US 12,353,967 B2
Method and apparatus for determining feature contribution to performance
Vahid Bastani, Eindhoven (NL); Dag Sonntag, Eindhoven (NL); Reza Sahraeian, Eindhoven (NL); and Dimitra Gkorou, Eindhoven (NL)
Assigned to ASML NETHERLANDS B.V., Veldhoven (NL)
Appl. No. 17/624,014
Filed by ASML NETHERLANDS B.V., Veldhoven (NL)
PCT Filed Jun. 5, 2020, PCT No. PCT/EP2020/065619
§ 371(c)(1), (2) Date Dec. 30, 2021,
PCT Pub. No. WO2021/001114, PCT Pub. Date Jan. 7, 2021.
Claims priority of application No. 19184423 (EP), filed on Jul. 4, 2019; and application No. 19186833 (EP), filed on Jul. 17, 2019.
Prior Publication US 2022/0351075 A1, Nov. 3, 2022
Int. Cl. G03F 7/00 (2006.01); G06N 20/00 (2019.01); H01L 21/66 (2006.01)
CPC G06N 20/00 (2019.01) [G03F 7/705 (2013.01); G03F 7/70616 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a first model trained on first process data and first performance data;
identifying one or more substrates based on a quality of prediction of the first model when applied to process data associated with the one or more substrates;
training, by a hardware computer system, a second model on second process data and second performance data associated with a process of patterning substrates and associated with the identified one or more substrates; and
using the second model to determine a contribution of a process feature of the second process data to the second performance data associated with the one or more substrates.