US 12,443,111 B2
Prediction data selection for model calibration to reduce model prediction uncertainty
Lei Wang, Los Gatos, CA (US); Yi-Yin Chen, Santa Clara, CA (US); Mu Feng, San Jose, CA (US); and Qian Zhao, San Jose, CA (US)
Assigned to ASML NETHERLANDS, Veldhoven (NL)
Appl. No. 17/625,125
Filed by ASML NETHERLANDS B.V., Veldhoven (NL)
PCT Filed Jun. 15, 2020, PCT No. PCT/EP2020/066446
§ 371(c)(1), (2) Date Jan. 6, 2022,
PCT Pub. No. WO2021/004725, PCT Pub. Date Jan. 14, 2021.
Claims priority of provisional application 62/872,521, filed on Jul. 10, 2019.
Prior Publication US 2022/0276563 A1, Sep. 1, 2022
Int. Cl. G06F 30/398 (2020.01); G03F 1/36 (2012.01); G03F 1/68 (2012.01); G03F 7/00 (2006.01)
CPC G03F 7/705 (2013.01) [G03F 1/36 (2013.01); G03F 1/68 (2013.01); G03F 7/706839 (2023.05)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
determining, by a hardware computer system, prediction data using one or more the prediction models, the one or more prediction models having been calibrated with calibration data;
determining a prediction uncertainty parameter based on the prediction data, the prediction uncertainty parameter associated with variation in the prediction data;
selecting, based on the prediction uncertainty parameter, a set of data associated with a patterning process; and
using the set of data to enable configuration of a prediction model that produces, in use, less uncertain or more accurate prediction data.