US 12,380,367 B2
Metrology in the presence of CMOS under array (CuA) structures utilizing machine learning and physical modeling
Houssam Chouaib, San Jose, CA (US); Zhaxylyk Kudyshev, Milpitas, CA (US); Chao Chang, Milpitas, CA (US); and Derrick A. Shaughnessy, San Jose, CA (US)
Assigned to KLA Corporation, Milpitas, CA (US)
Filed by KLA Corporation, Milpitas, CA (US)
Filed on Jun. 30, 2023, as Appl. No. 18/217,290.
Prior Publication US 2025/0005435 A1, Jan. 2, 2025
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 22 Claims
OG exemplary drawing
 
1. A system, comprising:
a controller including one or more processors configured to execute program instructions causing the one or more processors to implement a measurement recipe by:
generating a transformation model for transforming full loop optical measurement data to short loop optical measurement data, wherein the short loop optical measurement data includes optical measurement data of periodic memory array structures, wherein the full loop optical measurement data includes optical measurement data of complementary metal-oxide-semiconductor (CMOS) under array (CuA) devices, the CuA devices including CMOS structures beneath duplicates of the periodic memory array structures;
generating a measurement model for determining one or more measurements of the CuA devices based on the short loop optical measurement data;
receiving the full loop optical measurement data for the CuA devices on one or more test samples;
converting the full loop optical measurement data for the CuA devices on the one or more test samples to the short loop optical measurement data for the CuA devices on the one or more test samples using the transformation model; and
determining values of the one or more measurements of the periodic memory array structures on the one or more test samples using the measurement model with the short loop optical measurement data for the CuA devices.