Noncontact Atomic Force Microscopy - Yale School of Engineering ...
Noncontact Atomic Force Microscopy - Yale School of Engineering ...
Noncontact Atomic Force Microscopy - Yale School of Engineering ...
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
P.I-26<br />
Deciphering Nanoscale Interactions: Artificial Neural Networks and<br />
Scanning Probe <strong>Microscopy</strong><br />
Maxim Nikiforov, Stephen Jesse, Oleg Ovchinnikov, and Sergei V. Kalinin<br />
Oak Ridge National Laboratory, Oak Ridge, TN 37831<br />
Scanning Probe <strong>Microscopy</strong> techniques provide a wealth <strong>of</strong> information on<br />
nanoscale interactions. The rapid emergence <strong>of</strong> spectroscopic imaging techniques in<br />
which the response to local force, bias, or temperature is measured at each spatial<br />
location necessitates the development <strong>of</strong> data interpretation and visualization techniques<br />
for 3- or higher dimensional data sets.<br />
In this presentation, we summarize recent advances in the application <strong>of</strong> neural<br />
network based artificial intelligence methods to scanning probe microscopy. The<br />
examples will include biological identification based on the dynamics <strong>of</strong> the<br />
electromechanical response, direct mapping <strong>of</strong> dynamic disorder in ferroelectric relaxors,<br />
and reconstruction <strong>of</strong> random bond-random field Ising model parameters in ferroelectric<br />
capacitors. The future prospects for smart, multispectral SPMs are discussed.<br />
Research was supported by the U.S. Department <strong>of</strong> Energy Office <strong>of</strong> Basic<br />
Energy Sciences Division <strong>of</strong> Scientific User Facilities and was performed at Oak Ridge<br />
National Laboratory which is operated by UT-Battelle, LLC.<br />
Figure 1: Results <strong>of</strong> neural network identification <strong>of</strong> bacteria (M. Lysodeikticus (red), P.<br />
Fluorescens (green)) are overlaid on the topographic image. Training area for neural network is<br />
outlined by black rectangle (in collaboration with A. Vertegel and V. Reukov, Clemson<br />
University).<br />
117