codes for "Machine Learning-Enhanced Optical Monitoring for Identifying Pitting-Susceptible Zones in 316L Stainless Steel" article

This upload contains original data and supplementary data for the publication titled "Machine Learning-Enhanced Optical Monitoring for Identifying Pitting-Susceptible Zones in 316L Stainless Steel" by Aleksei Makogon, Leonardo Bertolucci Coelho, Jon Ustarroz, Philippe Decorse ,Frédéric Kanoufi ,Slava SHKIRSKIY. The preprint of the paper is available on ChemRxiv (10.26434/chemrxiv-2025-xqprl-v2) This uploads contains the following datasets: 1.6CA-10mM_NaCL.zip – Microscopy images of SS316L samples polarized at +1.6V (vs Ag/AgCl) in 10 mM NaCl solution. Acquisition rate: 15 Hz.1.6CA-30mM_NaCL.zip – Microscopy images of SS316L samples polarized at +1.6V (vs Ag/AgCl) in 30 mM NaCl solution. Acquisition rate: 15 Hz.5mM_CA1.6-w-snaps.zip – Microscopy images of SS316L samples polarized at +1.6V (vs Ag/AgCl) in 5 mM NaCl solution. Acquisition rate: 5 Hz.10mM_1.6V-w-snaps.zip – Microscopy images of SS316L samples polarized at +1.6V (vs Ag/AgCl) in 10 mM NaCl solution. Acquisition rate: 5 Hz.30mM_1.6V-w-snaps.zip – Microscopy images of SS316L samples polarized at +1.6V (vs Ag/AgCl) in 30 mM NaCl solution. Acquisition rate: 5 Hz.50mM_1.6V-w-snaps.zip – Microscopy images of SS316L samples polarized at +1.6V (vs Ag/AgCl) in 50 mM NaCl solution. Acquisition rate: 5 Hz. The file Stats_K_means_UMAP.ipynb contains implementation of Chi square test of independence The file Run_UMAP.ipynb contains python implementation of UMAP for pits detection from videos