US 11,714,357 B2
Method to predict yield of a device manufacturing process
Alexander Ypma, Veldhoven (NL); Cyrus Emil Tabery, San Jose, CA (US); Simon Hendrik Celine Van Gorp, Oud-Turnhout (BE); Chenxi Lin, Newark, CA (US); Dag Sonntag, Eindhoven (NL); Hakki Ergün Cekli, Singapore (SG); Ruben Alvarez Sanchez, Veldhoven (NL); Shih-Chin Liu, Eindhoven (NL); Simon Philip Spencer Hastings, San Jose, CA (US); Boris Menchtchikov, Redwood City, CA (US); Christiaan Theodoor De Ruiter, Eindhoven (NL); Peter Ten Berge, Eindhoven (NL); Michael James Lercel, Fishkill, NY (US); Wei Duan, Eindhoven (NL); and Pierre-Yves Jerome Yvan Guittet, Veldhoven (NL)
Assigned to ASML NETHERLANDS B.V., Veldhoven (NL)
Filed by ASML NETHERLANDS B.V., Veldhoven (NL)
Filed on Jun. 30, 2021, as Appl. No. 17/363,057.
Application 17/363,057 is a continuation of application No. 16/497,826, granted, now 11,086,229, previously published as PCT/EP2018/058096, filed on Mar. 29, 2018.
Claims priority of provisional application 62/645,345, filed on Mar. 20, 2018.
Claims priority of provisional application 62/502,281, filed on May 5, 2017.
Prior Publication US 2021/0325788 A1, Oct. 21, 2021
Int. Cl. G03F 7/20 (2006.01); G03F 7/00 (2006.01)
CPC G03F 7/70491 (2013.01) [G03F 7/705 (2013.01); G03F 7/70658 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a machine learning model trained to metrology data comprising measurements of an electrical characteristic from previously processed substrates and process metrology data comprising measurements of at least one parameter related to a process characteristic measured from the previously processed substrates;
obtaining process metrology data related to a substrate comprising the at least one parameter; and
providing the obtained process metrology data to the machine learning model for predicting an electrical characteristic of the substrate; and
dynamically updating the machine learning model based on new process metrology data and/or new metrology data.