Abstract: A metrology system may include a spectroscopic metrology sub-system and a controller, the controller including one or more processors configured to execute program instructions configured to cause the one or more processors to: generate a tool-induced shift (TIS) model of a training sample by the metrology sub-system comprising: receiving training data from metrology measurements of the training sample, the training data comprising spectral data associated with at least one off-diagonal Mueller matrix element generated by one or more first measurements of the training sample at a first azimuthal angle and one or more second measurements of the training sample at a second azimuthal angle, deriving overlay spectra data and TIS spectra data from the training data, decomposing the overlay spectra data and the TIS spectra data, and inferring a TIS signature for the training sample; and to remove the TIS signature from a test sample.

Abstract: Methods and systems for measurement of wafer tilt and overlay are described herein. In some embodiments, the measurements are based on the value of an asymmetry response metric and known wafer statistics. Spectral measurements are performed at two different azimuth angles, preferably separated by one hundred eighty degrees. A sub-range of wavelengths is selected with significant signal sensitivity to wafer tilt or overlay. An asymmetry response metric is determined based on a difference between the spectral signals measured at the two different azimuth angles within the selected sub-range of wavelengths. The value of the asymmetry response metric is mapped to an estimated value of wafer tilt or overlay. In some other embodiments, the measurement of wafer tilt or overlay is based on a trained measurement model. Training data may be programmed or determined based on one or more asymmetry response metrics at two different azimuth angles.

Abstract: A metrology module includes an estimation model that is configured to provide an estimation of independent overlay with tool induced shift on received wafers based on only one azimuth angle spectra. The estimation model can use at least one machine learning algorithm. The estimation model can be derived by the machine learning algorithm applied to calculated training data based on a first training sample set from initial metrology measurements and an additional tool induced shift training sample.

Abstract: Methods and systems for determining information for a specimen are provided. One system includes an output acquisition subsystem configured to generate output for a specimen at one or more target locations on the specimen and one or more temperature sensors configured to measure one or more temperatures within the system. The system also includes a deep learning model configured for predicting error in at least one of the one or more target locations based on at least one of the one or more measured temperatures input to the deep learning model by the computer subsystem. The computer subsystem is configured for determining a corrected target location for the at least one of the one or more target locations by applying the predicted error to the at least one of the one or more target locations.

Abstract: Methods and systems for measurements of semiconductor structures based on a trained whole wafer measurement model that is valid for all possible measurement locations on a wafer are described herein. A whole wafer measurement model is trained based on Design Of Experiments (DOE) measurement data collected across an entire wafer or set of wafers subjected to the same set of process steps. By employing DOE measurement data across an entire wafer or set of wafers, information about process behavior across the entire wafer is implicitly incorporated into the trained model at all locations across the wafer under measurement. The model training process encourages physical process behavior, which reduces the degrees of freedom of the underlying model, breaks correlations between parameters, and reduces the dimension of the solution space. As a result, measurement performance and robustness is improved.

Abstract: A characterization system is disclosed. The system may include one or more controllers including one or more processors configured to execute a set of program instructions stored in memory. The controller may be configured to train a machine learning-based characterization library based on a set of training data. The controller may be configured to generate one or more characterization measurements using the trained machine learning-based characterization library based on the real-time characterization data associated with the one or more samples from the characterization sub-system. The controller may be configured to determine one or more additional characterization measurements based on a non-machine learning-based technique. The controller may be configured to compare the one or more characterization measurements and the one or more additional characterization measurements to monitor a measurement uncertainty of the machine learning-based characterization library.

Abstract: Methods and systems for determining information for a specimen are provided. One system includes an output acquisition subsystem configured to generate output for a specimen at one or more target locations on the specimen and one or more temperature sensors configured to measure one or more temperatures within the system. The system also includes a deep learning model configured for predicting error in at least one of the one or more target locations based on at least one of the one or more measured temperatures input to the deep learning model by the computer subsystem. The computer subsystem is configured for determining a corrected target location for the at least one of the one or more target locations by applying the predicted error to the at least one of the one or more target locations.

Abstract: A self-calibrating overlay metrology system may receive device overlay data for a device targets on a sample from an overlay metrology tool, determine preliminary device overlay measurements for the device targets including device-scale features using an overlay recipe with the device overlay data as inputs, receive assist overlay data for one or more assist targets on the sample including device-scale features from the overlay metrology tool, where at least one of the one or more assist targets has a programmed overlay offset of a selected value along a particular measurement direction, determine self-calibrating assist overlay measurements for the one or more assist targets based on the assist overlay data, where the self-calibrating assist overlay measurements are linearly proportional to overlay on the sample, and generate corrected overlay measurements for the device targets by adjusting the preliminary device overlay measurements based on the self-calibrating assist overlay measurements.

Abstract: A metrology module includes an estimation model that is configured to provide an estimation of independent overlay with tool induced shift on received wafers based on only one azimuth angle spectra. The estimation model can use at least one machine learning algorithm. The estimation model can be derived by the machine learning algorithm applied to calculated training data based on a first training sample set from initial metrology measurements and an additional tool induced shift training sample.

Abstract: A self-calibrating overlay metrology system may receive device overlay data for a device targets on a sample from an overlay metrology tool, determine preliminary device overlay measurements for the device targets including device-scale features using an overlay recipe with the device overlay data as inputs, receive assist overlay data for one or more assist targets on the sample including device-scale features from the overlay metrology tool, where at least one of the one or more assist targets has a programmed overlay offset of a selected value along a particular measurement direction, determine self-calibrating assist overlay measurements for the one or more assist targets based on the assist overlay data, where the self-calibrating assist overlay measurements are linearly proportional to overlay on the sample, and generate corrected overlay measurements for the device targets by adjusting the preliminary device overlay measurements based on the self-calibrating assist overlay measurements.

Abstract: A self-calibrating overlay metrology system may receive device overlay data from device targets on a sample, determine preliminary device overlay measurements for the device targets including device-scale features using an overlay recipe with the device overlay data as inputs, receive assist overlay data from sets of assist targets on the sample including device-scale features, where a particular set of assist targets includes one or more target pairs formed with two overlay targets having programmed overlay offsets of a selected value with opposite signs along a particular measurement direction.

Abstract: An overlay metrology system may receive overlay data for in-die overlay targets within various fields on a skew training sample from one or more overlay metrology tools, wherein the in-die overlay targets within the fields have a range programmed overlay offsets, wherein the fields are fabricated with a range of programmed skew offsets. The system may further generate asymmetric target signals for the in-die overlay targets using an asymmetric function providing a value of zero when physical overlay is zero and a sign indicative of a direction of physical overlay. The system may further generate corrected overlay offsets for the in-die overlay targets on the asymmetric target signals, generate self-calibrated overlay offsets for the in-die overlay targets based on the programmed overlay offsets and the corrected overlay offsets, generate a trained overlay recipe, and generate overlay measurements for in-die overlay targets on additional samples using the trained overlay recipe.

Abstract: An overlay metrology system may receive overlay data for in-die overlay targets within various fields on a skew training sample from one or more overlay metrology tools, wherein the in-die overlay targets within the fields have a range programmed overlay offsets, wherein the fields are fabricated with a range of programmed skew offsets. The system may further generate asymmetric target signals for the in-die overlay targets using an asymmetric function providing a value of zero when physical overlay is zero and a sign indicative of a direction of physical overlay. The system may further generate corrected overlay offsets for the in-die overlay targets on the asymmetric target signals, generate self-calibrated overlay offsets for the in-die overlay targets based on the programmed overlay offsets and the corrected overlay offsets, generate a trained overlay recipe, and generate overlay measurements for in-die overlay targets on additional samples using the trained overlay recipe.

Abstract: Methods and systems for measurement of wafer tilt and overlay are described herein. In some embodiments, the measurements are based on the value of an asymmetry response metric and known wafer statistics. Spectral measurements are performed at two different azimuth angles, preferably separated by one hundred eighty degrees. A sub-range of wavelengths is selected with significant signal sensitivity to wafer tilt or overlay. An asymmetry response metric is determined based on a difference between the spectral signals measured at the two different azimuth angles within the selected sub-range of wavelengths. The value of the asymmetry response metric is mapped to an estimated value of wafer tilt or overlay. In some other embodiments, the measurement of wafer tilt or overlay is based on a trained measurement model. Training data may be programmed or determined based on one or more asymmetry response metrics at two different azimuth angles.

Abstract: Methods and systems for estimating a value of a quality metric indicative of one or more performance characteristics of a semiconductor measurement are presented herein. The value of the quality metric is normalized to ensure applicability across a broad range of measurement scenarios. In some embodiments, a value of a quality metric is determined for each measurement sample during measurement inference. In some embodiments, a trained quality metric model is employed to determine the uncertainty of defect classification. In some embodiments, a trained quality metric model is employed to determine the uncertainty of estimated parameters of interest, such as geometric, dispersion, process, and electrical parameters. In some examples, a quality metric is employed as a filter to detect measurement outliers. In some other examples, a quality metric is employed as a trigger to adjust a semiconductor process.

Abstract: A self-calibrating overlay metrology system may receive device overlay data from device targets on a sample, determine preliminary device overlay measurements for the device targets including device-scale features using an overlay recipe with the device overlay data as inputs, receive assist overlay data from sets of assist targets on the sample including device-scale features, where a particular set of assist targets includes one or more target pairs formed with two overlay targets having programmed overlay offsets of a selected value with opposite signs along a particular measurement direction.

Abstract: Methods and systems for estimating a value of a quality metric indicative of one or more performance characteristics of a semiconductor measurement are presented herein. The value of the quality metric is normalized to ensure applicability across a broad range of measurement scenarios. In some embodiments, a value of a quality metric is determined for each measurement sample during measurement inference. In some embodiments, a trained quality metric model is employed to determine the uncertainty of defect classification. In some embodiments, a trained quality metric model is employed to determine the uncertainty of estimated parameters of interest, such as geometric, dispersion, process, and electrical parameters. In some examples, a quality metric is employed as a filter to detect measurement outliers. In some other examples, a quality metric is employed as a trigger to adjust a semiconductor process.