Prediction of deep learning for spectrum-pulse width on petawatt laser

The spectrum is a crucial parameter to a petawatt laser which is adopting the chirped pulse amplification technique. In such complex systems with high gain and wide spectrum bandwidth, the shape of the spectrum is crucial to the final output pulse width. In daily operation, the width of the compressed pulse will have some abnormal fluctuation, and the shape of the spectrum before compressed is also changed at the same shot. It will mislead the power and intensity estimation in laser-matter interaction experiments. So far, no theory has been able to analyze the relationship between spectrum and pulse width completely. Because it is hard to describe the fluctuation of the compressed pulse width which the online measure spectral phase in the high power laser system is difficult. In this paper, we first found and analyzed the relation between spectral variation and pulse width in the petawatt laser. With the support of existing data, we establish an end-toend deep learning model to map the petawatt laser’s spectrum before the compressor to the compressed pulse width. The deep learning scheme which based on Bayesian Neural Network (BNN) can provide an estimate of uncertainty as a function of pulse width to improve the accuracy of the model. After 20000 iterations, the Mean Square Error (MSE) is reduced to 0.08 in the validation test. Under the experiment, the model realizes an effective predict of the compressed pulse width. With the help of deep learning, we can get more information on the spectrum rather than the center wavelength and spectrum width to predict the compressed pulse width. It should be emphasized that this method will help to avoid unstable pulse output caused by an abnormal spectrum and to improve the operating efficiency of the petawatt laser system.

[1]  H T Powell,et al.  Petawatt laser pulses. , 1999, Optics letters.

[2]  Edmund Y. Lam,et al.  Learning-based nonparametric autofocusing for digital holography , 2018 .

[3]  Guohai Situ,et al.  eHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstruction. , 2018, Optics express.

[4]  John A. Caird,et al.  An overview of LLNL high-energy short-pulse technology for advanced radiography of laser fusion experiments , 2004 .

[5]  Accuracy of single-shot autocorrelation measurements of petawatt laser pulses. , 2012, Applied optics.

[6]  Xiantu He,et al.  Review of the current status of fast ignition research at the IAPCM , 2014, High Power Laser Science and Engineering.

[7]  T. Winstone,et al.  Review of laser diagnostics at the Vulcan laser facility , 2015, High Power Laser Science and Engineering.

[8]  D. D. Meyerhofer,et al.  Propagation of light pulses in a chirped-pulse-amplification laser , 1993 .

[9]  Marco Galimberti,et al.  The Vulcan 10 PW project , 2010 .

[10]  X. Ouyang,et al.  Temporal characterization of petawatt class laser at Shen Guang II facility. , 2016, Applied optics.

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Jens Limpert,et al.  Petawatt and exawatt class lasers worldwide , 2019, High Power Laser Science and Engineering.

[13]  Zunqi Lin,et al.  Analysis and construction status of SG-II 5PW laser facility , 2018, High Power Laser Science and Engineering.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Craig W. Siders,et al.  Active learning with deep Bayesian neural network for laser control , 2018, Optical Engineering + Applications.

[16]  Mike C. Nostrand,et al.  Characterization and repair of small damage sites and their impact on the lifetime of fused silica optics on the National Ignition Facility , 2018, Laser Damage.

[17]  Tao Wang,et al.  1 kJ Petawatt Laser System for SG-II-U Program , 2008 .

[18]  Dean Liu,et al.  Status and development of high-power laser facilities at the NLHPLP , 2018, High Power Laser Science and Engineering.

[19]  P. B. Radha,et al.  Polar direct drive – Ignition at 1 MJ , 2006 .

[20]  Tarek M. Taha,et al.  Optical beam classification using deep learning: a comparison with rule- and feature-based classification , 2017, Optical Engineering + Applications.

[21]  J Luce,et al.  1.15 PW-850 J compressed beam demonstration using the PETAL facility. , 2017, Optics express.