Extreme learning machine computational method of modeling energy gap of doped zinc selenide nano-material semiconductor

Zinc selenide (ZnSe) semiconductor belongs to a class of wide energy gap material with low visible region optical absorption, high optical coefficient (nonlinear) and fascinating optoelectronic as well as photocatalytic features which foster and strengthen its applications in resisting thermal shock, photoelectric fields (which include dielectric mirrors, shot wavelength lasers and light emitting diode), buffer layer of solar cell and many photo catalytic environmental cleanliness applications. Nanostructured ZnSe semiconductors occupy a special place in application domain due to the characteristic features attached to the crystallite size of the material which include high fluorescence quantum yields, solvent dispersibility and adjustable emission color among others. Effective utilization of nanostructured ZnSe semiconductor involves tuning of its energy gap through doping mechanisms which is accompanied with distortion in the parent lattice structure. In this contribution, extreme learning machine (ELM) computational intelligent method is proposed for predicting the band gap energy of doped ZnSe nanostructured semiconductor using the material crystallite size and lattice parameter as descriptors to the models. The developed ELM based model using sine (Sine), sigmoid (Sig) and transig (Trang) activation functions were compared with the existing SVR-GA and SPR models in the literature using various performance metrics. The developed Sine-ELM model shows superior performance over Sig-ELM, Trang-ELM, SVR-GA (2021) and SPR (2021) models with performance improvement of 12.74%, 64.89%, 68.87% and 75.62% using mean squared error (MSE) metric for testing data samples. The superiority of the model developed was further justified through validation with external set of data. The precision and superiority of the ELM based models developed would eventually ease quick characterization and tuning of energy gap of ZnSe nanostructured semiconductors for various applications.

Automated summary

In this paper, an extreme learning machine (ELM) computational intelligent method is proposed to predict the band gap energy of doped ZnSe nanostructured semiconductor using the material crystallite size and lattice parameter as descriptors. The developed ELM model with sine activation function shows superior performance compared to other models and its superiority is further justified through validation with external data. This is of great importance for quick characterization and tuning of energy gap of ZnSe nanostructured semiconductors.