Spatial optical mode decomposition using deep learning

We demonstrate using a convolutional neural network (CNN) architecture such as Resnet20 how to perform complete Laguerre-Gauss (LG) decomposition of an unknown, incoming laser beam using only intensity images. For our proof-ofconcept simulations, we use random super-positions of first 10 azimuthal LG modes with l-values from 0 to 9. For these random super-positions, both the amplitudes and phase values are random. Random white noise is added to the intensity images of these simulated fields. 80,000 such training images are used to train our Resnet20 CNN while another 20,000 images are in the test set. Prediction results on the test set show a correlation value of 98.75% showing the efficacy of using a CNN to perform spatial mode decomposition.

[1]  Sahar Froim,et al.  Beam profiler network (BPNet): a deep learning approach to mode demultiplexing of Laguerre-Gaussian optical beams. , 2019, Optics letters.

[2]  High-efficiency phase flattening based Laguerre–Gauss spectrometer using variable focus lenses , 2016, 1601.01834.

[3]  L. Torner,et al.  Observation of the orbital angular momentum spectrum of a light beam. , 2003, Optics letters.

[4]  S. Barnett,et al.  Measuring the orbital angular momentum of a single photon. , 2002, Physical review letters.

[5]  A. Willner,et al.  Terabit free-space data transmission employing orbital angular momentum multiplexing , 2012, Nature Photonics.

[6]  J. P. Woerdman,et al.  Determining the dimensionality of bipartite orbital-angular-momentum entanglement using multi-sector phase masks , 2012 .

[7]  L. R. Hofer,et al.  Hermite-Gaussian mode detection via convolution neural networks. , 2019, Journal of the Optical Society of America. A, Optics, image science, and vision.

[8]  Yi An,et al.  Learning to decompose the modes in few-mode fibers with deep convolutional neural network. , 2018, Optics express.

[9]  Yi An,et al.  Deep learning enabled superfast and accurate M2 evaluation for fiber beams. , 2019, Optics express.

[10]  Sanjaya Lohani,et al.  On the use of deep neural networks in optical communications. , 2018, Applied optics.

[11]  Johannes Courtial,et al.  Measurement of the light orbital angular momentum spectrum using an optical geometric transformation , 2011 .

[12]  Gabriel Molina-Terriza,et al.  Management of the angular momentum of light: preparation of photons in multidimensional vector states of angular momentum. , 2002, Physical review letters.

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  M. Sheikh,et al.  High-efficiency measurement of all orbital angular momentum modes in a light beam , 2016, 1611.06964.

[15]  D. Gauthier,et al.  High-dimensional quantum cryptography with twisted light , 2014, 1402.7113.

[16]  S. Barnett,et al.  Free-space information transfer using light beams carrying orbital angular momentum. , 2004, Optics express.

[17]  A. Vaziri,et al.  Entanglement of the orbital angular momentum states of photons , 2001, Nature.

[18]  D. Flamm,et al.  Measurement of the orbital angular momentum density of light by modal decomposition , 2013 .

[19]  Ebrahim Karimi,et al.  Efficient generation and sorting of orbital angular momentum eigenmodes of light by thermally tuned q-plates , 2009, 0905.0562.

[20]  Robert W Boyd,et al.  Efficient separation of the orbital angular momentum eigenstates of light , 2013, Nature Communications.

[21]  Tianyue Hou,et al.  Fast modal analysis for Hermite-Gaussian beams via deep learning. , 2020, Applied optics.

[22]  M. Lavery,et al.  Efficient sorting of orbital angular momentum states of light. , 2010, Physical review letters.

[23]  A. Willner,et al.  Terabit-Scale Orbital Angular Momentum Mode Division Multiplexing in Fibers , 2013, Science.

[24]  Ebrahim Karimi,et al.  Limitations to the determination of a Laguerre–Gauss spectrum via projective, phase-flattening measurement , 2014, 1401.3512.