Abstract: A method of processing a substrate includes subjecting a substrate to processing that modifies a thickness of an outer layer of the substrate, measuring a spectrum of light reflected from the substrate during processing, reducing the dimensionality of the measured spectrum to generate a plurality of component values, generating a characterizing value using an artificial neural network, and determining at least one of whether to halt processing of the substrate or an adjustment for a processing parameter based on the characterizing value. The artificial neural network has a plurality of input nodes to receive the plurality of component values, an output node to output the characterizing value, and a plurality of hidden nodes connecting the input nodes to the output node.

Abstract: A chemical mechanical polishing apparatus includes a platen to hold a polishing pad, a carrier laterally movable by an actuator across the polishing pad to hold a substrate against a polishing surface of the polishing pad during a polishing process, a thermal control system including a plurality of independently controllable heaters and coolers to independently control temperatures of a plurality of zones on the polishing pad, and a controller configured to cause the thermal control system to generate a first zone having a first temperature and a second zone having a different second temperature on the polishing pad.

Abstract: A chemical mechanical polishing apparatus includes a rotatable platen to hold a polishing pad, a rotatable carrier to hold a substrate against a polishing surface of the polishing pad during a polishing process, a polishing liquid supply port to supply a polishing liquid to the polishing surface, a thermal control system including a movable nozzle to spray a medium onto the polishing surface to adjust a temperature of a zone on the polishing surface, an actuator to move the nozzle radially relative to an axis of rotation of the platen, and a controller configured to coordinate dispensing of the medium from the nozzle with motion of the nozzle across the polishing surface.

Abstract: Operating a substrate processing system includes receiving a plurality of sets of training data, storing a plurality of machine learning models, storing a plurality of physical process models, receiving a selection of a machine learning model from the plurality of machine learning models and a selection of a physical process model from the plurality of physical process models, generating an implemented machine learning model according to the selected machine learning model, calculating a characterizing value for each training spectrum in each set of training data thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra, training the implemented machine learning model using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and passing the trained machine learning model to a control system of the substrate processing system.

Abstract: An apparatus for chemical mechanical polishing includes a platen having a surface to support a polishing pad, a carrier head to hold a substrate against a polishing surface of the polishing pad, a pad conditioner to press an abrasive body against the polishing surface, an in-situ polishing pad monitoring system including an imager disposed above the platen to capture an image of the polishing pad, and a controller configured to receive the image from the monitoring system and generate a measure of polishing pad surface roughness based on the image. The controller can use machine-learning based image processing to generate the measure of surface roughness.

Abstract: A method of processing a substrate includes subjecting a substrate to processing that modifies a thickness of an outer layer of the substrate, measuring a spectrum of light reflected from the substrate during processing, reducing the dimensionality of the measured spectrum to generate a plurality of component values, generating a characterizing value using an artificial neural network, and determining at least one of whether to halt processing of the substrate or an adjustment for a processing parameter based on the characterizing value. The artificial neural network has a plurality of input nodes to receive the plurality of component values, an output node to output the characterizing value, and a plurality of hidden nodes connecting the input nodes to the output node.

Abstract: During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.

Abstract: A method of generating training spectra for training of a neural network includes generating a plurality of theoretically generated initial spectra from an optical model, sending the plurality of theoretically generated initial spectra to a feedforward neural network to generate a plurality of modified theoretically generated spectra, sending an output of the feedforward neural network and empirically collected spectra to a discriminatory convolutional neural network, determining that the discriminatory convolutional neural network does not discriminate between the modified theoretically generated spectra and empirically collected spectra, and thereafter, generating a plurality of training spectra from the feedforward neural network.

Abstract: A method of generating training spectra for training of a neural network includes measuring a first plurality of training spectra from one or more sample substrates, measuring a characterizing value for each training spectra of the plurality of training spectra to generate a plurality of characterizing values with each training spectrum having an associated characterizing value, measuring a plurality of dummy spectra during processing of one or more dummy substrates, and generating a second plurality of training spectra by combining the first plurality of training spectra and the plurality of dummy spectra, there being a greater number of spectra in the second plurality of training spectra than in the first plurality of training spectra. Each training spectrum of the second plurality of training spectra having an associated characterizing value.

Abstract: A chemical mechanical polishing apparatus includes a platen to support a polishing pad, and an in-situ acoustic emission monitoring system including an acoustic emission sensor supported by the platen, a waveguide configured to extending through at least a portion of the polishing pad, and a processor to receive a signal from the acoustic emission sensor. The in-situ acoustic emission monitoring system is configured to detect acoustic events caused by deformation of the substrate and transmitted through the waveguide, and the processor is configured to determine a polishing endpoint based on the signal.

Abstract: A method of operating a polishing system includes training a plurality of models using a machine learning algorithm to generate a plurality of trained models, each trained model configured to determine a characteristic value of a layer of a substrate based on a monitoring signal from an in-situ monitoring system of a semiconductor processing system, storing the plurality of trained models, receiving data indicating a characteristic of a substrate to be processed, selecting one of the plurality of trained models based on the data, and passing the selected trained model to the processing system.

Abstract: Operating a substrate processing system includes receiving a plurality of sets of training data, storing a plurality of machine learning models, storing a plurality of physical process models, receiving a selection of a machine learning model from the plurality of machine learning models and a selection of a physical process model from the plurality of physical process models, generating an implemented machine learning model according o the selected machine learning model, calculating a characterizing value for each training spectrum in each set of training data thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra, training the implemented machine learning model using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and passing the trained machine learning model to a control system of the substrate processing system.

Abstract: A method of polishing a layer on the substrate at a polishing station includes the actions of monitoring the layer during polishing at the polishing station with an in-situ monitoring system to generate a plurality of measured signals for a plurality of different locations on the layer; generating, for each location of the plurality of different locations, an estimated measure of thickness of the location, the generating including processing the plurality of measured signals through a neural network; and at least one of detecting a polishing endpoint or modifying a polishing parameter based on each estimated measure of thickness.

Abstract: A plurality of spectra reflected from one or more substrates at a plurality of different positions on the one or more substrates are represented in the form of a first matrix, and the first matrix is decomposed into products of at least two component matrixes of a first set of component matrixes. The dimensions of each of the at least two component matrixes is reduced to produce a second set of component matrixes containing the at least two matrixes with reduced dimensions.

Abstract: A method of processing a substrate includes subjecting a substrate to processing that modifies a thickness of an outer layer of the substrate, measuring a spectrum of light reflected from the substrate during processing, reducing the dimensionality of the measured spectrum to generate a plurality of component values, generating a characterizing value using an artificial neural network, and determining at least one of whether to halt processing of the substrate or an adjustment for a processing parameter based on the characterizing value. The artificial neural network has a plurality of input nodes to receive the plurality of component values, an output node to output the characterizing value, and a plurality of hidden nodes connecting the input nodes to the output node.

Abstract: A plurality of spectra reflected from one or more substrates at a plurality of different positions on the one or more substrates are represented in the form of a first matrix, and the first matrix is decomposed into products of at least two component matrixes of a first set of component matrixes. The dimensions of each of the at least two component matrixes is reduced to produce a second set of component matrixes containing the at least two matrixes with reduced dimensions.

Abstract: A plurality of spectra reflected from one or more substrates at a plurality of different positions on the one or more substrates are represented in the form of a first matrix, and the first matrix is decomposed into products of at least two component matrixes of a first set of component matrixes. The dimensions of each of the at least two component matrixes is reduced to produce a second set of component matrixes containing the at least two matrixes with reduced dimensions.

Abstract: A plurality of spectra reflected from one or more substrates at a plurality of different positions on the one or more substrates are represented in the form of a first matrix, and the first matrix is decomposed into products of at least two component matrixes of a first set of component matrixes. The dimensions of each of the at least two component matrixes is reduced to produce a second set of component matrixes containing the at least two matrixes with reduced dimensions.

Abstract: A method of controlling polishing includes polishing a region of a substrate at a first polishing rate, measuring a sequence of characterizing values for the region of the substrate during polishing with an in-situ monitoring system, determining a polishing rate adjustment for each of a plurality of adjustment times prior to a polishing endpoint time, and adjusting a polishing parameter to polish the substrate at a second polishing rate. The time period is greater than a period between the adjustment times and the projected time is before the polishing endpoint time. The second polishing rate is the first polishing rate as adjusted by the polishing rate adjustment.

Abstract: Among other things, a machine based method includes representing a plurality of spectra reflected from one or more substrates at a plurality of different positions on the one or more substrates in the form of a first matrix; decomposing, by one or more computers, the first matrix into products of at least two component matrixes of a first set of component matrixes; reducing dimensions of each of the at least two component matrixes to produce a second set of component matrixes containing the at least two matrixes with reduced dimensions; and generating, by the one or more computers, a second matrix by taking a product of the matrixes of the second set of component matrixes.