Determination of substrate layer thickness with polishing pad wear compensation

1. A method of training a neural network, comprising:

for each test substrate of a plurality of test substrates having a different thickness profile, obtaining a ground truth thickness profile for the test substrate;

obtaining a first thickness value;

for each test substrate of the plurality of test substrates, obtaining a first measured thickness profile corresponding to the test substrate being measured by an in-situ monitoring system while on a polishing pad of a first thickness corresponding to the first thickness value;

obtaining a second thickness value;

for each test substrate of the plurality of test substrates, obtaining a second measured thickness profile corresponding to the test substrate being measured by the in-situ monitoring system while on a polishing pad of a second thickness corresponding to the second thickness value;

for each test substrate of the plurality of test substrates, generating an estimated third thickness profile for a third thickness value that is between the first thickness value and the second thickness value by interpolating between the first measured thickness profile for the test substrate and the second measured thickness profile; and

training a neural network that has a plurality of input nodes and a plurality of output nodes by, for each test substrate, applying the estimated third thickness profile to a multiplicity of input nodes from the plurality of input nodes, applying the third thickness value to an input node from the plurality of input nodes or to an intermediate node in the neural network, and applying the ground truth thickness profile to a plurality of output nodes while the neural network is in a training mode.

2. The method of claim 1 , wherein obtaining the first and second thickness values include measuring a thickness of the polishing pad of the first thickness and measuring a thickness of the polishing pad of the second thickness.

3. The method of claim 2 , wherein measuring thickness of the polishing pad of the first thickness and measuring thickness of the polishing pad of the second thickness comprises measuring with a profilometer.

4. The method of claim 1 , wherein obtaining the first or second measured thickness profiles further includes placing the test substrate on a polishing pad of the first or second thickness and scanning the test substrate with an in-situ monitoring system.

5. The method of claim 1 , wherein training the neural network further includes applying the first or second thickness and the first or second measured thickness profiles to a plurality of input nodes and the ground truth thickness profile to a plurality of output nodes while the neural network is in the training mode.

6. The method of claim 1 , wherein training the neural network further includes applying a fourth thickness and an estimated fourth thickness profile to a plurality of input nodes and the ground truth thickness profile to a plurality of output nodes while the neural network is in the training mode.

7. The method of claim 1 , wherein the interpolation is a linear interpolation.

8. The method of claim 1 , comprising applying the third thickness value directly to the intermediate node.

9. The method of claim 1 , comprising applying the third thickness value to the input node from the plurality of input nodes.

10. The method of claim 1 , wherein the first measured thickness profile and the second measured thickness profile are thicknesses of a conductive layer on the test substrate.

11. The method of claim 10 , wherein the in-situ monitoring system comprises an eddy current monitoring system.

12. The method of claim 10 , wherein obtaining the ground truth thickness profile comprises an electrical impedance measurement.

13. The method of claim 12 , wherein the electrical impedance measurement comprises measuring using a four point probe.