Predicting etch characteristics in thermal etching and atomic layer etching

Patent metadata

Field	Value
Publication number	US-2019340316-A1
Application number	US-201815970744-A
Country	US
Kind code	A1
Filing date	May 3, 2018
Priority date	May 3, 2018
Publication date	Nov 7, 2019
Grant date	—

Abstract

Etch in a thermal etch reaction is predicted using a machine learning model. Chemical characteristics of an etch process and associated energies in one or more reaction pathways of a given thermal etch reaction are identified using a quantum mechanical simulation. Labels indicative of etch characteristics may be associated with the chemical characteristics and associated energies of the given thermal etch reaction. The machine learning model can be trained using chemical characteristics and associated energies as independent variables and labels as dependent variables across many different etch reactions of different types. When chemical characteristics and associated energies for a new thermal etch reaction are provided as inputs in the machine learning model, the machine learning model can accurately predict etch characteristics of the new thermal etch reaction as outputs.

First claim

What is claimed is:

1 . A method for predicting an etch characteristic in a reaction between a surface layer and an etch precursor, the method comprising:
(a) identifying chemical characteristics and associated energies for one or more reaction pathways in a simulated reaction between the surface layer and the etch precursor using a quantum mechanical model; (b) providing the chemical characteristics and associated energies in the simulated reaction as inputs into a machine learning model; and (c) determining an etch characteristic for the simulated reaction between the surface layer and the etch precursor using the machine learning model.

2 . The method of claim 1 , wherein the chemical characteristics and associated energies for the one or more reaction pathways in the simulated reaction are determined using the quantum mechanical model configured with a selected surface representation of the surface layer and one or more selected initial conditions.

3 . The method of claim 2 , wherein the one or more selected initial conditions include a separation distance between the surface layer and the etch precursor at an onset of the simulated reaction, an orientation and/or direction of the surface layer and the etch precursor at the onset of the simulated reaction, a form of an initial chemical bridge between the surface layer and the etch precursor at the onset of the simulated reaction, an internal or kinetic energy of the etch precursor or the surface layer at the onset of the simulated reaction, or combinations thereof.

4 . The method of claim 2 , wherein the selected surface representation of the surface layer is selected from a group consisting of: a molecule, a small cluster of molecules, and a large cluster of molecules.

5 . The method of claim 1 , wherein the quantum mechanical model includes a density functional theory (DFT) model, a Hartree-Fock model, a semi-empirical model, or combinations thereof.

6 . The method of claim 1 , wherein the inputs include one or both of a temperature and pressure of the simulated reaction.

7 . The method of claim 1 , wherein the chemical characteristics include bonding configurations or molecular structures of one or more reaction intermediates and/or products produced in the one or more reaction pathways.

8 . The method of claim 7 , wherein the bonding configurations or molecular structures include one or more of a single bridge dimer, a double bridge dimer, a triple bridge dimer, and no dimer.

9 . The method of claim 1 , wherein the etch characteristic for the simulated reaction includes an etch rate of the surface layer.

10 . The method of claim 1 , wherein the etch characteristic for the simulated reaction includes an indication whether the surface layer is etched or not.

11 . The method of claim 1 , further comprising:
organizing the chemical characteristics and the associated energies for the one or more reaction pathways of the simulated reaction into a feature vector.

12 . The method of claim 1 , wherein the machine learning model was trained using a training set comprising a plurality of training set members, each training set member comprising (i) a feature vector containing chemical characteristics and associated energies for intermediates and/or products produced in one or more reaction pathways for a thermal etch reaction simulated by at least one quantum mechanical simulation, and (ii) a label representing a characteristic of the thermal etch reaction.

13 . The method of claim 12 , wherein each of the feature vectors includes a unique combination of: a specified etch precursor, a specified modified surface layer, a specified quantum mechanical model, a specified surface representation of the specified modified surface layer, and one or more specified initial conditions.

14 . The method of claim 1 , further comprising:
validating the determined etch characteristic for the simulated reaction based on an experimentally measured value of the etch characteristic.

15 . The method of claim 1 , further comprising:
identifying one or more candidate thermal etch reactions using the machine learning model, wherein each of the one or more identified candidate thermal etch reactions includes at least an identified etch precursor.

16 . The method of claim 15 , wherein each of the one or more identified candidate thermal etch reactions further includes an identified material to be etched by the identified etch precursor, an identified etch mask material, and/or an identified chamber material.

17 . A method of generating a machine learning model for use in predicting etch information in a thermal etch reaction:
performing at least one quantum mechanical simulation for each of a plurality of thermal etch reactions, each quantum mechanical simulation generating chemical characteristics and associated energies for one or more reaction pathways in a corresponding thermal etch reaction between a surface layer and an etch precursor; determining, for each of the plurality of thermal etch reactions, an experimentally determined etch characteristic; generating a training set comprising a plurality of training set members, each training set member comprising (i) at least one feature vector containing the chemical characteristics and associated energies for intermediates and/or products produced in the one or more reaction pathways for the corresponding thermal etch reaction, and (ii) a label representing the experimentally determined etch characteristic; and generating the machine learning model trained using the training set, wherein the machine learning model is configured to predict the etch information in the thermal etch reaction.

18 . The method of claim 17 , wherein the machine learning model is a classification and regression tree, a random forest tree, an artificial neural network, a linear regression, a logistic regression, or a support vector machine.

19 . The method of claim 17 , wherein performing the at least one quantum mechanical simulation comprises performing multiple quantum mechanical simulations for each of the plurality of thermal etch reactions, and wherein each feature vector contains the chemical characteristics and associated energies for intermediates and/or products produced in the one or more reaction pathways from one of the multiple quantum mechanical simulations of the corresponding thermal etch reaction.

20 . The method of claim 17 , wherein each of the at least one quantum mechanical simulation includes a quantum mechanical model configured with a surface representation of the surface layer and one or more initial conditions.

21 . The method of claim 20 , wherein the one or more initial conditions include a separation distance between the surface layer and the etch precursor at an onset of the quantum mechanical simulation, an orientation and/or direction of the surface layer and the etch precursor at the onset of the quantum mechanical simulation, a form of an initial chemical bridge between the surface layer and the etch precursor at the onset of the quantum mechanical simulation, an internal or kinetic energy of the etch precursor or the surface layer at the onset of the quantum mechanical simulation, or combinations thereof.

22 . The method of claim 20 , wherein the surface representation of the surface layer is selected from a group consisting of: a molecule, a small cluster of molecules, and a large cluster of molecules.

23 . The method of claim 2

Assignees

• Lam Res Corp

Inventors

• Lill Thorsten
• Fischer Andreas
• Berry Iii Ivan L
• Draeger Nerissa Sue
• Gottscho Richard A

Classifications

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06N99/005

  Physics · mapped topic

• G06N99/002

  Physics · mapped topic

• G06F17/5009 Primary

  Physics · mapped topic