{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T11:47:37Z","timestamp":1768218457246,"version":"3.49.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This study addresses the challenge of improving wavefront correction for Orbital Angular Momentum (OAM) in oceanic turbulence using a physics-constrained Generative Adversarial Network (GAN).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We integrated physical constraints into a deep learning framework to reconstruct degraded input images (SSIM = 0.62). The model was trained with varied loss settings, including a baseline model, spectral constraints (+Spec), and spatial constraints (+Ortho).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The dual-constraint approach (+Ortho+Spec) reached a near-optimal SSIM of 0.98. Ablation studies revealed that while +Ortho boosted modal purity to 95.7%, the dual-constraints achieved 98.4% purity. Power spectral density analysis via KL divergence confirmed the dual-constraints' superiority (KL = 0.56) over the baseline (KL = 2.47).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results demonstrate that integrating both spatial and spectral constraints effectively optimizes reconstruction, purity, and spectral fidelity, offering a robust solution for OAM correction in underwater optical communication systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1702056","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:34:37Z","timestamp":1768206877000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics-constrained GAN boosts OAM correction in ocean turbulence"],"prefix":"10.3389","volume":"8","author":[{"given":"Xiaoji","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"8185","DOI":"10.1103\/PhysRevA.45.8185","article-title":"Orbital angular momentum of light and the transformation of Laguerre-Gaussian laser modes","volume":"45","author":"Allen","year":"1992","journal-title":"Phys. Rev. A"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.17826","article-title":"A survey on machine and deep learning for optical communications (version 1)","author":"Amirabadi","year":"2024","journal-title":"arXiv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1650284","DOI":"10.3389\/fphy.2025.1650284","article-title":"High-speed and potentially scalable UWOC\/UWB converged transmission link for underwater wireless optical sensor networks","volume":"13","author":"Armghan","year":"2025","journal-title":"Front. Phys."},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.1364\/CLEO_SI.2025.SS118_7","article-title":"\u201cSingle-shot wavefront aberration correction using a hybrid neural network approach,\u201d","volume-title":"CLEO 2025, SS118_7","author":"Baharlou","year":"2025"},{"key":"B5","doi-asserted-by":"publisher","first-page":"108624","DOI":"10.1016\/j.optlastec.2022.108624","article-title":"Underwater turbulence, its effects on optical wireless communication and imaging: a review","volume":"156","author":"Baykal","year":"2022","journal-title":"Optics Laser Technol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"013508","DOI":"10.1103\/PhysRevA.110.013508","article-title":"Deep-learning-based recognition of composite vortex beams through long-distance and moderate-to-strong atmospheric turbulence","volume":"110","author":"Cai","year":"2024","journal-title":"Phys. Rev. A"},{"key":"B7","doi-asserted-by":"publisher","first-page":"5310","DOI":"10.1109\/JLT.2023.3262352","article-title":"90-m\/660-Mbps underwater wireless optical communication enabled by interleaved single-carrier FDM scheme combined with sparse weight-initiated DNN equalizer","volume":"41","author":"Du","year":"2023","journal-title":"J. Lightwave Technol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2041","DOI":"10.1109\/JLT.2022.3218828","article-title":"Distortion compensation for orbital angular momentum beams: from probing to deep learning","volume":"41","author":"Guo","year":"2023","journal-title":"J. Lightwave Technol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1387284","DOI":"10.3389\/fphy.2024.1387284","article-title":"Symbol error rate minimization using deep learning approaches for short-reach optical communication networks","volume":"12","author":"Iqbal","year":"2024","journal-title":"Front. Phys."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632","article-title":"\u201cImage-to-image translation with conditional adversarial networks (version 3),\u201d","author":"Isola","year":"2016","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B12","doi-asserted-by":"publisher","first-page":"915","DOI":"10.54097\/hset.v39i.6676","article-title":"Comparative analysis of Pix2Pix and CycleGAN for image-to-image translation","volume":"39","author":"Lin","year":"2023","journal-title":"Highlights Sci. Eng. Technol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1109\/ICETCI64844.2025.11084007","author":"Liu","year":"2025"},{"key":"B14","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1002\/lpor.202300833","article-title":"In-situ wavefront correction via physics-informed neural network","volume":"18","author":"Long","year":"2024","journal-title":"Laser Photon. Rev."},{"key":"B15","doi-asserted-by":"publisher","first-page":"104045","DOI":"10.1016\/j.yofte.2024.104045","article-title":"Relay aided UWOC-SMF-FSO based hybrid link for underwater wireless optical sensor network","volume":"89","author":"Mirza","year":"2025","journal-title":"Optical Fiber Technol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"232","DOI":"10.2184\/lsj.32.232","article-title":"Laguerre-gaussian beams and optical orbital angular momentum","volume":"32","author":"Miyamoto","year":"2004","journal-title":"Rev. Laser Eng."},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1364\/CLEO_SI.2011.CMG4","article-title":"\u201cIncident field image reconstruction using speckle intensity correlations over position,\u201d","volume-title":"CLEO:2011 - Laser Applications to Photonic Applications, CMG4","author":"Newman","year":"2011"},{"key":"B18","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1615\/InterJFluidMechRes.v27.i1.70","article-title":"Spectrum of turbulent fluctuations of the sea-water refraction index","volume":"27","author":"Nikishov","year":"2000","journal-title":"Int. J. Fluid Mech. Res."},{"key":"B19","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1109\/ICCMC53470.2022.9753782","article-title":"\u201cA survey of modern deep learning based generative adversarial networks (GANs),\u201d","volume-title":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","author":"Pradhyumna","year":"2022"},{"key":"B20","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1109\/I-SMAC58438.2023.10290678","article-title":"\u201cPerformance enhancement in underwater optical wireless communication using deep reinforcement learning approach,\u201d","volume-title":"2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","author":"Rathour","year":"2023"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s12596-025-02944-9.","article-title":"Performance analysis of underwater optical wireless communication in different ocean water types using spatial diversity","author":"Shafi","year":"2025","journal-title":"J. Opt"},{"key":"B22","doi-asserted-by":"publisher","first-page":"28623","DOI":"10.1109\/JIOT.2024.3404476","article-title":"Multidimensional beam optimization in underwater optical wireless communication based on deep reinforcement learning","volume":"11","author":"Shin","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"B23","doi-asserted-by":"publisher","first-page":"141403","DOI":"10.1109\/ACCESS.2025.3597025","article-title":"A novel energy adaptive neural network and deep Q-learning network for improved energy efficiency in dynamic underwater iot environment","volume":"13","author":"Simon","year":"2025","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.01907","article-title":"Turbulence enrichment using physics-informed generative adversarial networks (version 2)","author":"Subramaniam","year":"2020","journal-title":"arXiv"},{"key":"B25","doi-asserted-by":"publisher","first-page":"152","DOI":"10.54254\/2755-2721\/2025.LD25482","article-title":"Generative adversarial networks (GANs): principles, development, challenges, and diverse applications","volume":"165","author":"Sun","year":"2025","journal-title":"Appl. Comput. Eng."},{"key":"B26","doi-asserted-by":"publisher","first-page":"172126","DOI":"10.1016\/j.ijleo.2024.172126","article-title":"A survey of turbulence in underwater optical wireless communications","volume":"320","author":"Vali","year":"2025","journal-title":"Optik ."},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1364\/OFC.2014.W4J.5","article-title":"\u201cUsing orbital angular momentum modes for optical transmission,\u201d","volume-title":"Optical Fiber Communication Conference","author":"Wang","year":"2014"},{"key":"B28","doi-asserted-by":"crossref","first-page":"786","DOI":"10.23919\/EuMC58039.2023.10290384","article-title":"\u201cInfluence of the communication environment on orbital angular momentum (OAM) mode orthogonality,\u201d","volume-title":"2023 53rd European Microwave Conference (EuMC)","author":"Wulff","year":"2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1038\/s42005-024-01571-3","article-title":"Multiplexed orbital angular momentum beams demultiplexing using hybrid optical-electronic convolutional neural network","volume":"7","author":"Ye","year":"2024","journal-title":"Commun. Phys."},{"key":"B30","doi-asserted-by":"publisher","first-page":"166990","DOI":"10.1016\/j.ijleo.2021.166990","article-title":"Experimental analysis of adaptive optics correction methods on the beam carrying orbital angular momentum mode through oceanic turbulence","volume":"240","author":"Zhan","year":"2021","journal-title":"Optik"},{"key":"B31","doi-asserted-by":"publisher","first-page":"e00909","DOI":"10.1002\/lpor.202500909","article-title":"Single-pass wavefront reconstruction via depth heterogeneity self-supervised neural operator for turbulence correction","volume":"19","author":"Zhang","year":"2025","journal-title":"Laser Photon. Rev."},{"key":"B32","doi-asserted-by":"publisher","first-page":"105532","DOI":"10.1088\/1402-4896\/ad74b8","article-title":"Turbulence compensation with pix-to-pix generative adversarial networks in vector vortex beams","volume":"99","author":"Zhang","year":"2024","journal-title":"Phys. Scripta"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1702056\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:34:40Z","timestamp":1768206880000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1702056\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":32,"alternative-id":["10.3389\/frai.2025.1702056"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1702056","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1702056"}}