{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:44:46Z","timestamp":1757540686483},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2020,9,11]],"date-time":"2020-09-11T00:00:00Z","timestamp":1599782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,3,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Adaptive optics are techniques used for processing the spatial resolution of astronomical images taken from large ground-based telescopes. In this work, computational results are presented for a modified curvature sensor, the tomographic pupil image wavefront sensor (TPI-WFS), which measures the turbulence of the atmosphere, expressed in terms of an expansion over Zernike polynomials. Convolutional neural networks (CNN) are presented as an alternative to the TPI-WFS reconstruction. This technique is a machine learning model of the family of artificial neural networks, which are widely known for its performance as modeling and prediction technique in complex systems. Results obtained from the reconstruction of the networks are compared with the TPI-WFS reconstruction by estimating errors and optical measurements (root mean square error, mean structural similarity and Strehl ratio). The reconstructed wavefronts from both techniques are compared for wavefronts of 153 Zernike modes. For this case, a detailed comparison and grid search to find the most suitable neural network is performed, searching between multi-layer perceptron, CNN and recurrent networks topologies. In general, the best network was a CNN trained for TPI-WFS reconstruction, achieving better performance than the reconstruction software from TPI-WFS in most of the turbulent profiles, but the most significant improvements were found for higher turbulent profiles that have the lowest r0 values.<\/jats:p>","DOI":"10.1093\/jigpal\/jzaa045","type":"journal-article","created":{"date-parts":[[2020,8,6]],"date-time":"2020-08-06T14:39:42Z","timestamp":1596724782000},"page":"180-192","source":"Crossref","is-referenced-by-count":3,"title":["Compensating atmospheric turbulence with CNNs for defocused pupil image wavefront sensors"],"prefix":"10.1093","volume":"29","author":[{"given":"Sergio Luis Su\u00e1rez","family":"G\u00f3mez","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of Oviedo, Oviedo, Spain"}]},{"given":"Carlos","family":"Gonz\u00e1lez-Guti\u00e9rrez","sequence":"additional","affiliation":[{"name":"Department of Information Technology, University of Oviedo, Oviedo, Spain"}]},{"given":"Juan D\u00edaz","family":"Su\u00e1rez","sequence":"additional","affiliation":[{"name":"Department of Physics, University of Oviedo, Oviedo, Spain and Wooptix S.L., San Crist\u00f3bal de La Laguna, Spain"}]},{"given":"Juan Jos\u00e9 Fern\u00e1ndez","family":"Valdivia","sequence":"additional","affiliation":[{"name":"Department of Physics, University of Oviedo, Oviedo, Spain and Wooptix S.L., San Crist\u00f3bal de La Laguna, Spain"}]},{"given":"Jos\u00e9 Manuel Rodr\u00edguez","family":"Ramos","sequence":"additional","affiliation":[{"name":"Department of Physics, University of Oviedo, Oviedo, Spain and Wooptix S.L., San Crist\u00f3bal de La Laguna, Spain"}]},{"given":"Luis Fernando Rodr\u00edguez","family":"Ramos","sequence":"additional","affiliation":[{"name":"Instituto de Astrof\u00edsica de Canarias, San Crist\u00f3bal de La Laguna, Spain"}]},{"given":"Jes\u00fas Daniel Santos","family":"Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"Department of Physics, University of Oviedo, Oviedo, Spain and Wooptix S.L., San Crist\u00f3bal de La Laguna, Spain"}]}],"member":"286","published-online":{"date-parts":[[2020,9,11]]},"reference":[{"key":"2021032210351992900_ref1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511525179","volume-title":"Adaptive Optics in Astronomy","author":"Roddier","year":"1999"},{"key":"2021032210351992900_ref2","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1364\/JOSAA.10.002277","article-title":"Wave-front reconstruction from defocused images and the testing of ground-based optical telescopes","volume":"10","author":"Roddier","year":"1993","journal-title":"Journal of the Optical Society of America"},{"key":"2021032210351992900_ref3","doi-asserted-by":"crossref","first-page":"2855","DOI":"10.1093\/mnras\/stx262","article-title":"Laboratory and telescope demonstration of the TP3-WFS for the adaptive optics segment of AOLI","volume":"467","author":"Colodro-Conde","year":"2017","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"key":"2021032210351992900_ref4","doi-asserted-by":"crossref","first-page":"215","DOI":"10.3233\/ICA-150488","article-title":"A hybrid intelligent recognition system for the early detection of strokes","volume":"22","author":"Villar","year":"2015","journal-title":"Integrated Computer Aided Engineering"},{"key":"2021032210351992900_ref5","doi-asserted-by":"crossref","first-page":"5188","DOI":"10.1016\/j.eswa.2013.03.013","article-title":"A hybrid intelligent system for PID controller using in a steel rolling process","volume":"40","author":"Calvo-Rolle","year":"2013","journal-title":"Expert Systems with Applications"},{"key":"2021032210351992900_ref6","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.jal.2015.09.007","article-title":"An intelligent fault detection system for a heat pump installation based on a geothermal heat exchanger","volume":"17","author":"Casteleiro-Roca","year":"2016","journal-title":"Journal of Applied Logic"},{"key":"2021032210351992900_ref7","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/978-3-319-19719-7_4","volume-title":"10th International Conference on Soft Computing Models in Industrial and Environmental Applications","author":"Villar","year":"2015"},{"key":"2021032210351992900_ref8","doi-asserted-by":"crossref","first-page":"2420","DOI":"10.1364\/OE.20.002420","article-title":"Using artificial neural networks for open-loop tomography","volume":"20","author":"Osborn","year":"2012","journal-title":"Optics Express"},{"key":"2021032210351992900_ref9","doi-asserted-by":"crossref","first-page":"8895","DOI":"10.3390\/s120708895","article-title":"An ANN-based smart tomographic reconstructor in a dynamic environment","volume":"12","author":"de Cos Juez","year":"2012","journal-title":"Sensors (Switzerland)"},{"key":"2021032210351992900_ref10","doi-asserted-by":"crossref","first-page":"2508","DOI":"10.1093\/mnras\/stu758","article-title":"Open-loop tomography with artificial neural networks on CANARY: on-sky results","volume":"441","author":"Osborn","year":"2014","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"key":"2021032210351992900_ref11","doi-asserted-by":"crossref","first-page":"103","DOI":"10.3390\/e19030103","article-title":"Analysis of the temporal structure evolution of physical systems with the self-organising tree algorithm (SOTA): application for validating neural network systems on adaptive optics data before on-sky implementation","volume":"19","author":"Su\u00e1rez G\u00f3mez","year":"2017","journal-title":"Entropy"},{"key":"2021032210351992900_ref12","volume-title":"Neural Networks: A Comprehensive Foundation","author":"Haykin","year":"1999"},{"key":"2021032210351992900_ref13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2018\/5348265","article-title":"Multi-GPU development of a neural networks based reconstructor for adaptive optics","volume":"2018","author":"Gonz\u00e1lez-Guti\u00e9rrez","year":"2018","journal-title":"Complexity"},{"key":"2021032210351992900_ref14","first-page":"1","article-title":"A methodology for detecting relevant single nucleotide polymorphism in prostate cancer with multivariate adaptive regression splines and backpropagation artificial neural networks","author":"Lasheras","year":"2018","journal-title":"Neural Computing and Applications"},{"key":"2021032210351992900_ref15","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1109\/MLSP.2008.4685487","volume-title":"IEEE Workshop on Machine Learning for Signal Processing, 2008. MLSP 2008","author":"Mirowski","year":"2008"},{"key":"2021032210351992900_ref16","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1109\/ICSIPA.2011.6144164","volume-title":"IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 2011","author":"Nagi","year":"2011"},{"key":"2021032210351992900_ref17","first-page":"2451","article-title":"Learning to forget: Continual prediction with LSTM","volume-title":"Neural computation","author":"Gers","year":"1999"},{"key":"2021032210351992900_ref18","doi-asserted-by":"crossref","first-page":"21356","DOI":"10.1364\/OE.18.021356","article-title":"Modeling a MEMS deformable mirror using non-parametric estimation techniques","volume":"18","author":"Guzm\u00e1n","year":"2010","journal-title":"Optics Express"},{"key":"2021032210351992900_ref19","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1364\/JOSAA.11.000783","article-title":"First-order performance evaluation of adaptive-optics systems for atmospheric-turbulence compensation in extended-field-of-view astronomical telescopes","volume":"11","author":"Ellerbroek","year":"1994","journal-title":"Journal of the Optical Society of America A"},{"key":"2021032210351992900_ref20","doi-asserted-by":"crossref","first-page":"A253","DOI":"10.1364\/JOSAA.27.00A253","article-title":"Tomography approach for multi-object adaptive optics","volume":"27","author":"Vidal","year":"2010","journal-title":"Journal of the Optical Society of America A"},{"key":"2021032210351992900_ref21","first-page":"91484M","article-title":"First on-sky results of a neural network based tomographic reconstructor: Carmen on Canary","volume":"9148","author":"Osborn","year":"2014","journal-title":"Adaptive Optics Systems IV"},{"key":"2021032210351992900_ref22","doi-asserted-by":"crossref","first-page":"23565","DOI":"10.1364\/OE.22.023565","article-title":"First on-sky SCAO validation of full LQG control with vibration mitigation on the CANARY pathfinder","volume":"22","author":"Sivo","year":"2014","journal-title":"Optics Express"},{"key":"2021032210351992900_ref23","doi-asserted-by":"crossref","first-page":"L2","DOI":"10.1051\/0004-6361\/201116658","article-title":"MOAO first on-sky demonstration with CANARY","volume":"529","author":"Gendron","year":"2011","journal-title":"Astronomy and Astrophysics"},{"key":"2021032210351992900_ref24","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1364\/JOSA.66.000207","article-title":"Zernike polynomials and atmospheric turbulence","volume":"66","author":"Noll","year":"1976","journal-title":"Journal of the Optical Society of America A"},{"key":"2021032210351992900_ref25","first-page":"1051","volume-title":"International Conference on Intelligent Systems Design and Applications","author":"Su\u00e1rez G\u00f3mez","year":"2016"},{"key":"2021032210351992900_ref26","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1364\/JOSAA.19.001390","article-title":"Extended analysis of curvature sensing","volume":"19","author":"van Dam","year":"2002","journal-title":"Journal of the Optical Society of America A"},{"key":"2021032210351992900_ref27","doi-asserted-by":"crossref","first-page":"5497","DOI":"10.1364\/AO.41.005497","article-title":"Wave-front sensing from defocused images by use of wave-front slopes","volume":"41","author":"van Dam","year":"2002","journal-title":"Applied Optics"},{"key":"2021032210351992900_ref28","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"2021032210351992900_ref29","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2021032210351992900_ref30","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","volume-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Graves","year":"2013"},{"key":"2021032210351992900_ref31","first-page":"807","volume-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)","author":"Nair","year":"2010"},{"key":"2021032210351992900_ref32","author":"Lipton","year":"2015"},{"key":"2021032210351992900_ref33","article-title":"Keras: deep learning library for Theano and TensorFlow","author":"Chollet","year":"2015"}],"container-title":["Logic Journal of the IGPL"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jigpal\/article-pdf\/29\/2\/180\/36646490\/jzaa045.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jigpal\/article-pdf\/29\/2\/180\/36646490\/jzaa045.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T10:35:59Z","timestamp":1616409359000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jigpal\/article\/29\/2\/180\/5903191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,11]]},"references-count":33,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,9,11]]},"published-print":{"date-parts":[[2021,3,25]]}},"URL":"https:\/\/doi.org\/10.1093\/jigpal\/jzaa045","relation":{},"ISSN":["1367-0751","1368-9894"],"issn-type":[{"value":"1367-0751","type":"print"},{"value":"1368-9894","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,4]]},"published":{"date-parts":[[2020,9,11]]}}}