Abstract
[Display omitted]
•Hybrid GABSVR model is developed for strontium titanate energy gap estimation.•SRA model is developed for controlling energy gap of strontium titanate.•GABSVR model outperforms SRA model using various error metrics.•The influence doping and co-doping on energy gap of strontium titanate is explored.
Strontium titanate semiconductor is multi-functional metallic oxide with perovskite structure and wide range of applications in oxygen gas sensors (in storage batteries), superconductivity, ferro-electricity, dielectric constant materials, dye-sensitized solar cells photo-electrodes, optoelectronics applications and photocatalysis. The wide band gap of strontium titanate metal oxide constrains its response to ultraviolent light with light harvesting capacity of 5% for incoming solar energy in generating photocatalytic activity. Anions and cations incorporation into the parent strontium titanate compound strongly break the semiconductor symmetry and ultimately influence the energy gap with stretches as well as distortions in perovskite structural architecture. This work develops genetic algorithm based support vector regression (GABSVR) hybrid model and stepwise regression algorithm (SRA) for modeling the energy gap of distorted strontium titanate semiconductor using structural lattice constants and the size of its nano-particles as model descriptors. The developed GABSVR model performs better than SRA model with performance improvement of 62.98%, 79.12% and 81.05% using coefficient of correlation (CC), mean absolute error (MAE) and root mean square error (RMAE) metrics, respectively. The developed model investigates the influence of preparation method, silver dopants, nitrogen dopants and sulfur incorporation on energy gap of strontium titanate photocatalytic activity. The developed GABSVR model was further validated externally for determining the significance of cobalt dopants on the activity of strontium titanate and the obtained energy gaps agree well with the measured values. High level of precision demonstrated by the developed hybrid model is of enormous significance for strengthening light harvesting capacity of the semiconductor for optoelectronics and photocatalysis applications.