Nano-scale Defect Analysis Through K-Means Clustering of CuInSe2 Solar Cells with Ag and K Incorporation

Tara Nietzold, Michael Stuckelberger, Trumann Walker, Nicholas Valdes, Bradley M. West, Barry Lai, William N. Shafarman, Mariana I. Bertoni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Nano-X-ray fluorescence microscopy is used to correlate elemental inhomogeneity to device performance measured through X-ray beam induced current (XBIC). Unsupervised machine learning techniques can be useful in the processing and correlation of XRF/XBIC data. A case study using CuInSe2 solar cells treated with Ag-alloying and KF-post- deposition treatment (PDT) is presented. The implementation of K-means clustering is studied for its ability to identify statistically meaningful results from XRF/XBIC data. The procedure described may be applied to datasets of a similar nature.

Original languageEnglish (US)
Title of host publication2019 IEEE 46th Photovoltaic Specialists Conference, PVSC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2164-2166
Number of pages3
ISBN (Electronic)9781728104942
DOIs
StatePublished - Jun 2019
Event46th IEEE Photovoltaic Specialists Conference, PVSC 2019 - Chicago, United States
Duration: Jun 16 2019Jun 21 2019

Publication series

NameConference Record of the IEEE Photovoltaic Specialists Conference
ISSN (Print)0160-8371

Conference

Conference46th IEEE Photovoltaic Specialists Conference, PVSC 2019
Country/TerritoryUnited States
CityChicago
Period6/16/196/21/19

Keywords

  • CIS
  • K-means
  • X-ray beam induced current
  • X-ray fluorescence
  • clustering
  • machine learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Nano-scale Defect Analysis Through K-Means Clustering of CuInSe2 Solar Cells with Ag and K Incorporation'. Together they form a unique fingerprint.

Cite this