A method of extracting a feature from a data set includes iteratively extracting a feature from a data set based on a visualization of a residual pattern within the data set, wherein the feature is distinct from a feature extracted in a previous iteration, and the visualization of the residual pattern uses the feature extracted in the previous iteration. Visualizing the data set using the feature extracted in the previous iteration may include showing residual patterns of attribute data that are relevant to target data. Visualizing the data set using the feature extracted in the previous iteration may involve adding cluster constraints to the data set, based on the feature extracted in the previous iteration. Additionally or alternatively, visualizing the data set using the feature extracted in the previous iteration may involve defining conditional probabilities conditioned on the feature extracted in the previous iteration.

A method of determining a field of view setting for an inspection tool having a configurable field of view, the method including: obtaining a process margin distribution of features on at least part of a substrate; obtaining a threshold value; identifying, in dependence on the obtained process margin distribution and the threshold value, one or more regions on at least part of the substrate; and determining the field of view setting in dependence on the identified one or more regions.

An arrangement of a microlithographic optical imaging device includes first and supporting structures. The first supporting structure supports an optical element of the imaging device. The first supporting structure supports the second supporting structure via supporting spring devices of a vibration decoupling device. The supporting spring devices act kinematically parallel to one another between the first and second supporting structures. Each supporting spring device defines a supporting force direction and a supporting length along the supporting force direction. The second supporting structure supports a measuring device configured to measure the position and/or orientation of the optical element in relation to a reference in at least one degree of freedom and up to all six degrees of freedom in space. A creep compensation device compensates a change in a static relative situation between the first and second supporting structures in at least one correction degree of freedom.

Methods and systems for milling and imaging a sample based on multiple fiducials at different sample depths include forming a first fiducial on a first sample surface at a first sample depth; milling at least a portion of the sample surface to expose a second sample surface at a second sample depth; forming a second fiducial on the second sample surface; and milling at least a portion of the second sample surface to expose a third sample surface including a region of interest (ROI) at a third sample depth. The location of the ROI at the third sample depth relative to the first fiducial may be calculated based on an image of the ROI and the second fiducial as well as relative position between the first fiducial and the second fiducial.

According to aspects of the embodiments, there is provided an apparatus and method for driving a laser imaging module (LIM) that includes an adjustment current to have all laser diodes emitting the same amount of output so that the diodes can be connected in series on a single high current power source. Fine tuning can be done by a dedicated low current controllable power source connected directly to each laser diode. A series connected LIM uses only two heavy gauge wires so total power loss and heat stress on the LIM and module drawer connectors will be significantly reduced. Additional fine tuning can include an electronic gate so that individual diodes could be quickly turned off independently from each other.

An extreme ultraviolet lithography (EUVL) method includes providing at least two phase-shifting mask areas having a same pattern. A resist layer is formed over a substrate. An optimum exposure dose of the resist layer is determined, and a latent image is formed on a same area of the resist layer by a multiple exposure process. The multiple exposure process includes a plurality of exposure processes and each of the plurality of exposure processes uses a different phase-shifting mask area from the at least two phase-shifting mask areas having a same pattern.

A semiconductor processing system includes a first photolithography system and a second photolithography system. The semiconductor processing system includes a layout database that stores a plurality of layouts indicating features to be formed in a wafer. The semiconductor processing system includes a layout analyzer that analyzes the layouts and selects either the first photolithography system or the second photolithography system based on dimensions of features in the layouts.

A method for controlling a lithographic apparatus, and associated apparatuses. The method is configured to provide product structures to a substrate in a lithographic process and includes determining optimization data. The optimization data includes measured and/or simulated data of at least one performance parameter associated with the product structures and/or their arrangement which are to be applied to the substrate in the lithographic process. Substrate specific metrology data as measured and/or modeled before the providing of product structures to the substrate is determined, the substrate specific metrology data including metrology data relating to a characteristic of the substrate to which the structures are being applied and/or the state of the lithographic apparatus at the time that the structures are applied to the substrate. The method further includes optimizing control of the lithographic apparatus during the lithographic process based on the optimization data and the substrate specific metrology data.

Described herein is a method for training a machine learning model to determine a source of error contribution to multiple features of a pattern printed on a substrate. The method includes obtaining training data having multiple datasets, wherein each dataset has error contribution values representative of an error contribution from one of multiple sources to the features, and wherein each dataset is associated with an actual classification that identifies a source of the error contribution of the corresponding dataset; and training, based on the training data, a machine learning model to predict a classification of a reference dataset of the datasets such that a cost function that determines a difference between the predicted classification and the actual classification of the reference dataset is reduced.

A field-of-view at a first modeled target location of a first target disposed on a specimen can be configured, which can include moving the stage relative to the detector. The first modeled target location is determined by summing a first design target location and a navigational error provided by an online model. A first image of the field-of-view is grabbed using the detector. The field-of-view at a second modeled target location of a second target disposed on the specimen is configured. Concurrent with configuring the field-of-view at the second modeled target location, using a processor, the position of a first actual target location is determined using the first image. The online model is updated with a difference between the first design target location and the first actual target location.