The present application discloses a dose mapper method, which includes: step 1: collecting critical dimension fingerprint of each tool and each mask and storing the critical dimension fingerprint in a database; step 2: before exposing a wafer, pre-selecting the tool and the mask to be used, selecting the corresponding critical dimension fingerprint from the database and combining the corresponding critical dimension fingerprint to form total critical dimension fingerprint; step 3: obtaining dose mapper data for exposure of the wafer according to the total critical dimension fingerprint; step 4: exposing the wafer, and correcting the exposure of the wafer according to the dose mapper data in an exposure process. The present application can quickly and easily generate a dose mapper data file, especially when there is a new tool or mask to be expanded, thus improving the efficiency of generating the dose mapper data file and improving the production capacity.

Combined electron beam overlay and scatterometry overlay targets include first and second periodic structures with gratings. Gratings in the second periodic structure can be positioned under the gratings of the first periodic structure or can be positioned between the gratings of the first periodic structure. These overlay targets can be used in semiconductor manufacturing.

An acoustic scatterometer has an acoustic source operable to project acoustic radiation onto a periodic structure and formed on a substrate. An acoustic detector is operable to detect the −1st acoustic diffraction order diffracted by the periodic structure and while discriminating from specular reflection (0th order). Another acoustic detector is operable to detect the +1st acoustic diffraction order diffracted by the periodic structure, again while discriminating from the specular reflection (0th order). The acoustic source and acoustic detector may be piezo transducers. The angle of incidence of the projected acoustic radiation and location of the detectors and are arranged with respect to the periodic structure and such that the detection of the −1st and +1st acoustic diffraction orders and discriminates from the 0th order specular reflection.

Techniques and systems for critical dimension metrology are disclosed. Critical parameters can be constrained with at least one floating parameter and one or more weight coefficients. A neural network is trained to use a model that includes a Jacobian matrix. During training, at least one of the weight coefficients is adjusted, a regression is performed on reference spectra, and a root-mean-square error between the critical parameters and the reference spectra is determined. The training may be repeated until the root-mean-square error is less than a convergence threshold.

A method for monitoring performance of a manufacturing process is described. The method includes receiving one or more input signals that convey information related to geometry of a substrate generated by the manufacturing process; and determining, with a prediction model, variation in the manufacturing process based on the one or more input signals. A method for predicting substrate geometry associated with a manufacturing process is also described. The method includes receiving input information including geometry information and manufacturing process information for a substrate; and predicting, using a machine learning prediction model, output substrate geometry based on the input information. The method may further include tuning the predicted output substrate geometry. The tuning includes comparing the output substrate geometry to corresponding physical substrate measurements and/or predictions from a different non-machine learning prediction model, generating a loss function based on the comparison, and optimizing the loss function.

A method for training a machine learning model to generate a predicted measured image, the method including obtaining (a) an input target image associated with a reference design pattern, and (b) a reference measured image associated with a specified design pattern printed on a substrate, wherein the input target image and the reference measured image are non-aligned images; and training, by a hardware computer system and using the input target image, the machine learning model to generate a predicted measured image.

A method of treating a surface of a reticle includes retrieving a reticle from a reticle library and transferring the reticle to a treatment device. The surface of the reticle is treated in the treatment device by irradiating the surface of the reticle with UV radiation while ozone fluid is over the surface of the reticle for a predetermined irradiation time. After the treatment, the reticle is transferred to an exposure device for lithography operation to generate a photo resist pattern on a wafer. A surface of the wafer is imaged to generate an image of the photo resist pattern on the wafer. The generated image of the photo resist pattern is analyzed to determine critical dimension uniformity (CDU) of the photo resist pattern. The predetermined irradiation time is increased if the CDU does not satisfy a threshold CDU.

A recipe selection method includes obtaining measurements from metrology targets, metrology targets positioned on a semiconductor substrate, obtaining measurements from in-device targets, in-device targets positioned on the semiconductor substrate, and determining a recipe for accurate metrology using both metrology target measurements and in-device metrology measurements.

Apparatus and method for measuring one or more parameters of a substrate (300) using source radiation emitted from a radiation source (100) and directed onto the substrate. The apparatus comprises at least one reflecting element (710a) and at least one detector (720, 721). The at least one reflecting element is configured to receive a reflected radiation resulting from reflection of the source radiation from the substrate and further reflect the reflected radiation into a further reflected radiation. The at least one detector is configured for measurement of the further reflected radiation for determination of at least an alignment of the source radiation and/or the substrate

A method for monitoring a process variation index includes operations of: obtaining a target parameter to be monitored and a reference parameter used to increase goodness of fit among structural parameters predicted by measuring a structure in a specific location of a wafer; obtaining a reference parameter set in a reference model; and calculating a process variation index capable of confirming a structural change of the structure according to a change in process conditions using the structural parameter and the reference parameter.