X
Go

Electrical Test Prediction Using Hybrid Metrology and Machine Learning

Authored by: Mary Breton a, Robin Chao a, Gangadhara Raja Muthinti a, Abraham A. de la Peña a, Jacques Simon a, Aron J. Cepler b, Matthew Sendelbach b, John Gaudiello a, Hao Tang a, Susan Emans b, Michael Shifrin c, Yoav Etzioni c, Ronen Urenski c, Wei Ti Lee d | SPIE 2017, February 1, 2017

ABSTRACT
Electrical test measurement in the back-end of line (BEOL) is crucial for wafer and die sorting as well as comparing
intended process splits. Any in-line, nondestructive technique in the process flow to accurately predict these
measurements can significantly improve mean-time-to-detect (MTTD) of defects and improve cycle times for yield and
process learning. Measuring after BEOL metallization is commonly done for process control and learning, particularly
with scatterometry (also called OCD (Optical Critical Dimension)), which can solve for multiple profile parameters such
as metal line height or sidewall angle and does so within patterned regions. This gives scatterometry an advantage over
inline microscopy-based techniques, which provide top-down information, since such techniques can be insensitive to
sidewall variations hidden under the metal fill of the trench. But when faced with correlation to electrical test
measurements that are specific to the BEOL processing, both techniques face the additional challenge of sampling.
Microscopy-based techniques are sampling-limited by their small probe size, while scatterometry is traditionally limited
(for microprocessors) to scribe targets that mimic device ground rules but are not necessarily designed to be electrically
testable.
A solution to this sampling challenge lies in a fast reference-based machine learning capability that allows for OCD
measurement directly of the electrically-testable structures, even when they are not OCD-compatible. By incorporating
such direct OCD measurements, correlation to, and therefore prediction of, resistance of BEOL electrical test structures
is significantly improved. Improvements in prediction capability for multiple types of in-die electrically-testable device
structures is demonstrated. To further improve the quality of the prediction of the electrical resistance measurements,
hybrid metrology using the OCD measurements as well as X-ray metrology (XRF) is used. Hybrid metrology is the
practice of combining information from multiple sources in order to enable or improve the measurement of one or more
critical parameters. Here, the XRF measurements are used to detect subtle changes in barrier layer composition and
thickness that can have second-order effects on the electrical resistance of the test structures. By accounting for such
effects with the aid of the X-ray-based measurements, further improvement in the OCD correlation to electrical test
measurements is achieved. Using both types of solution—incorporation of fast reference-based machine learning on non-
OCD-compatible test structures, and hybrid metrology combining OCD with XRF technology—improvement in BEOL
cycle time learning could be accomplished through improved prediction capability.
Keywords: OCD, scatterometry, machine learning, electrical test, prediction, XRF, hybrid metrology, resistance