SurfaceScience21 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
O: Fachverband Oberflächenphysik
O 109: Poster Session VIII: Poster to Mini-Symposium: Machine learning applications in surface science III
O 109.2: Poster
Donnerstag, 4. März 2021, 13:30–15:30, P
Predicting hydration layers on surfaces using deep learning — •Yashasvi S Ranawat1, Ygor M Jaques1, and Adam S Foster1,2 — 1Department of Applied Physics, Aalto Uiversity, Finland — 2WPI Nano Life Science Institute (WPI-NanoLSI), Kanazawa University, Kakuma-machi, Kanazawa 920-1192, Japan
Surface characterisation at the nano-scale of a mineral-water interface has applications in understanding many technological and natural processes dominated by the mineral-water interactions, for example biominerelisation, corrosion etc. Atomic Force Microscopy (AFM) has the potential to characterise such surfaces. The image mechanism is governed by the complex interplay of the tip with the hydration layers over the surface and hence high resolution requirements pose a challenge. A direct link between the AFM images and water density over a surface has paved the way for theoretical molecular dynamics methods to simulate the density over a given surface, and therefore the AFM image. The computationally intense theoretical approaches have helped with the surface characterisation. However the search space, given a hydration layer image, is wide and the approach is prohibitively expensive. Here we introduce deep learning methods to swiftly and reliably predict the hydration layer over a given surface. These methods are tested on the polymorphs of calcium carbonate.