Abstract:
A method for training a deep learning model of a patterning process. The method includes obtaining (i) training data including an input image of at least a part of a substrate having a plurality of features and including a truth image, (ii) a set of classes, each class corresponding to a feature of the plurality of features of the substrate within the input image, and (iii) a deep learning model configured to receive the training data and the set of classes, generating a predicted image, by modeling and/or simulation with the deep learning model using the input image, assigning a class of the set of classes to a feature within the predicted image based on matching of the feature with a corresponding feature within the truth image, and generating, by modeling and/or simulation, a trained deep learning model by iteratively assigning weights using a loss function.
Abstract:
A method of, and associated apparatus for, determining focus corrections for a lithographic projection apparatus. The method comprises exposing a plurality of global correction fields on a test substrate, each comprising a plurality of global correction marks, and each being exposed with a tilted focus offset across it; measuring a focus dependent characteristic for each of the plurality of global correction marks to determine interfield focus variation information; and calculating interfield focus corrections from the interfield focus variation information.
Abstract:
For angular resolved spectrometry a radiation beam is used having an illumination profile having four quadrants is used. The first and third quadrants are illuminated whereas the second and fourth quadrants aren't illuminated. The resulting pupil plane is thus also divided into four quadrants with only the zeroth order diffraction pattern appearing in the first and third quadrants and only the first order diffraction pattern appearing in the second and third quadrants.
Abstract:
For angular resolved spectrometry a radiation beam is used having an illumination profile having four quadrants is used. The first and third quadrants are illuminated whereas the second and fourth quadrants aren't illuminated. The resulting pupil plane is thus also divided into four quadrants with only the zeroth order diffraction pattern appearing in the first and third quadrants and only the first order diffraction pattern appearing in the second and third quadrants.
Abstract:
An apparatus and method to determine a property of a substrate by measuring, in the pupil plane of a high numerical aperture lens, an angle-resolved spectrum as a result of radiation being reflected off the substrate. The property may be angle and wavelength dependent and may include the intensity of TM- and TE-polarized radiation and their relative phase difference.