Sun, Changhyo Sriboriboon, Panithan Han, Junghun Ko, Sang-Jin Lee, Seung-Yong Heo, Yooun Shim, Jae-Hyeok Yang, Sejung Kim, Jung-Gu Kim, Yunseok 2024-10-02T09:30:18Z 2024-10-02T09:30:18Z 2024-10-02 2024-11 0010-938X https://pubs.kist.re.kr/handle/201004/150691 A deep understanding of corrosion behavior is critical for improving steel durability and reliability. Typically, it requires significant experimental effort and extensive measurements over a long period of time. Therefore, exploring the time-dependent corrosion at an early stage to predict its progress at a later stage can effectively understand it. In this study, we quantitatively predicted later stages of local corrosion behavior using deep learning methods based on the early stage topographical information. Furthermore, we predicted and visualized the formation, growth, and accumulation of the particle-like oxides. Our proposed method can be extended to other types of corrosion-resistant electrochemical materials. English Pergamon Press Ltd. Prediction of quantitative in-situ local corrosion via deep learning Article 10.1016/j.corsci.2024.112431 1 Corrosion Science, v.240 Corrosion Science 240 N scie scopus 001310829800001 2-s2.0-85203253883 Materials Science, Multidisciplinary Metallurgy & Metallurgical Engineering Materials Science Metallurgy & Metallurgical Engineering Article DUAL-PHASE STEEL DEFORMATION DIFFRACTION ENVIRONMENT MICROSCOPY BEHAVIOR FERRITE Atomic force microscopy Corrosion Quantitative topography Deep learning Advanced high strength steel