Apparatus and method for analyzing an element of a photolithography process with the aid of a transformation model

An apparatus for transforming first image data of a first element of a photolithography process measured by use of a first measuring apparatus into second image data, the apparatus comprising:

• a computer system comprising a transformation model;
• wherein the second image data represents a prediction of an image of the first element measured by a second measuring apparatus if the second measuring apparatus were used to measure the first element, enabling an assessment of the first element without the first element needing to be transported and aligned with respect to the second measuring apparatus,
• wherein the second measuring apparatus comprises at least one of:
• a first scanning particle microscope or an optical measuring tool,
• wherein the transformation model has been trained using a multiplicity of first training data and second training data,
• wherein the first training data comprise data obtained by using the first measuring apparatus to measure a set of at least one element of the photolithography process, and the second training data comprise image data obtained by using the second measuring apparatus to measure the set of at least one element of the photolithography process, and
• wherein the apparatus is configured to use the transformation model to transform the first image data of the first element of the photolithography process into the second image data;
• wherein the transformation model comprises at least one encoder block for determining information-carrying features from the first image data and at least one decoder block for producing the second image data;
• and
• wherein the transformation model is trained by:
• applying the transformation model to the first training data to generate third image data that represents a prediction of at least one image of the set of the at least one element of the photolithography process measured by use of the first measuring apparatus;
• comparing the third image data with corresponding fourth image data in the second training data, wherein the fourth image data represents the at least one image of the at least one element of the photolithography process measured by the second measuring apparatus;
• and
• modifying parameters of the transformation model based on the comparison of the third image data with the corresponding fourth image data.

A method for analyzing a first element of a photolithography process, including the steps of:

• a. measuring first image data of the first element with a first measuring apparatus;
• and
• b. transforming the first image data into second image data that represents a prediction of an image of the first element measured by a second measuring apparatus if the second measuring apparatus were used to measure the first element, enabling an assessment of the first element without the first element needing to be transported and aligned with respect to the second measuring apparatus, wherein the second measuring apparatus comprises at least one of:
• a scanning particle microscope or an optical measuring tool,
• wherein the transforming of the first image data into the second image data is performed using an apparatus that comprises a computer system comprising a transformation model,
• wherein the transformation model comprises at least one encoder block for determining information-carrying features from the first image data and at least one decoder block for producing the second image data,
• wherein the transformation model has been trained using a multiplicity of first training data and second training data,
• wherein the first training data comprise image data obtained by using the first measuring apparatus to measure a set of at least one element of the photolithography process, and the second training data comprise image data obtained by using the second measuring apparatus to measure the set of at least one element of the photolithography process, and
• wherein the transformation model is trained by:
• applying the transformation model to the first training data to generate third image data that represents a prediction of at least one image of the set of the at least one element of the photolithography process measured by use of the first measuring apparatus,
• comparing the third image data with corresponding fourth image data of the second training data, wherein the fourth image data represents the at least one image of the set of at least one element of the photolithography process measured by the second measuring apparatus, and
• modifying parameters of the transformation model based on the comparison of the third image data with the corresponding fourth image data.

An apparatus comprising:

• at least one of:
• a scanning particle microscope or a scanning probe microscope configured to generate first measurement data representing measurements of a first element of a photolithography process;
• and
• a computer system comprising a transformation model configured to transform the first measurement data into second image data,
• wherein the transformation model comprises at least one encoder block for determining information-carrying features from the first measurement data and at least one decoder block for producing the second image data,
• wherein the second image data represents a prediction of an image of the first element measured by an optical measuring tool if the optical measuring tool were used to measure the first element, enabling an assessment of the first element without the first element needing to be transported and aligned with respect to the optical measuring tool;
• and
• wherein the transformation model has been trained using a multiplicity of previously recorded first training data and second training data, the first training data comprise data obtained by using at least one of:
• the scanning particle microscope or the scanning probe microscope to measure a set of at least one element of the photolithography process, and the previously recorded second training data comprise data obtained by using the optical measuring tool to measure the set of at least one element of the photolithography process;
• wherein the transformation model is trained by:
• applying the transformation model to the first training data to generate third image data that represents a prediction of at least one image of the set of the at least one element of the photolithography process measured by use of the scanning particle microscope or the scanning probe microscope,
• comparing the third image data with corresponding fourth image data of the second training data, wherein the fourth image data represents the at least one image of the set of at least one element of the photolithography process measured by the optical measuring tool, and
• modifying parameters of the transformation model based on the comparison of the third image data with the corresponding fourth image data.