Machine learning for improved image-based wavefront sensing.

For large amounts of wavefront error, gradient-based optimization methods for image-based wavefront sensing are unlikely to converge when the starting guess for the wavefront differs greatly from the true wavefront. We use machine learning operating on a point-spread function to determine a good initial estimate of the wavefront. We show that our trained convolutional neural network provides good initial estimates in the presence of simulated detector noise and is more effective than using many random starting guesses for large amounts of wavefront error.

Extending capture range for piston retrieval in segmented systems.

Image-based wavefront sensing is a powerful technique for measuring the aberrations of optical systems and surfaces. It often fails for segmented systems with large piston errors per segment. We propose a method for finding these errors using broadband light and a specialized grid search as part of a more global search. We show that this method has a high rate of success for a case where nonlinear optimization gets stuck in local minima. We also explore points of failure.