Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images a specimen, and a controller communicatively coupled to the characterization sub-system. The controller may be configured to: receive from the characterization sub-system one or more training images of one or more defects of a training specimen; generate one or more augmented images of the one or more defects of the training specimen; generate a machine learning classifier based on the one or more augmented images of the one or more defects of the training specimen; receive from the characterization sub-system one or more target images of one or more target features of a target specimen; and determine one or more defects of the one or more target features with the machine learning classifier.

Abstract: Process window qualification (PWQ) layouts can be used to determine a presence of a pattern anomaly associated with the pattern, patterning process, or patterning apparatus. For example, a modulated die or field can be compared to a slightly lower offset modulated die or field. In another example, the high to low corners for a particular condition or combination of conditions are compared. In yet another example, process modulation parameters can be used to estimate criticality of particular weak points of interest.

Abstract: Methods and systems for determining information for a specimen are provided. One system includes a computer subsystem and one or more components executed by the computer subsystem. The one or more components include a deep learning model configured for denoising an image of a specimen generated by an imaging subsystem. The computer subsystem is configured for determining information for the specimen from the denoised image.

Abstract: A method of defect discovery can include providing a nuisance bin in a nuisance filter, partitioning the defect population into a defect population partition, segmenting the defect population partition into a defect population segment, selecting from the defect population segment a selected set of defects, computing one or more statistics of the signal attributes of the defects in the defect population segment, replicating the selected set of defects to yield generated defects, shifting the generated defects outside of the defect population segment, creating a training set, and training a binary classifier. This method can be operated on a system. The method can enable a semiconductor manufacturer to determine more accurately the presence of defects that would otherwise have gone unnoticed.

Abstract: Methods and systems for improved detection and classification of defects of interest (DOI) is realized based on values of one or more automatically generated attributes derived from images of a candidate defect. Automatically generated attributes are determined by iteratively training, reducing, and retraining a deep learning model. The deep learning model relates optical images of candidate defects to a known classification of those defects. After model reduction, attributes of the reduced model are identified which strongly relate the optical images of candidate defects to the known classification of the defects. The reduced model is subsequently employed to generate values of the identified attributes associated with images of candidate defects having unknown classification. In another aspect, a statistical classifier is employed to classify defects based on automatically generated attributes and attributes identified manually.

Abstract: Machine learning approaches provide additional information about semiconductor wafer inspection stability issues that makes it possible to distinguish consequential process variations like process excursions from minor process variations that are within specification. The effect of variable defect of interest (DOI) capture rates in the inspection result and the effect of variable defect count on the wafer can be monitored independently.

Abstract: Wafer inspection with stable nuisance rates and defect of interest capture rates are disclosed. This technique can be used for discovery of newly appearing defects that occur during the manufacturing process. Based on a first wafer, defects of interest are identified based on the classified filtered inspection results. For each remaining wafer, the defect classifier is updated and defects of interest in the next wafer are identified based on the classified filtered inspection results.

Abstract: A system for defect review and classification is disclosed. The system may include a controller, wherein the controller may be configured to receive one or more training images of a specimen. The one or more training images including a plurality of training defects. The controller may be further configured to apply a plurality of difference filters to the one or more training images, and receive a signal indicative of a classification of a difference filter effectiveness metric for at least a portion of the plurality of difference filters. The controller may be further configured to generate a deep learning network classifier based on the received classification and the attributes of the plurality of training defects. The controller may be further configured to extract convolution layer filters of the deep learning network classifier, and generate one or more difference filter recipes based on the extracted convolution layer filters.

Abstract: Defect location accuracy can be increased using shape based grouping with pattern-based defect centering. Design based grouping of defects on a wafer can be performed. A spatial distribution of the defects around at least one structure on the wafer, such as a predicted hot spot, can be determined. At least one design based defect property for a location around the structure can be determined. The defects within an x-direction threshold and a y-direction threshold of the structure may be prioritized.

Abstract: Systems and methods for detecting defect candidates on a specimen are provided. One method includes, after scanning of at least a majority of a specimen is completed, applying one or more segmentation methods to at least a substantial portion of output generated during the scanning thereby generating two or more segments of the output. The method also includes separately detecting outliers in the two or more segments of the output. In addition, the method includes detecting defect candidates on the specimen by applying one or more predetermined criteria to results of the separately detecting to thereby designate a portion of the detected outliers as the defect candidates.

Abstract: To evaluate a semiconductor-fabrication process, a semiconductor wafer is obtained that includes die grouped into modulation sets. Each modulation set is fabricated using distinct process parameters. The wafer is optically inspected to identify defects. A nuisance filter is trained to classify the defects as DOI or nuisance defects. Based on results of the training, a first, preliminary process window for the wafer is determined and die structures having DOI are identified in a first group of modulation sets bordering the first process window. The trained nuisance filter is applied to the identified defects to determine a second, revised process window for the wafer. A third, further revised process window for the wafer is determined based on SEM images of specified care areas in one or more modulation sets within the second, revised process window. A report is generated that specifies the third process window.

Abstract: A system, method, and non-transitory computer readable medium are provided for training and applying defect classifiers in wafers having deeply stacked layers. In use, a plurality of images generated by an inspection system for a location of a defect detected on a wafer by the inspection system are acquired. The location on the wafer is comprised of a plurality of stacked layers, and each image of the plurality of images is generated by the inspection system at the location using a different focus setting. Further, a classification of the defect is determined, utilizing the plurality of images.

Abstract: To evaluate a semiconductor-fabrication process, a semiconductor wafer is obtained that includes die grouped into modulation sets. Each modulation set is fabricated using distinct process parameters. The wafer is optically inspected to identify defects. A nuisance filter is trained to classify the defects as DOI or nuisance defects. Based on results of the training, a first, preliminary process window for the wafer is determined and die structures having DOI are identified in a first group of modulation sets bordering the first process window. The trained nuisance filter is applied to the identified defects to determine a second, revised process window for the wafer. A third, further revised process window for the wafer is determined based on SEM images of specified care areas in one or more modulation sets within the second, revised process window. A report is generated that specifies the third process window.

Abstract: Machine learning approaches provide additional information about semiconductor wafer inspection stability issues that makes it possible to distinguish consequential process variations like process excursions from minor process variations that are within specification. The effect of variable defect of interest (DOI) capture rates in the inspection result and the effect of variable defect count on the wafer can be monitored independently.

Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images a specimen, and a controller communicatively coupled to the characterization sub-system. The controller may be configured to: receive from the characterization sub-system one or more training images of one or more defects of a training specimen; generate one or more augmented images of the one or more defects of the training specimen; generate a machine learning classifier based on the one or more augmented images of the one or more defects of the training specimen; receive from the characterization sub-system one or more target images of one or more target features of a target specimen; and determine one or more defects of the one or more target features with the machine learning classifier.

Abstract: Defects of interest can be captured by a classifier. Images of a semiconductor wafer can be received at a deep learning classification module. These images can be sorted into soft decisions with the deep learning classification module. A class of the defect of interest for an image can be determined from the soft decisions. The deep learning classification module can be in electronic communication with an optical inspection system or other types of semiconductor inspection systems.

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: Systems and methods for detecting defect candidates on a specimen are provided. One method includes, after scanning of at least a majority of a specimen is completed, applying one or more segmentation methods to at least a substantial portion of output generated during the scanning thereby generating two or more segments of the output. The method also includes separately detecting outliers in the two or more segments of the output. In addition, the method includes detecting defect candidates on the specimen by applying one or more predetermined criteria to results of the separately detecting to thereby designate a portion of the detected outliers as the defect candidates.

Abstract: Methods and systems for improved detection and classification of defects of interest (DOI) is realized based on values of one or more automatically generated attributes derived from images of a candidate defect. Automatically generated attributes are determined by iteratively training, reducing, and retraining a deep learning model. The deep learning model relates optical images of candidate defects to a known classification of those defects. After model reduction, attributes of the reduced model are identified which strongly relate the optical images of candidate defects to the known classification of the defects. The reduced model is subsequently employed to generate values of the identified attributes associated with images of candidate defects having unknown classification. In another aspect, a statistical classifier is employed to classify defects based on automatically generated attributes and attributes identified manually.

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.