Abstract
Titanium dioxide (TiO2) semiconductor is characterized with a wide band gap and attracts a significant attention for several applications that include solar cell carrier transportation and photo-catalysis. The tunable band gap of this semiconductor coupled with low cost, chemical stability and non-toxicity make it indispensable for these applications. Structural distortion always accompany TiO2 band gap tuning through doping and this present work utilizes the resulting structural lattice distortion to estimate band gap of doped TiO2 using support vector regression (SVR) coupled with novel gravitational search algorithm (GSA) for hyper-parameters optimization. In order to fully capture the non-linear relationship between lattice distortion and band gap, two SVR models were homogeneously hybridized and were subsequently optimized using GSA. GSA-HSVR (hybridized SVR) performs better than GSA-SVR model with performance improvement of 57.2% on the basis of root means square error reduction of the testing dataset. Effect of Co doping and Nitrogen-Iodine co-doping on band gap of TiO2 semiconductor was modeled and simulated. The obtained band gap estimates show excellent agreement with the values reported from the experiment. By implementing the models, band gap of doped TiO2 can be estimated with high level of precision and absorption ability of the semiconductor can be extended to visible region of the spectrum for improved properties and efficiency.
Highlights
Fabrication of titanium dioxide (TiO2) semiconductor of desired band gap still remains a challenge in the field of material sciences for photo-catalysis application.[1]
Sixty-three experimental data-points consisting of crystal lattice parameters and the corresponding band gaps were used in training and validating the algorithms through which the proposed gravitational search algorithm (GSA)-hybridized SVR (HSVR) and GSA-support vector regression (SVR) models were developed
Correlation cross-plots between the estimated band gaps using GSA-SVR and GSA-HSVR model and experimental values for testing set of data is presented in fig.[6]
Summary
Since the accuracy of SVR-based model is affected by the proper selection of its hyperparameters, these hyper-parameters were optimized using a novel gravitational search optimization algorithm (GSA) that is developed based on gravitational law and mass interaction.[26] The developed model, GSA- HSVR, has two stages of implementation; the first stage uses the crystal structural lattice parameters as the descriptors to SVR algorithm (resulting in GSA-SVR) while the estimated band gap of the first stage serves as the descriptor to the second SVR algorithm (leading to GSAHSVR). Evaluation of the generalization capacity of the developed GSA-HSVR model to unseen data shows that the model can effectively estimate the band gap of doped TiO2 with mean absolute error as low as 0.07eV when validated using unseen dataset This precision demonstrated by the proposed model is of high significance in band gap engineering and can effectively improve photo-catalytic activity of TiO2 semiconductor for better performance and efficiency
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
