PhD Proposal by Kerisha Nicole Williams

Event Details
  • Date/Time:
    • Friday October 8, 2021
      11:00 am - 1:00 pm
  • Location: Atlanta, GA; REMOTE
  • Phone:
  • URL: Bluejeans
  • Email:
  • Fee(s):
    N/A
  • Extras:
Contact
No contact information submitted.
Summaries

Summary Sentence: Machine Learning for Piezoresponse Force Microscopy

Full Summary: No summary paragraph submitted.

THE SCHOOL OF MATERIALS SCIENCE AND ENGINEERING 

  

GEORGIA INSTITUTE OF TECHNOLOGY   

 

Under the provisions of the regulations for the degree
 

DOCTOR OF PHILOSOPHY
 

on Friday, October 8, 2021

11:00 AM

via

 

BlueJeans Video Conferencing

https://bluejeans.com/526281391/5916

 

will be held the

 

DISSERTATION PROPOSAL DEFENSE

for

 

Kerisha Nicole Williams

 

"Machine Learning for Piezoresponse Force Microscopy"

 

Committee Members:

 

Prof. Nazanin Bassiri-Gharb, Advisor, MSE/ME

Prof. Lauren Garten, MSE

Prof. Asif Kahn, ECE

Prof. Yao Xie, ISYE

Prof. Eric Vogel, MSE

 

Abstract:

 

Piezoresponse force microscopy (PFM) probes the nanoscale electromechanical response of materials through measurement of the sample surface displacement upon application of electric field through a conductive cantilever tip. However, in addition to piezoelectric coupling, non-piezoelectric phenomena such as electrostatic forces arising from charge injection and electro-chemo-mechanical force arising from ionic and defect motion can also contribute to the observed response. Hence, analysis of the observed response is hindered in physical interpretation. Moreover, both piezoelectric and non-piezoelectric contributors are modulated by changes to the materials surface and/or the local environment, further limiting physical insights into the underlying materials response. While such limitations might be marginal in epitaxial ferroelectric ultra-thin films samples often used in PFM studies, no material is a priori impervious to them. Machine Learning techniques have been increasingly used in the analysis of PFM data to overcome some of these interpretation challenges. Specifically, dimensional stacking (concatenation of multiple datasets) can be used to first encode physical constraints into multi-dimensional datasets before separation of co-contributing behaviors via (unsupervised) dimensional reduction techniques. This work proposes to use PFM combined with machine learning to separate and quantify the chemical and physical phenomena contributing to nanoscale electromechanical behavior of ferroelectric perovskites observed, as characterized by resonant PFM.

Additional Information

In Campus Calendar
No
Groups

Graduate Studies

Invited Audience
Faculty/Staff, Public, Undergraduate students
Categories
Other/Miscellaneous
Keywords
Phd proposal
Status
  • Created By: Tatianna Richardson
  • Workflow Status: Published
  • Created On: Sep 28, 2021 - 12:00pm
  • Last Updated: Sep 28, 2021 - 12:00pm