Artificial Intelligence-Assisted Laser Science and Technology: Status, Opportunities, and Challenges

Hanshuo Wu; Min Jiang; Pu Zhou

doi:10.3788/CJL230692

[1] Hecht J. A short history of laser development[J]. Applied Optics, 49, F99-F122(2010).

[2] Bertolotti M[M]. The history of the laser(2004).

[3] Hollenstein U, Palm H, Merkt F. A broadly tunable extreme ultraviolet laser source with a 0.008 cm-1 bandwidth[J]. Review of Scientific Instruments, 71, 4023-4028(2000).

[4] Köhler R, Tredicucci A, Beltram F et al. Terahertz semiconductor-heterostructure laser[J]. Nature, 417, 156-159(2002).

[5] Faist J, Capasso F, Sivco D L et al. Quantum cascade laser[J]. Science, 264, 553-556(1994).

[6] Gales S, Tanaka K A, Balabanski D L et al. The extreme light infrastructure: nuclear physics (ELI-NP) facility: new horizons in physics with 10 PW ultra-intense lasers and 20 MeV brilliant gamma beams[J]. Reports on Progress in Physics, 81, 094301(2018).

[7] Azadgoli B, Baker R Y. Laser applications in surgery[J]. Annals of Translational Medicine, 4, 452(2016).

[8] Slusher R E. Laser technology[J]. Reviews of Modern Physics, 71, S471-S479(1999).

[9] Shi W, Fang Q, Zhu X S et al. Fiber lasers and their applications[J]. Applied Optics, 53, 6554-6568(2014).

[10] Jiang M, Wu H S, An Y et al. Fiber laser development enabled by machine learning: review and prospect[J]. PhotoniX, 3, 1-27(2022).

[11] Genty G, Salmela L, Dudley J M et al. Machine learning and applications in ultrafast photonics[J]. Nature Photonics, 15, 91-101(2021).

[12] Zhou P, Su R T, Huang L J et al. Research progress and future perspective on ultrafast fiber laser enabled by computing technique(invited)[J]. Infrared and Laser Engineering, 47, 0803001(2018).

[13] Ma W, Liu Z C, Kudyshev Z A et al. Deep learning for the design of photonic structures[J]. Nature Photonics, 15, 77-90(2021).

[14] Jiang J Q, Chen M K, Fan J A. Deep neural networks for the evaluation and design of photonic devices[J]. Nature Reviews Materials, 6, 679-700(2020).

[15] Wang F Y, Zhang J J, Zheng X H et al. Where does AlphaGo go: from church-turing thesis to AlphaGo thesis and beyond[J]. IEEE/CAA Journal of Automatica Sinica, 3, 113-120(2016).

[16] Koshiba M. Full-vector analysis of photonic crystal fibers using the finite element method[J]. IEICE Transactions on Electronics, 85, 881-888(2002).

[17] Shi S Y, Chen C H, Prather D W. Plane-wave expansion method for calculating band structure of photonic crystal slabs with perfectly matched layers[J]. Journal of the Optical Society of America A, 21, 1769-1775(2004).

[18] Yu C P, Chang H C. Applications of the finite difference mode solution method to photonic crystal structures[J]. Optical and Quantum Electronics, 36, 145-163(2004).

[19] Hameed M F O, Obayya S S A, Al-Begain K et al. Accurate radial basis function based neural network approach for analysis of photonic crystal fibers[J]. Optical and Quantum Electronics, 40, 891-905(2008).

[20] Rodríguez-Esquerre V F, Isídio-Lima J J, Dourado-Sisnando A et al. Artificial neural networks for the chromatic dispersion prediction of photonic crystal fibers[J]. Microwave and Optical Technology Letters, 55, 2179-2181(2013).

[21] El-Mosalmy D D, Hameed M F O, Areed N F F et al. Novel neural network based optimization approach for photonic devices[J]. Optical and Quantum Electronics, 46, 439-453(2014).

[22] Chugh S, Gulistan A, Ghosh S et al. Machine learning approach for computing optical properties of a photonic crystal fiber[J]. Optics Express, 27, 36414-36425(2019).

[23] Jabin M A, Fok M P. Prediction of 12 photonic crystal fiber optical properties using MLP in deep learning[J]. IEEE Photonics Technology Letters, 34, 391-394(2022).

[24] Li H W, Chen H L, Li Y X et al. Prediction of the optical properties in photonic crystal fiber using support vector machine based on radial basis functions[J]. Optik, 275, 170603(2023).

[25] Bozinovic N, Yue Y, Ren Y X et al. Terabit-scale orbital angular momentum mode division multiplexing in fibers[J]. Science, 340, 1545-1548(2013).

[26] Ramachandran S, Kristensen P, Yan M F. Generation and propagation of radially polarized beams in optical fibers[J]. Optics Letters, 34, 2525-2527(2009).

[27] Li S H, Wang J. A compact trench-assisted multi-orbital-angular-momentum multi-ring fiber for ultrahigh-density space-division multiplexing (19 rings×22 modes)[J]. Scientific Reports, 4, 3853(2014).

[28] Li S H, Wang J. Supermode fiber for orbital angular momentum (OAM) transmission[J]. Optics Express, 23, 18736-18745(2015).

[29] Tian W, Zhang H, Zhang X G et al. A circular photonic crystal fiber supporting 26 OAM modes[J]. Optical Fiber Technology, 30, 184-189(2016).

[30] Rjeb A, Seleem H, Fathallah H et al. Design of 12 OAM-Graded index few mode fibers for next generation short haul interconnect transmission[J]. Optical Fiber Technology, 55, 102148(2020).

[31] Qin H B, Huang W, Song B B et al. Hybrid method for inverse design of orbital angular momentum transmission fiber based on neural network and optimization algorithms[J]. Journal of Lightwave Technology, 40, 5974-5985(2022).

[32] Tu X, Xie W S, Chen Z M et al. Analysis of deep neural network models for inverse design of silicon photonic grating coupler[J]. Journal of Lightwave Technology, 39, 2790-2799(2021).

[33] Fan J J, Huang W, Zhang R et al. Resonance prediction and inverse design of multi-core selective couplers based on neural networks[J]. Applied Optics, 61, 9350-9359(2022).

[34] Zhang S Y, Zhang C, Zeng Y et al. Machine learning assisted ultra-wideband fiber-optics mode selective coupler design[J]. IEEE Journal of Selected Topics in Quantum Electronics, 28, 4500110(2022).

[35] Ma Z H, Li Y. Parameter extraction and inverse design of semiconductor lasers based on the deep learning and particle swarm optimization method[J]. Optics Express, 28, 21971-21981(2020).

[36] Tang P, Chi X M, Chen B et al. Predictions of resonant mode characteristics for terahertz quantum cascade lasers with distributed feedback utilizing machine learning[J]. Optics Express, 29, 15309-15326(2021).

[37] Limbacher B, Schoenhuber S, Kainz M A et al. Deep learning control of THz QCLs[J]. Optics Express, 29, 23611-23621(2021).

[38] Olivier M, Gagnon M D, Piché M. Automated mode locking in nonlinear polarization rotation fiber lasers by detection of a discontinuous jump in the polarization state[J]. Optics Express, 23, 6738-6746(2015).

[39] Woodward R I, Kelleher E J R. Towards ‘smart lasers’: self-optimisation of an ultrafast pulse source using a genetic algorithm[J]. Scientific Reports, 6, 37616(2016).

[40] Fu X, Kutz J N. High-energy mode-locked fiber lasers using multiple transmission filters and a genetic algorithm[J]. Optics Express, 21, 6526-6537(2013).

[41] Pu G Q, Yi L L, Zhang L et al. Intelligent programmable mode-locked fiber laser with a human-like algorithm[J]. Optica, 6, 362-369(2019).

[42] Pu G Q, Zhang L, Hu W S et al. Automatic mode-locking fiber lasers: progress and perspectives[J]. Science China Information Sciences, 63, 160404(2020).

[43] Fu X, Brunton S L, Kutz J N. Classification of birefringence in mode-locked fiber lasers using machine learning and sparse representation[J]. Optics Express, 22, 8585-8597(2014).

[44] Brunton S L, Fu X, Kutz J N. Self-tuning fiber lasers[J]. IEEE Journal of Selected Topics in Quantum Electronics, 20, 464-471(2014).

[45] Baumeister T, Brunton S L, Nathan Kutz J. Deep learning and model predictive control for self-tuning mode-locked lasers[J]. Journal of the Optical Society of America B, 35, 617-626(2018).

[46] Yan Q Q, Deng Q H, Zhang J et al. Low-latency deep-reinforcement learning algorithm for ultrafast fiber lasers[J]. Photonics Research, 9, 1493-1501(2021).

[47] Pu G Q, Liu R M, Yang H et al. Fast predicting the complex nonlinear dynamics of mode-locked fiber laser by a recurrent neural network with prior information feeding[J]. Laser & Photonics Reviews, 2200363(2023).

[48] Zibar D, Brusin A M R, de Moura U C et al. Inverse system design using machine learning: the Raman amplifier case[J]. Journal of Lightwave Technology, 38, 736-753(2020).

[49] de Moura U C, Rosa Brusin A M, Carena A et al. Simultaneous gain profile design and noise figure prediction for Raman amplifiers using machine learning[J]. Optics Letters, 46, 1157-1160(2021).

[50] de Moura U C, Zibar D, Brusin A M R et al. Fiber-agnostic machine learning-based Raman amplifier models[J]. Journal of Lightwave Technology, 41, 83-95(2023).

[51] Chen Y F, Du J B, Huang Y T et al. Intelligent gain flattening in wavelength and space domain for FMF Raman amplification by machine learning based inverse design[J]. Optics Express, 28, 11911-11920(2020).

[52] Huang Y T, Du J B, Chen Y F et al. Machine learning assisted inverse design for ultrafine, dynamic and arbitrary gain spectrum shaping of Raman amplification[J]. Photonics, 8, 260(2021).

[53] Fan T Y. Laser beam combining for high-power, high-radiance sources[J]. IEEE Journal of Selected Topics in Quantum Electronics, 11, 567-577(2005).

[54] Liu Z J, Jin X X, Su R T et al. Development status of high power fiber lasers and their coherent beam combination[J]. Science China Information Sciences, 62, 1-32(2019).

[55] Chang H X, Chang Q, Xi J C et al. First experimental demonstration of coherent beam combining of more than 100 beams[J]. Photonics Research, 8, 1943-1948(2020).

[56] Ahn H K, Kong H J. Cascaded multi-dithering theory for coherent beam combining of multiplexed beam elements[J]. Optics Express, 23, 12407-12413(2015).

[57] Tünnermann H, Shirakawa A. Deep reinforcement learning for coherent beam combining applications[J]. Optics Express, 27, 24223-24230(2019).

[58] Shpakovych M, Maulion G, Kermene V et al. Experimental phase control of a 100 laser beam array with quasi-reinforcement learning of a neural network in an error reduction loop[J]. Optics Express, 29, 12307-12318(2021).

[59] Zhang X, Li P X, Zhu Y C et al. Coherent beam combination based on Q-learning algorithm[J]. Optics Communications, 490, 126930(2021).

[60] Hou T Y, An Y, Chang Q et al. Deep-learning-based phase control method for tiled aperture coherent beam combining systems[J]. High Power Laser Science and Engineering, 7, e59(2019).

[61] Hou T Y, An Y, Chang Q et al. Deep-learning-assisted, two-stage phase control method for high-power mode-programmable orbital angular momentum beam generation[J]. Photonics Research, 8, 715-722(2020).

[62] Liu R Q, Peng C, Liang X Y et al. Coherent beam combination far-field measuring method based on amplitude modulation and deep learning[J]. Chinese Optics Letters, 18, 041402(2020).

[63] Chang Q, An Y, Hou T Y et al. Phase-locking system in fiber laser array through deep learning with diffusers[C], M4A.96(2020).

[64] Feng G Y, Zhou T H, Gao C Q[M]. Laser mode field and beam quality characterization(2016).

[65] An Y. Beam characterization for few-mode fibers based on deep learning[D](2019).

[66] An Y, Huang L J, Li J et al. Learning to decompose the modes in few-mode fibers with deep convolutional neural network[J]. Optics Express, 27, 10127-10137(2019).

[67] An Y, Huang L, Li J et al. Deep learning-based real-time mode decomposition for multimode fibers[J]. IEEE Journal of Selected Topics in Quantum Electronics, 26, 4400806(2020).

[68] Fan X J, Ren F, Xie Y L et al. Mitigating ambiguity by deep-learning-based modal decomposition method[J]. Optics Communications, 471, 125845(2020).

[69] Rothe S, Zhang Q, Koukourakis N et al. Intensity-only mode decomposition on multimode fibers using a densely connected convolutional network[J]. Journal of Lightwave Technology, 39, 1672-1679(2020).

[70] Gao H, Chen Z, Zhang Y X et al. Rapid mode decomposition of few-mode fiber by artificial neural network[J]. Journal of Lightwave Technology, 39, 6294-6300(2021).

[71] Jiang M, An Y, Su R T et al. Deep mode decomposition: real-time mode decomposition of multimode fibers based on unsupervised learning[J]. IEEE Journal of Selected Topics in Quantum Electronics, 28, 0900207(2022).

[72] Tian Z C, Pei L, Wang J S et al. Physics-driven mode decomposition based on a training-free shallow neural network[J]. Optical Fiber Technology, 76, 103239(2023).

[73] Siegman A E. How to (maybe) measure laser beam quality[C], MQ1(1998).

[74] An Y, Li J, Huang L J et al. Deep learning enabled superfast and accurate M2 evaluation for fiber beams[J]. Optics Express, 27, 18683-18694(2019).

[75] Jiang M, An Y, Huang L J et al. M2 factor estimation in few-mode fibers based on a shallow neural network[J]. Optics Express, 30, 27304-27313(2022).

[76] Kokhanovskiy A, Bednyakova A, Kuprikov E et al. Machine learning-based pulse characterization in figure-eight mode-locked lasers[J]. Optics Letters, 44, 3410-3413(2019).

[77] Chen J B, Wang M, Xia W. Neural-network-assisted femtosecond laser pulse duration measurement using two-photon absorption[J]. Chinese Optics Letters, 18, 121901(2020).

[78] Geffert O, Kolbasova D, Trabattoni A et al. In situ characterization of few-femtosecond laser pulses by learning from first-principles calculations[J]. Optics Letters, 47, 3992-3995(2022).

[79] Zou L, Geng Y C, Liu B G et al. CNN-based neural network model for amplified laser pulse temporal shape prediction with dynamic requirement in high-power laser facility[J]. Optics Express, 30, 29885-29899(2022).

[80] Chryssolouris G[M]. Laser machining: theory and practice(2013).

[81] Mills B, Grant-Jacob J A. Lasers that learn: the interface of laser machining and machine learning[J]. IET Optoelectronics, 15, 207-224(2021).

[82] Rajaram N, Sheikh-Ahmad J, Cheraghi S H. CO2 laser cut quality of 4130 steel[J]. International Journal of Machine Tools and Manufacture, 43, 351-358(2003).

[83] Zhang Y Q, Chen W Z, Zhang X D et al. Synthetic evaluation and neural-network prediction of laser cutting quality[J]. Proceedings of SPIE, 5629, 237-246(2005).

[84] Klancnik S, Begic-Hajdarevic D, Paulic M et al. Prediction of laser cut quality for tungsten alloy using the neural network method[J]. Journal of Mechanical Engineering, 61, 714-720(2015).

[85] Courtier A F, McDonnell M, Praeger M et al. Modelling of fibre laser cutting via deep learning[J]. Optics Express, 29, 36487-36502(2021).

[86] Liu S K, Wu D, Luo Z Y et al. Measurement of pulsed laser welding penetration based on keyhole dynamics and deep learning approach[J]. Measurement, 199, 111579(2022).

[87] Masinelli G, Le-Quang T, Zanoli S et al. Adaptive laser welding control: a reinforcement learning approach[J]. IEEE Access, 8, 103803-103814(2020).

[88] Wang C, Tan X P, Tor S B et al. Machine learning in additive manufacturing: state-of-the-art and perspectives[J]. Additive Manufacturing, 36, 101538(2020).

[89] Su J L, Chen L Q, Tan C L et al. Progress in machine-learning-assisted process optimization and novel material development in additive manufacturing[J]. Chinese Journal of Lasers, 49, 1402101(2022).

[90] Caiazzo F, Caggiano A. Laser direct metal deposition of 2024 Al alloy: trace geometry prediction via machine learning[J]. Materials, 11, 444(2018).

[91] Tapia G, Khairallah S, Matthews M et al. Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel[J]. The International Journal of Advanced Manufacturing Technology, 94, 3591-3603(2018).

[92] Zhang M, Sun C N, Zhang X et al. High cycle fatigue life prediction of laser additive manufactured stainless steel: a machine learning approach[J]. International Journal of Fatigue, 128, 105194(2019).

[93] Garg A, Lam J S L. Measurement of environmental aspect of 3-D printing process using soft computing methods[J]. Measurement, 75, 210-217(2015).

[94] Garg A, Lam J S L, Savalani M M. A new computational intelligence approach in formulation of functional relationship of open porosity of the additive manufacturing process[J]. The International Journal of Advanced Manufacturing Technology, 80, 555-565(2015).

[95] Ren K, Chew Y, Zhang Y F et al. Thermal field prediction for laser scanning paths in laser aided additive manufacturing by physics-based machine learning[J]. Computer Methods in Applied Mechanics and Engineering, 362, 112734(2020).

[96] Xie T A, Grossman J C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties[J]. Physical Review Letters, 120, 145301(2018).

[99] Boolakee T, Heide C, Garzón-Ramírez A et al. Light-field control of real and virtual charge carriers[J]. Nature, 605, 251-255(2022).

[100] E W N. The dawning of a new era in applied mathematics[J]. Notices of the American Mathematical Society, 68, 565-571(2021).

[102] Liu Y. Special project of AI for science unveiled[N]. Science and Technology Daily.