Determining pattern ranking based on measurement feedback from printed substrate

A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:

• determine, via simulation using a patterning process model, a simulated pattern of a patterning process and a characteristic of the simulated pattern;
• determine, via a trained machine learning model, a characteristic adjustment value for the characteristic of the simulated pattern;
• and
• adjust the characteristic of the simulated pattern based on the characteristic adjustment value.

A method comprising:

• adjusting, using a first machine learning model, a characteristic of at least one simulated pattern within a set of simulated patterns of a patterning process;
• determining a subset of the simulated patterns based on the adjusted characteristic of the at least one simulated pattern;
• and
• determining, using a second machine learning model, a ranking of the at least one simulated pattern within the subset of the simulated patterns.

A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:

• adjust, using a first machine learning model, a characteristic of at least one simulated pattern within a set of simulated patterns of a patterning process;
• determine a subset of the simulated patterns based on the adjusted characteristic of the at least one simulated pattern;
• and
• determine, using a second machine learning model, a ranking of the at least one simulated pattern within subset of the simulated patterns.