[en] Instrumental aberrations strongly limit high-contrast imaging of exoplanets, especially when they produce quasistatic speckles in the science images. With the help of recent advances in deep learning, we have developed in previous works an approach that applies convolutional neural networks (CNN) to estimate pupil-plane phase aberrations from point spread functions (PSF). In this work we take a step further by incorporating into the deep learning architecture the physical simulation of the optical propagation occurring inside the instrument. This is achieved with an autoencoder architecture, which uses a differentiable optical simulator as the decoder. Because this unsupervised learning approach reconstructs the PSFs, knowing the true phase is not needed to train the models, making it particularly promising for on-sky applications. We show that the performance of our method is almost identical to a standard CNN approach, and that the models are sufficiently stable in terms of training and robustness. We notably illustrate how we can benefit from the simulator-based autoencoder architecture by quickly fine-tuning the models on a single test image, achieving much better performance when the PSFs contain more noise and aberrations. These early results are very promising and future steps have been identified to apply the method on real data.
Disciplines :
Space science, astronomy & astrophysics
Author, co-author :
Quesnel, Maxime ; Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
Orban De Xivry, Gilles ; Université de Liège - ULiège > Département d'astrophysique, géophysique et océanographie (AGO) > Planetary & Stellar systems Imaging Laboratory
Absil, Olivier ; Université de Liège - ULiège > Département d'astrophysique, géophysique et océanographie (AGO) > Planetary & Stellar systems Imaging Laboratory
Louppe, Gilles ; Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Big Data
Language :
English
Title :
A simulator-based autoencoder for focal plane wavefront sensing
Jovanovic, N., Absil, O., Baudoz, P., Beaulieu, M., Bottom, M., Cady, E., Carlomagno, B., Carlotti, A., Doelman, D., Fogarty, K., Galicher, R., Guyon, O., Haffert, S., Huby, E., Jewell, J., Keller, C., Kenworthy, M. A., Knight, J., Kühn, J., Miller, K., Mazoyer, J., N'Diaye, M., Por, E., Pueyo, L., Riggs, A. J. E., Ruane, G., Sirbu, D., Snik, F., Wallace, J. K., Wilby, M., and Ygouf, M., “Review of high-contrast imaging systems for current and future ground-based and space-based telescopes: Part II. Common path wavefront sensing/control and coherent differential imaging,” in [Adaptive Optics Systems VI], Close, L. M., Schreiber, L., and Schmidt, D., eds., Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series 10703, 107031U (July 2018).
Paine, S. W. and Fienup, J. R., “Machine learning for improved image-based wavefront sensing,” Optics Letters 43, 1235 (Mar. 2018).
Andersen, T., Owner-Petersen, M., and Enmark, A., “Neural networks for image-based wavefront sensing for astronomy,” Optics Letters 44, 4618 (Sept. 2019).
Andersen, T., Owner-Petersen, M., and Enmark, A., “Image-based wavefront sensing for astronomy using neural networks,” Journal of Astronomical Telescopes, Instruments, and Systems 6, 034002 (July 2020).
Quesnel, M., Orban de Xivry, G., Louppe, G., and Absil, O., “Deep learning-based focal plane wavefront sensing for classical and coronagraphic imaging,” in [Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series], Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series 11448, 114481G (Dec. 2020).
Orban de Xivry, G., Quesnel, M., Vanberg, P. O., Absil, O., and Louppe, G., “Focal plane wavefront sensing using machine learning: performance of convolutional neural networks compared to fundamental limits,” 505, 5702-5713 (Aug. 2021).
Quesnel, M., Orban de Xivry, G., Absil, O., and Louppe, G., “A deep learning approach for focal-plane wavefront sensing using vortex phase diversity,” (submitted, 2022).
Bostan, E., Heckel, R., Chen, M., Kellman, M., and Waller, L., “Deep phase decoder: self-calibrating phase microscopy with an untrained deep neural network,” Optica 7, 559-562 (Jun 2020).
Wang, F., Bian, Y., Haichao, W., Lyu, M., Pedrini, G., Osten, W., Barbastathis, G., and Situ, G., “Phase imaging with an untrained neural network,” Light: Science Applications 9, 77 (05 2020).
Peng, Y., Choi, S., Padmanaban, N., and Wetzstein, G., “Neural holography with camera-in-the-loop training,” ACM Trans. Graph. 39 (nov 2020).
Liaudat, T., Starck, J.-L., Kilbinger, M., and Frugier, P.-A., “Rethinking data-driven point spread function modeling with a differentiable optical model,” (2022).
Wong, A., Pope, B., Desdoigts, L., Tuthill, P., Norris, B., and Betters, C., “Phase retrieval and design with automatic differentiation: tutorial,” Journal of the Optical Society of America B 38, 2465 (aug 2021).
Noll, R. J., “Zernike polynomials and atmospheric turbulence.,” Journal of the Optical Society of America (1917-1983) 66, 207-211 (Mar. 1976).
Krist, J. E., “PROPER: an optical propagation library for IDL,” in [Optical Modeling and Performance Predictions III], Kahan, M. A., ed., 6675, 250-258, International Society for Optics and Photonics, SPIE (2007).
Gonsalves, R. A., “Phase Retrieval And Diversity In Adaptive Optics,” Optical Engineering 21(5), 829-832 (1982).
Vievard, S., Bos, S. P., Cassaing, F., Ceau, A., Guyon, O., Jovanovic, N., Keller, C., Lozi, J., Martinache, F., Mary, D., Montmerle-Bonnefois, A., Mugnier, L., N'diaye, M., Norris, B., Sahoo, A., Sauvage, J.F., Snik, F., Wilby, M. J., and Wong, A., “Overview of focal plane wavefront sensors to correct for the Low Wind Effect on SUBARU/SCExAO,” in [6th International Conference on Adaptive Optics for Extremely Large Telescopes, AO4ELT 2019], (June 2019).
Ferreira, F., Gratadour, D., Sevin, A., and Doucet, N., “Compass: An efficient gpu-based simulation software for adaptive optics systems,” 2018 International Conference on High Performance Computing & Simulation (HPCS), 180-187 (2018).
Tan, M. and Le, Q., “EfficientNet: Rethinking model scaling for convolutional neural networks,” in [Proceedings of the 36th International Conference on Machine Learning], Chaudhuri, K. and Salakhutdinov, R., eds., Proceedings of Machine Learning Research 97, 6105-6114, PMLR (09-15 Jun 2019).
Kingma, D. P. and Ba, J., “Adam: A method for stochastic optimization,” (2017).
Kingma, D. P. and Welling, M., “Auto-encoding variational bayes,” (2013).
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., and Chintala, S., “Pytorch: An imperative style, high-performance deep learning library,” in [Advances in Neural Information Processing Systems], Wallach, H., Larochelle, H., Beygelzimer, A., d'Alché-Buc, F., Fox, E., and Garnett, R., eds., 32, 8026-8037, Curran Associates, Inc. (2019).
Klaus Greff, Aaron Klein, Martin Chovanec, Frank Hutter, and Jürgen Schmidhuber, “The Sacred Infrastructure for Computational Research,” in [Proceedings of the 16th Python in Science Conference], Katy Huff, David Lippa, Dillon Niederhut, and Pacer, M., eds., 49-56 (2017).