Abstract: Methods and systems for accelerated training of a machine learning based model for semiconductor applications are provided. One method for training a machine learning based model includes acquiring information for non-nominal instances of specimen(s) on which a process is performed. The machine learning based model is configured for performing simulation(s) for the specimens. The machine learning based model is trained with only information for nominal instances of additional specimen(s). The method also includes re-training the machine learning based model with the information for the non-nominal instances of the specimen(s) thereby performing transfer learning of the information for the non-nominal instances of the specimen(s) to the machine learning based model.

Abstract: Methods and systems for training a machine learning model using synthetic defect images are provided. One system includes one or more components executed by one or more computer subsystems. The one or more components include a graphical user interface (GUI) configured for displaying one or more images for a specimen and image editing tools to a user and for receiving input from the user that includes one or more alterations to at least one of the images using one or more of the image editing tools. The component(s) also include an image processing module configured for applying the alteration(s) to the at least one image thereby generating at least one modified image and storing the at least one modified image in a training set. The computer subsystem(s) are configured for training a machine learning model with the training set in which the at least one modified image is stored.

Abstract: Methods and systems for transforming positions of defects detected on a wafer are provided. One method includes aligning output of an inspection subsystem for a first frame in a first swath in a first die in a first instance of a multi-die reticle printed on the wafer to the output for corresponding frames, swaths, and dies in other reticle instances printed on the wafer. The method also includes determining different swath coordinate offsets for each of the frames, respectively, in the other reticle instances based on the swath coordinates of the output for the frames and the corresponding frames aligned thereto and applying one of the different swath coordinate offsets to the swath coordinates reported for the defects based on the other reticle instances in which they are detected thereby transforming the swath coordinates for the defects from swath coordinates in the other reticle instances to the first reticle instance.

Abstract: Methods and systems for setting up inspection of a specimen with design and noise based care areas are provided. One system includes one or more computer subsystems configured for generating a design-based care area for a specimen. The computer subsystem(s) are also configured for determining one or more output attributes for multiple instances of the care area on the specimen, and the one or more output attributes are determined from output generated by an output acquisition subsystem for the multiple instances. The computer subsystem(s) are further configured for separating the multiple instances of the care area on the specimen into different care area sub-groups such that the different care area sub-groups have statistically different values of the output attribute(s) and selecting a parameter of an inspection recipe for the specimen based on the different care area sub-groups.

Abstract: Methods and systems for determining a layer on which a defect detected on a wafer is located are provided. One method includes detecting defects on a wafer by directing light to the wafer at first and second angles of incidence and determining locations of the defects on the wafer based on the output corresponding to the defects. For one of the defects detected in the output generated for one spot illuminated on the wafer with the light directed to the wafer at the first and second angles, the method includes comparing the locations of the one of the defects determined based on the output generated with the light directed to the one spot on the wafer at the first and second angles. The method further includes determining a layer of the wafer on which the one of the defects is located based on results of the comparing.

Abstract: Methods and systems for generating a high resolution image for a specimen from a low resolution image of the specimen are provided. One system includes one or more computer subsystems configured for acquiring a low resolution image of a specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a deep convolutional neural network that includes one or more first layers configured for generating a representation of the low resolution image. The deep convolutional neural network also includes one or more second layers configured for generating a high resolution image of the specimen from the representation of the low resolution image. The second layer(s) include a final layer configured to output the high resolution image and configured as a sub-pixel convolutional layer.

Abstract: Methods and systems for aligning images for a specimen acquired with different modalities are provided. One method includes acquiring information for a specimen that includes at least first and second images for the specimen. The first image is acquired with a first modality different than a second modality used to acquire the second image. The method also includes inputting the information into a learning based model. The learning based model is included in one or more components executed by one or more computer systems. The learning based model is configured for transforming one or more of the at least first and second images to thereby render the at least the first and second images into a common space. In addition, the method includes aligning the at least the first and second images using results of the transforming. The method may also include generating an alignment metric using a classifier.

Abstract: Various embodiments for detecting defects on a wafer are provided. One method includes acquiring output generated by an inspection system for a wafer during an inspection process that is performed after at least first and second process steps have been performed on the wafer. The first and second process steps include forming first and second portions, respectively, of a design on the wafer. The first and second portions of the design are mutually exclusive in space on the wafer. The method also includes detecting defects on the wafer based on the output and determining positions of the defects with respect to the first and second portions of the design. In addition, the method includes associating different portions of the defects with the first or second process step based on the positions of the defects with respect to the first and second portions of the design.

Abstract: Methods and systems for training a learning based defect classifier are provided. One method includes training a learning based defect classifier with a training set of defects that includes identified defects of interest (DOIs) and identified nuisances. The DOIs and nuisances in the training set include DOIs and nuisances identified on at least one training wafer and at least one inspection wafer. The at least one training wafer is known to have an abnormally high defectivity and the at least one inspection wafer is expected to have normal defectivity.

Abstract: Methods and systems for performing active learning for defect classifiers are provided. One system includes one or more computer subsystems configured for performing active learning for training a defect classifier. The active learning includes applying an acquisition function to data points for the specimen. The acquisition function selects one or more of the data points based on uncertainty estimations associated with the data points. The active learning also includes acquiring labels for the selected one or more data points and generating a set of labeled data that includes the selected one or more data points and the acquired labels. The computer subsystem(s) are also configured for training the defect classifier using the set of labeled data. The defect classifier is configured for classifying defects detected on the specimen using the images generated by the imaging subsystem.

Abstract: Methods and systems for shape metric based scoring of wafer locations are provided. One method includes selecting shape based grouping (SBG) rules for at least two locations on a wafer. For one of the wafer locations, the selecting step includes modifying distances between geometric primitives in a design for the wafer with metrology data for the one location and determining metrical complexity (MC) scores for SBG rules associated with the geometric primitives in a field of view centered on the one location based on the distances. The selecting step also includes selecting one of the SBG rules for the one location based on the MC scores. The method also includes sorting the at least two locations on the wafer based on the SBG rule selected for the at least two locations.

Abstract: Methods and systems fir identifying nuisances and defects of interest (DOIs) in defects detected on a wafer are provided. One method includes acquiring metrology data for the wafer generated by a metrology tool that performs measurements on the wafer at an array of measurement points. In one embodiment, the measurement points are determined prior to detecting the defects on the wafer and independently of the defects detected on the wafer. The method also includes determining locations of defects detected on the wafer with respect to locations of the measurement points on the wafer and assigning metrology data to the defects as a defect attribute based on the locations of the defects determined with respect to the locations of the measurement points. In addition, the method includes determining if the defects are nuisances or DOIs based on the defect attributes assigned to the defects.

Abstract: Systems and methods for detecting programmed defects on a water during inspection of the wafer are provided. One method includes selecting a mode of an inspection subsystem for detecting programmed defects on a wafer that generates output for the wafer having the lowest non-defect signal and at least a minimum signal for the programmed defects. The method also includes selecting a training care area that is mutually exclusive of care area(s) used for detecting the programmed defects during inspection of the wafer. The training care area generates less of the non-defect signal than the care area(s). The method further includes training a programmed defect detection method using the output generated with the selected mode in the training care area and detecting the programmed defects during the inspection of the wafer by applying the trained programmed defect detection method to the output generated in the care area(s) with the selected mode.

Abstract: Methods and systems for selecting a mode for inspection of a specimen are provided. One method includes determining how separable defects of interest (DOIs) and nuisances detected on a specimen are in one or more modes of an inspection subsystem. The separability of the modes for the Dais and nuisances is used to select a subset of the modes for inspection of other specimens of the same type. Other characteristics of the performance of the modes may be used in combination with the separability to select the modes. The subset of modes selected based on the separability may also be an initial subset of modes for which additional analysis is performed to determine the final subset of the modes.

Abstract: Methods and systems for determining parameter(s) of a metrology process to be performed on a specimen are provided. One system includes one or more computer subsystems configured for automatically generating regions of interest (ROIs) to be measured during a metrology process performed for the specimen with the measurement subsystem based on a design for the specimen. The computer subsystem(s) are also configured for automatically determining parameter(s) of measurement(s) performed in first and second subsets of the ROIs during the metrology process with the measurement subsystem based on portions of the design for the specimen located in the first and second subsets of the ROIs, respectively. The parameter(s) of the measurement(s) performed in the first subset are determined separately and independently of the parameter(s) of the measurement(s) performed in the second subset.

Abstract: Various methods and systems for creating or performing a dynamic sampling scheme for a process during which measurements are performed on wafers are provided. One method for creating a dynamic sampling scheme for a process during which measurements are performed on wafers includes performing the measurements on all of the wafers in at least one lot at all measurement spots on the wafers. The method also includes determining an optimal sampling scheme, an enhanced sampling scheme, a reduced sampling scheme, and thresholds for the dynamic sampling scheme for the process based on results of the measurements. The thresholds correspond to values of the measurements at which the optimal sampling scheme, the enhanced sampling scheme, and the reduced sampling scheme are to be used for the process.

Abstract: Methods and systems for generating a high resolution image for a specimen from one or more low resolution images of the specimen are provided. One system includes one or more computer subsystems configured for acquiring one or more low resolution images of a specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a model that includes one or more first layers configured for generating a representation of the one or more low resolution images. The model also includes one or more second layers configured for generating a high resolution image of the specimen from the representation of the one or more low resolution images.

Abstract: Methods and systems for determining boundaries of patterned features formed on a specimen from an unresolved image of the specimen are provided. One system includes computer subsystem(s) configured for comparing a difference image in which patterned feature(s) are unresolved to different simulated images. The different simulated images are generated by simulating difference images generated for the patterned feature(s) formed on the specimen with different perturbations, respectively. The computer subsystem(s) are configured for, based on the comparing, assigning an amplitude to each of the different perturbations. The computer subsystem(s) are further configured for determining one or more boundaries of the patterned feature(s) formed on the specimen by applying the different perturbations to one or more designed boundaries of the patterned feature(s) with the assigned amplitudes.

Abstract: Methods and systems for creating a sample of defects for a specimen are provided. One method includes detecting defects on a specimen based on output generated by a detector of an output acquisition subsystem. For the defects detected in an array region on the specimen, where the array region includes multiple array cell types, the method includes stacking information for the defects based on the multiple array cell types. The stacking includes overlaying design information for only a first of the multiple array cell types with the information for only the defects detected in the first of the multiple array cell types. In addition, the method includes selecting a portion of the detected defects based on results of the stacking thereby creating a sample of the detected defects.

Abstract: Methods and systems for identifying a source of nuisance defects on a wafer are provided. One method includes detecting defects on a wafer by applying a hot threshold to output generated for the wafer by a detector of an inspection subsystem such that at least a majority of the detected defects include nuisance defects and determining locations of the detected defects with respect to design information for the wafer. In addition, the method includes stacking information for the detected defects based on the determined locations relative to a structure on the wafer such that the detected defects having the same locations relative to the structure are coincident with each other in results of the stacking. The method further includes identifying a source of the nuisance defects based on the results of the stacking.