TY - GEN
T1 - Deep neural networks to improve the dynamic range of Zernike phase-contrast wavefront sensing in high-contrast imaging systems
AU - Allan, Gregory
AU - Kang, Iksung
AU - Douglas, Ewan S.
AU - N'diaye, Mamadou
AU - Barbastathis, George
AU - Cahoy, Kerri
N1 - Funding Information:
I. Kang acknowledges a partial support from KFAS (Korea Foundation for Advanced Studies) scholarship. Portions of this work were supported by the WFIRST Science Investigation team prime award NNG16PJ24C. The authors thank Raphaël Pourcelot for his time and assistance, and acknowledge the MIT SuperCloud and Lincoln Laboratory Supercomputing Center for providing high-performance computing resources that have contributed to the research result reported within this paper. This research made use of POPPY, an open-source optical propagation Python package originally developed for the James Webb Space Telescope project.33
Publisher Copyright:
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
PY - 2020
Y1 - 2020
N2 - In high-contrast imaging applications, such as the direct imaging of exoplanets, a coronagraph is used to suppress the light from an on-axis star so that a dimmer, off-axis object can be imaged. To maintain a high-contrast dark region in the image, optical aberrations in the instrument must be minimized. The use of phase-contrast-based Zernike Wavefront Sensors (ZWFS) to measure and correct for aberrations has been studied for large segmented aperture telescopes and ZWFS are planned for the coronagraph instrument on the Roman Space Telescope (RST). ZWFS enable subnanometer wavefront sensing precision, but their response is nonlinear. Lyot-based Low-OrderWavefront Sensors (LLOWFS) are an alternative technique, where light rejected from a coronagraph's Lyot stop is used for linear measurement of small wavefront displacements. Recently, the use of Deep Neural Networks (DNNs) to enable phase retrieval from intensity measurements has been demonstrated in several optical configurations. In a LLOWFS system, the use of DNNs rather than linear regression has been shown to greatly extend the sensor's usable dynamic range. In this work, we investigate the use of two different types of machine learning algorithms to extend the dynamic range of the ZWFS. We present static and dynamic deep learning architectures for single- and multi-wavelength measurements, respectively. Using simulated ZWFS intensity measurements, we validate the network training technique and present phase reconstruction results. We show an increase in the capture range of the ZWFS sensor by a factor of 3.4 with a single wavelength and 4.5 with four wavelengths.
AB - In high-contrast imaging applications, such as the direct imaging of exoplanets, a coronagraph is used to suppress the light from an on-axis star so that a dimmer, off-axis object can be imaged. To maintain a high-contrast dark region in the image, optical aberrations in the instrument must be minimized. The use of phase-contrast-based Zernike Wavefront Sensors (ZWFS) to measure and correct for aberrations has been studied for large segmented aperture telescopes and ZWFS are planned for the coronagraph instrument on the Roman Space Telescope (RST). ZWFS enable subnanometer wavefront sensing precision, but their response is nonlinear. Lyot-based Low-OrderWavefront Sensors (LLOWFS) are an alternative technique, where light rejected from a coronagraph's Lyot stop is used for linear measurement of small wavefront displacements. Recently, the use of Deep Neural Networks (DNNs) to enable phase retrieval from intensity measurements has been demonstrated in several optical configurations. In a LLOWFS system, the use of DNNs rather than linear regression has been shown to greatly extend the sensor's usable dynamic range. In this work, we investigate the use of two different types of machine learning algorithms to extend the dynamic range of the ZWFS. We present static and dynamic deep learning architectures for single- and multi-wavelength measurements, respectively. Using simulated ZWFS intensity measurements, we validate the network training technique and present phase reconstruction results. We show an increase in the capture range of the ZWFS sensor by a factor of 3.4 with a single wavelength and 4.5 with four wavelengths.
KW - Deep neural networks
KW - High-contrast imaging
KW - Machine learning
KW - Wavefront sensing
UR - http://www.scopus.com/inward/record.url?scp=85099877412&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099877412&partnerID=8YFLogxK
U2 - 10.1117/12.2562927
DO - 10.1117/12.2562927
M3 - Conference contribution
AN - SCOPUS:85099877412
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Space Telescopes and Instrumentation 2020
A2 - Lystrup, Makenzie
A2 - Perrin, Marshall D.
PB - SPIE
T2 - Space Telescopes and Instrumentation 2020: Optical, Infrared, and Millimeter Wave
Y2 - 14 December 2020 through 22 December 2020
ER -