Abstract: A technique to generate predicted data for control or monitoring of a production process to improve a parameter of interest. Context data associated with operation of the production process is obtained. Metrology/testing is performed on the product of the production process, thereby obtaining performance data. A context-to-performance model is provided to generate predicted performance data based on labeling of the context data with performance data. This is an instance of semi-supervised learning. The context-to-performance model may include the learner that performs semi-supervised labeling. The context-to-performance model is modified using prediction information related to quality of the context data and/or performance data. Prediction information may include relevance information relating to relevance of the obtained context data and/or obtained performance data to the parameter of interest.

Abstract: A method for manufacturing or adjusting a reticle having a predetermined functionality, the method including obtaining a reticle having a first pattern, the first pattern representing a first functionality of structures provided to a substrate using the reticle, and patterning the reticle having the first pattern with a second pattern using a pattern generating tool, the combined first and second patterns having the predetermined functionality.

Abstract: A technique to generate predicted data for control or monitoring of a production process to improve a parameter of interest. Context data associated with operation of the production process is obtained. Metrology/testing is performed on the product of the production process, thereby obtaining performance data. A context-to-performance model is provided to generate predicted performance data based on labeling of the context data with performance data. This is an instance of semi-supervised learning. The context-to-performance model may include the learner that performs semi-supervised labeling. The context-to-performance model is modified using prediction information related to quality of the context data and/or performance data. Prediction information may include relevance information relating to relevance of the obtained context data and/or obtained performance data to the parameter of interest.

Abstract: A lithography system configured to apply a pattern to a substrate, the system including a lithography apparatus configured to expose a layer of the substrate according to the pattern, and a machine learning controller configured to control the lithography system to optimize a property of the pattern, the machine learning controller configured to be trained on the basis of a property measured by a metrology unit configured to measure the property of the exposed pattern in the layer and/or a property associated with exposing the pattern onto the substrate, and to correct lithography system drift by adjusting one or more selected from: the lithography apparatus, a track unit configured to apply the layer on the substrate for lithographic exposure, and/or a control unit configured to control an automatic substrate flow among the track unit, the lithography apparatus, and the metrology unit.

Abstract: A fault detection and classification method is disclosed that uses raw back-focal-plane image data of radiation from a substrate surface, detected by a scatterometer detector, to determine a variation in the raw data and correlate the variation in the raw data with a possible fault in a lithographic apparatus or a process that patterned the substrate surface. The correlation is carried out by comparing the variation in the raw data with known metrology data. Once a fault has been determined, a user may be notified of the fault.

Abstract: Two drive systems are responsible for moving a substrate beneath, for example, an illumination system or a measurement radiation beam. A first drive system drives a substrate in a X direction and a second drive system drives the substrate in a Y direction. In order to make a measurement of a feature of the substrate surface, targets are arranged in a lattice. Rather than having the lattice aligned with the X and Y directions such that only one drive system operates at a time to step between the targets, the lattice of targets is arranged at an angle with respect to the X and Y axes such that both drive systems operate simultaneously in order to move between the targets. The targets (or sub-targets within the targets) may also be arranged with respect to each other so as to save scribelane space and to create a most economical path between them.

Abstract: A fault detection and classification method is disclosed that uses raw back-focal-plane image data of radiation from a substrate surface, detected by a scatterometer detector, to determine a variation in the raw data and correlate the variation in the raw data with a possible fault in a lithographic apparatus or a process that patterned the substrate surface. The correlation is carried out by comparing the variation in the raw data with known metrology data. Once a fault has been determined, a user may be notified of the fault.

Abstract: A method is provided for compensating for the effect of flare lithographic apparatus. The method includes establishing a power spectral density (PSD) indicative of the spatial frequency of the stray radiation produced by a projection system, and determining, from the PSD, a modulation transfer function (MTF) relating the PSD to a pattern applied by a patterning device to take the effect of flare on the pattern image into account. The MTF is then used to determine the effect of flare on a critical dimension (CD) of the pattern image, and a relationship is established between any change in the CD of the pattern image and a change in the CD of the pattern. The patterning device may then be designed in such a way as to at least partially offset the effect of flare on the CD of the pattern image.