Method for adjusting a patterning process

A method for generating a control output for a patterning process, the method comprising:

• receiving a control input, the control input for controlling a patterning process, the control input comprising one or more parameters used in the patterning process;
• and
• generating, with a trained machine learning model, based on the control input, a control output for the patterning process, the machine learning model having been trained with training data generated from simulation of the patterning process and/or actual process data, wherein the training data comprises 1) a plurality of training control inputs corresponding to a plurality of operational conditions of the patterning process, the plurality of operational conditions of the patterning process associated with operational condition specific behavior of the patterning process over time, and 2) a plurality of training control outputs corresponding to the plurality of training control inputs, wherein each training control output is generated using a physical model having a corresponding training control input as an input;
• and
• configuring a physical measurement or manufacturing step of the patterning process based on the control output, or providing a signal representing, or based on, the control output to a system for use in configuration of a physical measurement or manufacturing step of the patterning process.

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

• receive a plurality of control inputs for controlling a patterning process for a plurality of corresponding operational conditions, each of the control inputs comprising one or more parameters used in the patterning process;
• generate or receive a plurality of control outputs associated with one or more adjustments of the one or more parameters, the plurality of control outputs based on the output of a physical model used in simulating behavior of the patterning process subject to the plurality of operational conditions;
• train a machine learning model configured to infer a new control output corresponding to a new control input by inputting the received plurality of control inputs and plurality of generated or received control outputs;
• and
• configure a physical measurement or manufacturing step of the patterning process based on the trained machine learning model, or provide a signal representing, or based on, the trained machine learning model to a system for use in configuration of a physical measurement or manufacturing step of the patterning process.