A semiconductor device metrology including creating a time-domain representation of wavelength-domain measurement data of light reflected by a patterned structure of a semiconductor device, selecting a relevant and irrelevant portion of the time-domain representation, and determining one or more measurements of one or more parameters of interest of the patterned structure by performing model-based processing using the relevant portion of the time-domain representation.

Provided is a process proximity effect correction method capable of efficiently improving the dispersion of patterns. There is a process proximity effect correction method according to some embodiments, the process proximity effect correction method of a process proximity effect correction device for performing process proximity effect correction (PPC) of a plurality of patterns using a machine learning module executed by a processor, comprising: training a sensitivity model by inputting a layout image of the plurality of patterns and a layout critical dimension (CD) of the plurality of patterns into the machine learning module; estimating an after cleaning inspection critical dimension (ACI-CD) sensitivity prediction value of the plurality of patterns by inferring an ACI-CD prediction value of the plurality of patterns; and determining a correction rate of the layout CD of the plurality of patterns using the estimated sensitivity prediction value.

A method and apparatus for training a defect location prediction model to predict a defect for a substrate location is disclosed. A number of datasets having data regarding process-related parameters for each location on a set of substrates is received. Some of the locations have partial datasets in which data regarding one or more process-related parameters is absent. The datasets are processed to generate multiple parameter groups having data for different sets of process-related parameters. For each parameter group, a sub-model of the defect location prediction model is created based on the corresponding set of process-related parameters and trained using data from the parameter group. A trained sub-model(s) may be selected based on process-related parameters available in a candidate dataset and a defect prediction may be generated for a location associated with the candidate dataset using the selected sub-model.

A method of determining a measurement recipe for measurement of in-die targets located within one or more die areas of an exposure field. The method includes obtaining first measurement data relating to measurement of a plurality of reference targets and second measurement data relating to measurement of a plurality of in-die targets, the targets having respective different overlay biases and measured using a plurality of different acquisition settings for acquiring the measurement data. One or more machine learning models are trained using the first measurement data to obtain a plurality of candidate measurement recipes, wherein the candidate measurement recipes include a plurality of combinations of a trained machine learned model and a corresponding acquisition setting; and a preferred measurement recipe is determined from the candidate measurement recipes using the second measurement data.

One or more optical images of a portion of a semiconductor wafer are obtained. The one or more optical images show a first structure in a first process layer and a second structure in a second process layer. The one or more optical images are provided to a machine-learning model trained to estimate an overlay offset between the first structure and the second structure. An estimated overlay offset between the first structure and the second structure is obtained from the machine-learning model.

A method, computer program and associated apparatuses for metrology. The method includes determining a reconstruction recipe describing at least nominal values for use in a reconstruction of a parameterization describing a target. The method includes obtaining first measurement data relating to measurements of a plurality of targets on at least one substrate, the measurement data relating to one or more acquisition settings and performing an optimization by minimizing a cost function which minimizes differences between the first measurement data and simulated measurement data based on a reconstructed parameterization for each of the plurality of targets. A constraint on the cost function is imposed based on a hierarchical prior. Also disclosed is a hybrid model method comprising obtaining a coarse model operable to provide simulated coarse data; and training a data driven model to correct the simulated coarse data so as to determine simulated data for use in reconstruction.

Systems, apparatuses, and methods are provided for correcting the detected positions of alignment marks disposed on a substrate and aligning the substrate using the corrected data to ensure accurate exposure of one or more patterns on the substrate. An example method can include receiving measurement data indicative of an interference between light diffracted from a plurality of alignment marks disposed on a substrate or reflected from the substrate. The example method can further include determining substrate deformation data based on the measurement data. The example method can further include determining alignment mark deformation data based on the measurement data. The alignment mark deformation data can include alignment mark deformation spectral pattern data, alignment mark deformation amplitude data, and alignment mark deformation offset data. Subsequently, the example method can include determining a correction to the measurement data based on the substrate deformation data and the alignment mark deformation data.

In the semiconductor industry, lithography refers to a manufacturing process in which light is projected through a geometric design on a mask to illuminate the design on a semiconductor wafer. The wafer has a light-sensitive material (i.e. resist) on its surface which, when illuminated by the light, causes the design to be etched onto the wafer. However, this lithography process does not perfectly transfer the design to the wafer, particularly because some diffracted light will inevitably distort the pattern etched onto the wafer (i.e. the resist image). To address this issue in lithography, an inverse lithography technology has been developed which optimizes the mask to match the desired shapes on the wafer. The present disclosure improves current inverse lithography technology by employing machine learning for mask optimization.

Embodiments of the present disclosure provide systems and methods for enhancing the semiconductor manufacturing yield. Embodiments of the present disclosure provide a yield improvement system. The system comprises a training tool configured to generate training data based on receipt of one or more verified results of an inspection of a first substrate. The system also comprises a point determination tool configured to determine one or more regions on a second substrate to inspect based on the training data, weak point information for the second substrate, and an exposure recipe for a scanner of the second substrate.

A processor-implemented method including generating a first corrected result image of a first desired pattern image using a backward correction neural network provided an input based on the first desired pattern image, the backward correction neural network performing a backward correction of a first process, generating a first simulated result image using a forward simulation neural network based on the first corrected result image, the forward simulation neural network performing a forward simulation of a performance of the first process, and updating the first corrected result image so that an error between the first desired pattern image and the first simulated result image is reduced.