Abstract: A method for obtaining a training data set including synthetic metrology data, the training data set being configured for training of a model relating to a manufacturing process for manufacturing an integrated circuit. The method includes obtaining behavioral property data describing a behavior of a process parameter resultant from the manufacturing process and/or a related tool or effect. Additionally, or alternatively metrology data performed on a structure formed by the manufacturing process and/or a similar manufacturing process may be obtained. Using the behavioral property data and/or metrology data, synthetic metrology data is determined, which describes the effect of variations in the manufacturing process, and/or a related tool or effect on the process parameter. The model is trained using the training data set including the synthetic metrology data.

Abstract: A method for optimizing a sequence of processes for manufacturing of product units, includes: associating measurement results of performance parameters (e.g., fingerprints) with the recorded process characteristics (e.g., context); obtaining a characteristic (e.g., context) of a previous process (e.g. deposition) in the sequence already performed on a product unit; obtaining a characteristic (e.g., context) of a subsequent process (e.g., exposure) in the sequence to be performed on the product unit; determining a predicted performance parameter (e.g., fingerprint) of the product unit associated with the sequence of previous and subsequent processes by using the obtained characteristics to retrieve measurement results of the performance parameters (e.g., fingerprints) corresponding to the recorded characteristics; and determining corrections to be applied to future processes (e.g. exposure, etch) in the sequence to be performed on the product unit, based on the determined predicted performance parameter.

Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

Abstract: A method for estimating a parameter across a region on a substrate, the region being divided into a plurality of sub-regions, the method including: obtaining values of the parameter for at least two sub-regions out of the plurality of sub-regions; and estimating the parameter for a position on the region by evaluation of a function having said values of the parameter as input values, wherein the function: a) has piecewise defined base functions, wherein a single base function is defined across a sub-region; and b) is continuous between one or more adjacent sub-regions of the at least two sub-regions within the region.

Abstract: A method for optimizing a sequence of processes for manufacturing of product units, includes: associating measurement results of performance parameters (e.g., fingerprints) with the recorded process characteristics (e.g., context); obtaining a characteristic (e.g., context) of a previous process (e.g. deposition) in the sequence already performed on a product unit; obtaining a characteristic (e.g., context) of a subsequent process (e.g., exposure) in the sequence to be performed on the product unit; determining a predicted performance parameter (e.g., fingerprint) of the product unit associated with the sequence of previous and subsequent processes by using the obtained characteristics to retrieve measurement results of the performance parameters (e.g., fingerprints) corresponding to the recorded characteristics; and determining corrections to be applied to future processes (e.g. exposure, etch) in the sequence to be performed on the product unit, based on the determined predicted performance parameter.

Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

Abstract: A method of characterizing distortions in a lithographic process, and associated apparatuses. The method includes obtaining measurement data corresponding to a plurality of measurement locations on a substrate, the measurement data comprising measurements performed on a plurality of substrates, and comprising one or more measurements performed on one or more of the substrates for each of the measurement locations. For each of the measurement locations, a first quality value representing a quality metric and a noise value representing a noise metric is determined from the measurements performed at that measurement location. A plurality of distortion parameters is determined, each distortion parameter configured to characterize a systematic distortion in the quality metric and a statistical significance of the distortion parameters from the first quality value and from the noise value is determined. Systematic distortion is parameterized from the distortion parameters determined to be statistically significant.

Abstract: A method, system and program for determining a fingerprint of a parameter. The method includes determining a contribution from a device out of a plurality of devices to a fingerprint of a parameter. The method includes obtaining parameter data and usage data, wherein the parameter data is based on measurements for multiple substrates having been processed by the plurality of devices, and the usage data indicates which of the devices out of the plurality of the devices were used in the processing of each substrate; and determining the contribution using the usage data and parameter data.

Abstract: A first substrate 2002 has a calibration pattern applied to a first plurality of fields 2004 by a lithographic apparatus. Further substrates 2006, 2010 have calibration patterns applied to further pluralities of fields 2008, 2012. The different pluralities of fields have different sizes and/or shapes and/or positions. Calibration measurements are performed on the patterned substrates 2002, 2006, 2010 and used to obtain corrections for use in controlling the apparatus when applying product patterns to subsequent substrates. Measurement data representing the performance of the apparatus on fields of two or more different dimensions (fields 2004, 2008, 2012 in this example) is gathered together in a database 2013 and used to synthesize the information needed to calibrate the apparatus for a new size. Calibration data is also obtained for different scan and step directions.

Abstract: A method for determining a preferred control strategy relating to control of a manufacturing process for manufacturing an integrated circuit. The method includes: obtaining process data associated with a design of said integrated circuit; and obtaining a plurality of candidate control strategies configured to control the manufacturing process based on the process data, each candidate control strategy including an associated cost metric based on an associated requirement to implement the candidate control strategy. A quality metric related to an expected performance of the manufacturing process is determined for each candidate control strategies, and a preferred control strategy is selected based on the determined quality metrics and associated cost metrics for each candidate control strategy.

Abstract: A method, system and program for determining a fingerprint of a parameter. The method includes determining a contribution from a device out of a plurality of devices to a fingerprint of a parameter. The method including: obtaining parameter data and usage data, wherein the parameter data is based on measurements for multiple substrates having been processed by the plurality of devices, and the usage data indicates which of the devices out of the plurality of the devices were used in the processing of each substrate; and determining the contribution using the usage data and parameter data.

Abstract: A method for determining a plurality of corrections for control of at least one manufacturing apparatus used in a manufacturing process for providing product structures to a substrate in a plurality of layers, the method including: determining the plurality of corrections including a correction for each layer, based on an actuation potential of the applicable manufacturing apparatus used in the formation of each layer, wherein the determining includes determining corrections for each layer simultaneously in terms of a matching parameter.

Abstract: A method includes determining topographic information of a substrate for use in a lithographic imaging system, determining or estimating, based on the topographic information, imaging error information for a plurality of points in an image field of the lithographic imaging system, adapting a design for a patterning device based on the imaging error information. In an embodiment, a plurality of locations for metrology targets is optimized based on imaging error information for a plurality of points in an image field of a lithographic imaging system, wherein the optimizing involves minimizing a cost function that describes the imaging error information. In an embodiment, locations are weighted based on differences in imaging requirements across the image field.

Abstract: A first substrate 2002 has a calibration pattern applied to a first plurality of fields 2004 by a lithographic apparatus. Further substrates 2006, 2010 have calibration patterns applied to further pluralities of fields 2008, 2012. The different pluralities of fields have different sizes and/or shapes and/or positions. Calibration measurements are performed on the patterned substrates 2002, 2006, 2010 and used to obtain corrections for use in controlling the apparatus when applying product patterns to subsequent substrates. Measurement data representing the performance of the apparatus on fields of two or more different dimensions (fields 2004, 2008, 2012 in this example) is gathered together in a database 2013 and used to synthesize the information needed to calibrate the apparatus for a new size. Calibration data is also obtained for different scan and step directions.

Abstract: A first substrate (2002) has a calibration pattern applied to a first plurality of fields (2004) by a lithographic apparatus. Further substrates (2006, 2010) have calibration patterns applied to further pluralities of fields (2008, 2012). The different pluralities of fields have different sizes and/or shapes and/or positions. Calibration measurements are performed on the patterned substrates (2002, 2006, 2010) and used to obtain corrections for use in controlling the apparatus when applying product patterns to subsequent substrates. Measurement data representing the performance of the apparatus on fields of two or more different dimensions (2004, 2008, 2012) is gathered together in a database (2013) and used to synthesize the information needed to calibrate the apparatus for a new size. Calibration data is also obtained for different scan and step directions.

Abstract: A method for optimizing a sequence of processes for manufacturing of product units, includes: associating measurement results of performance parameters (e.g., fingerprints) with the recorded process characteristics (e.g., context); obtaining a characteristic (e.g., context) of a previous process (e.g. deposition) in the sequence already performed on a product unit; obtaining a characteristic (e.g., context) of a subsequent process (e.g., exposure) in the sequence to be performed on the product unit; determining a predicted performance parameter (e.g., fingerprint) of the product unit associated with the sequence of previous and subsequent processes by using the obtained characteristics to retrieve measurement results of the performance parameters (e.g., fingerprints) corresponding to the recorded characteristics; and determining corrections to be applied to future processes (e.g. exposure, etch) in the sequence to be performed on the product unit, based on the determined predicted performance parameter.

Abstract: A method to change an etch parameter of a substrate etching process, the method including: making a first measurement of a first metric associated with a structure on a substrate before being etched; making a second measurement of a second metric associated with a structure on a substrate after being etched; and changing the etch parameter based on a difference between the first measurement and the second measurement.

Abstract: A method, system and program for determining a fingerprint of a parameter. The method includes determining a contribution from a device out of a plurality of devices to a fingerprint of a parameter. The method including: obtaining parameter data and usage data, wherein the parameter data is based on measurements for multiple substrates having been processed by the plurality of devices, and the usage data indicates which of the devices out of the plurality of the devices were used in the processing of each substrate; and determining the contribution using the usage data and parameter data.

Abstract: A method of characterizing distortions in a lithographic process, and associated apparatuses. The method includes obtaining measurement data corresponding to a plurality of measurement locations on a substrate, the measurement data comprising measurements performed on a plurality of substrates, and comprising one or more measurements performed on one or more of the substrates for each of the measurement locations. For each of the measurement locations, a first quality value representing a quality metric and a noise value representing a noise metric is determined from the measurements performed at that measurement location. A plurality of distortion parameters is determined, each distortion parameter configured to characterize a systematic distortion in the quality metric and a statistical significance of the distortion parameters from the first quality value and from the noise value is determined. Systematic distortion is parameterized from the distortion parameters determined to be statistically significant.