Understanding Nanoscale Electromechanical Energy Conversion with Machine Learning

Understanding Nanoscale Electromechanical Energy Conversion with Machine Learning

Scientific Achievement
The experiments utilized band-excitation piezoresponse spectroscopy, a tool developed at the CNMS, to unravel the role of domain geometry on ferroelectric and ferroelastic switching. A machine learning method enables determination of the switching pathway, providing insights into electromechanical energy conversion in ferroelectrics. (hi-res image)

A machine learning method enables greater understanding mechanisms of ferroelectric switching under an atomic force microscope tip.

Significance and Impact

Machine learning in conjunction with scanning probe techniques enable leads to an understanding of how electromechanical energy conversion proceeds.

Research Details

– Ferroelectrics are widely used in sensors, actuators and transducers, but precise details on the mechanisms of their transduction are often lacking.

– Here, an approach based on scanning probe microscopy is combined with machine learning to understand these energy conversion processes on the nanoscale.

– This leads to a understanding of the impact of domain geometry on the pathways of ferroelectric/elastic switching.


J. C. Agar, Y. Cao, B. Naul, S. Pandya, S. van der Walt, A. I. Luo, J. T. Maher, N. Balke, S. Jesse, S. V. Kalinin, R. K. Vasudevan. and L. W. Martin, "Machine detection of enhanced electromechanical energy conversion in PbZr0.2Ti0.8O3 thin films," Advanced Materials (2018).   DOI: 10.1002/adma.201800701

CNMS Researchers