Enhanced grey wolf algorithm for automatic tuning of an ensemble neural network in predicting PCF optical properties.

The structural characteristics of photonic crystal fibers (PCFs) determine their optical properties. This paper introduces an enhanced Grey Wolf Optimization algorithm termed ACD-GWO, which proposes adaptive strategies, chaotic mapping and dimension-based approaches and integrates them into the Grey Wolf Optimization framework. The aim is to achieve efficient automatic adjustment of hyperparameters and architecture for ensemble neural networks. The resulting ensemble neural network demonstrates accurate and rapid prediction of optical properties in PCFs, including effective refractive index, effective mode area, dispersion, and confinement loss, based on the PCF's structural characteristics. Compared to random forest and feedforward neural network models, the ensemble neural network achieves higher accuracy with a mean squared error of 3.78 × 10-6. Additionally, the computational time is significantly reduced, with only 2.27 minutes required for training and 0.08 seconds for prediction, which is much faster than numerical simulation software. This will provide new possibilities for optical device design and performance optimization, driving cutting-edge research and practical applications in the field of optics.

Controlled generation of soliton spectral tunneling by double pulses injection.

Numerical simulations of a simple and direct method to generate soliton spectral tunneling (SST) based on two input pulses are reported in the paper. An intense pump pulse and a weak probe pulse with a time delay are transmitted in a photonic crystal fiber with three zero-dispersion wavelengths. Our results demonstrate that the distance and the state of soliton tunneling are obviously influenced by the probe-pump delay. Therefore, the velocity and efficiency of SST can be effectively regulated by varying the relative time delay, thus affecting the SST formation. This scenario appears promising for designing a "soliton ejector", in which real-time control of the soliton ejection process can be achieved through phase modulation between pulses.

Accurately Shaping Supercontinuum Spectrum via Cascaded PCF.

Shaping is very necessary in order to obtain a wide and flat supercontinuum (SC). Via numerical simulations, we accurately demonstrated shaping the SC using the fiber cascading method to significantly increase the width as well as the flatness of the spectrum in silica photonic crystal fiber (PCF). The cascaded PCF contains two segments, each of which has dual zero-dispersion frequencies (ZDFs). The spectral range of the SC can be expanded tremendously by tuning the spacing between the two ZDFs of the first segmented cascaded PCF. Increasing the pump power generates more solitons at the red edge, which accelerates solitons trapping and improves the spectral flatness of the blue edge. Furthermore, cascading the second segmented PCF by choosing appropriate fiber parameters ensures the flatness of the red end of SC. Therefore, a cost-effective alternative method for broad and flat supercontinuum generation in the near-infrared range is proposed here, which can be implemented easily in any photonics laboratory, where dual ZDFs PCFs are commonly found.