Abstract: A profile model to characterize a structure to be examined using optical metrology is evaluated by displaying a set of profile parameters that characterizes the profile model. Each profile parameter has a range of values for the profile parameter. For each profile parameter having a range of values, an adjustment tool is displayed for selecting a value for the profile parameter within the range of values. A measured diffraction signal, which was measured using an optical metrology tool, is displayed. A simulated diffraction signal, which was generated based on the values of the profile parameters selected using the adjustment tools for the profile parameters, is displayed. The simulated diffraction signal is overlaid with the measured diffraction signal.

Abstract: Metrology data from a semiconductor treatment system is transformed using multivariate analysis. In particular, a set of metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. One or more essential variables for the obtained set of metrology data is determined using multivariate analysis. A first metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. The first obtained metrology data is not one of the metrology data in the set of metrology data earlier obtained. The first metrology data is transformed into a second metrology data using the one or more of the determined essential variables.

Abstract: In processing requests for wafer structure profile determination from optical metrology measurements, a plurality of measured diffraction signal of a plurality of structures formed on one or more wafers is obtained. The plurality of measured diffraction signals is distributed to a plurality of instances of a profile search module. The plurality of instances of the profile search model is activated in one or more processing threads of one or more computer systems. The plurality of measured diffraction signals is processed in parallel using the plurality of instances of the profile search module to determine profiles of the plurality of structures corresponding to the plurality of measured diffraction signals.

Abstract: The profile of a structure having a region with a spatially varying property is modeled using an optical metrology model. A set of profile parameters is defined for the optical metrology model to characterize the profile of the structure. A set of layers is defined for a portion the optical metrology model that corresponds to the region of the structure with the spatially varying property, each layer having a defined height and width. For each layer, a mathematic function that varies across at least a portion of the width of the layer is defined to characterize the spatially varying property within a corresponding layer in the region of the structure.

Abstract: A structure formed on a semiconductor wafer can be examined using a support vector machine. A profile model of the structure is obtained. The profile model is defined by profile parameters that characterize the geometric shape of the structure. A set of values for the profile parameters is obtained. A set of simulated diffraction signals is generated using the set of values for the profile parameters, each simulated diffraction signal characterizing the behavior of light diffracted from the structure. The support vector machine is trained using the set of simulated diffraction signals as inputs to the support vector machine and the set of values for the profile parameters as expected outputs of the support vector machine. A measured diffraction signal off the structure is obtained. The measured diffraction signal is inputted into the trained support vector machine. Values of profile parameters of the structure are obtained as an output from the trained support vector machine.

Abstract: A profile model for use in optical metrology of structures in a wafer is selected, the profile model having a set of geometric parameters associated with the dimensions of the structure. The set of geometric parameters is selected to a set of optimization parameters. The number of optimization parameters within the set of optimization parameters is less than the number of geometric parameters within the set of geometric parameters. A set of selected optimization parameters is selected from the set of optimization parameters. The parameters of the set of selected geometric parameters are used as parameters of the selected profile model. The selected profile model is tested against one or more termination criteria.

Abstract: An optical metrology model is created for a patterned structure formed on a semiconductor wafer. The optical metrology model has profile parameters, material refraction parameters, and metrology device parameters. Ranges of values for the parameters are defined. One or more measured diffraction signals of the patterned structure are obtained. The optical metrology model is optimized to obtain an optimized optical metrology model using the defined ranges of values defined and the one or more obtained measured diffraction signals of the patterned structure. For at least one parameter from amongst the material refraction parameters and the metrology device parameters, the at least one parameter is set to a fixed value within the range of values for the at least one parameter. At least one profile parameter of the patterned structure is determined using the optimized optical metrology model and the fixed value for the at least one parameter.

Abstract: A structure formed on a semiconductor wafer can be examined using a support vector machine. A profile model is defined by profile parameters that characterize the geometric shape of the structure. A training set of values for the profile parameters is obtained. A training set of simulated diffraction signals is generated using the training set of values for the profile parameters. The support vector machine is trained using the training set of values for the profile parameters. A simulated diffraction signal is generated using a set of values for the profile parameters as inputs to the trained support vector machine. A measured diffraction signal is compared to the simulated diffraction signal. When the signals match within one or more matching criteria, values of profile parameters of the structure are determined to be the set of values for the profile parameters used to generate the simulated diffraction signal.

Abstract: Specific wavelengths to use in optical metrology of an integrated circuit can be selected using one or more selection criteria and termination criteria. Wavelengths are selected using the selection criteria, and the selection of wavelengths is iterated until the termination criteria are met.

Abstract: To determine one or more features of an in-die structure on a semiconductor wafer, a correlation is determined between one or more features of a test structure to be formed on a test pad and one or more features of a corresponding in-die structure. A measured diffraction signal measured off the test structure is obtained. One or more features of the test structure are determined using the measured diffraction signal. The one or more features of the in-die structure are determined based on the one or more determined features of the test structure and the determined correlation.

Abstract: A system to process requests for wafer structure profile determination from optical metrology measurements off a plurality of structures formed on one or more wafer includes a diffraction signal processor, a diffraction signal distributor, and a plurality of profile search servers. The diffraction signal processor is configured to obtain a plurality of measured diffraction signals of the plurality of structures. The diffraction signal distributor is coupled to the diffraction signal processor. The diffraction signal processor is configured to transmit the plurality of measured diffraction signals to the diffraction signal distributor. The plurality of profile search servers is coupled to the diffraction signal distributor. The diffraction signal distributor is configured to distribute the plurality of measured diffraction signals to the plurality of profile search servers.

Abstract: Metrology data from a semiconductor treatment system is transformed using multivariate analysis. In particular, a set of metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. One or more essential variables for the obtained set of metrology data is determined using multivariate analysis. A first metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. The first obtained metrology data is not one of the metrology data in the set of metrology data earlier obtained. The first metrology data is transformed into a second metrology data using the one or more of the determined essential variables.

Abstract: An optical metrology model for a structure to be formed on a wafer is developed by characterizing a top-view profile and a cross-sectional view profile of the structure using profile parameters. The profile parameters of the top-view profile and the cross-sectional view profile are integrated together into the optical metrology model. The profile parameters of the optical metrology model are saved.

Abstract: A structure formed on a semiconductor wafer is examined by obtaining a first diffraction signal measured from the structure using an optical metrology device. A first profile is obtained from a first machine learning system using the first diffraction signal obtained as an input to the first machine learning system. The first machine learning system is configured to generate a profile as an output for a diffraction signal received as an input. A second profile is obtained from a second machine learning system using the first profile obtained from the first machine learning system as an input to the second machine learning system. The second machine learning system is configured to generate a diffraction signal as an output for a profile received as an input. The first and second profiles include one or more parameters that characterize one or more features of the structure.

Abstract: An optical metrology system includes a photometric device with a source configured to generate and direct light onto a structure, and a detector configured to detect light diffracted from the structure and to convert the detected light into a measured diffraction signal. A processing module of the optical metrology system is configured to receive the measured diffraction signal from the detector to analyze the structure. The optical metrology system also includes a generic interface disposed between the photometric device and the processing module. The generic interface is configured to provide the measured diffraction signal to the processing module using a standard set of signal parameters. The standard set of signal parameters includes a reflectance parameter, a first polarization parameter, a second polarization parameter, and a third polarization parameter.

Abstract: The profile of a single feature formed on a wafer can be determined by obtaining an optical signature of the single feature using a beam of light focused on the single feature. The obtained optical signature can then be compared to a set of simulated optical signatures, where each simulated optical signature corresponds to a hypothetical profile of the single feature and is modeled based on the hypothetical profile.

Abstract: A structure formed on a semiconductor wafer can be examined using a support vector machine. A profile model of the structure is obtained. The profile model is defined by profile parameters that characterize the geometric shape of the structure. A set of values for the profile parameters is obtained. A set of simulated diffraction signals is generated using the set of values for the profile parameters, each simulated diffraction signal characterizing the behavior of light diffracted from the structure. The support vector machine is trained using the set of simulated diffraction signals as inputs to the support vector machine and the set of values for the profile parameters as expected outputs of the support vector machine. A measured diffraction signal off the structure is obtained. The measured diffraction signal is inputted into the trained support vector machine. Values of profile parameters of the structure are obtained as an output from the trained support vector machine.

Abstract: A structure formed on a semiconductor wafer can be examined using a support vector machine. A profile model of the structure is obtained. The profile model is defined by profile parameters that characterize the geometric shape of the structure. A training set of values for the profile parameters is obtained. A training set of simulated diffraction signals is generated using the training set of values for the profile parameters, each simulated diffraction signal characterizing the behavior of light diffracted from the structure. The support vector machine is trained using the training set of values for the profile parameters as inputs to the support vector machine and the training set of simulated diffraction signals as expected outputs of the support vector machine. A measured diffraction signal off the structure is obtained. A simulated diffraction signal is generated using a set of values for the profile parameters as inputs to the trained support vector machine.

Abstract: A fabrication tool can be controlled using a support vector machine. A profile model of the structure is obtained. The profile model is defined by profile parameters that characterize the geometric shape of the structure. A set of values for the profile parameters is obtained. A set of simulated diffraction signals is generated using the set of values for the profile parameters, each simulated diffraction signal characterizing the behavior of light diffracted from the structure. The support vector machine is trained using the set of simulated diffraction signals as inputs to the support vector machine and the set of values for the profile parameters as expected outputs of the support vector machine. After the support vector machine has been trained, a fabrication process is performed using the fabrication tool to fabricate the structure on the wafer. A measured diffraction signal off the structure is obtained. The measured diffraction signal is inputted into the trained support vector machine.

Abstract: Split machine learning systems can be used to generate an output for an input. When the input is received, a determination is made as to whether the input is within a first, second, or third range of values. If the input is within the first range, the output is generated using a first machine learning system. If the input is within the second range, the output is generated using a second machine learning system. If the input is within the third range, the output is generated using the first and second machine learning systems.