Estimation of surface energies of face-centred cubic metals using computational intelligence technique

Abstract

There are numerous challenges associated with the experimental determination of average surface energies of materials despite the significances of material surface energy in understanding oxidation, catalysis, corrosion, crystal growth and adsorption. This research work aims at circumventing these challenges by developing a computational intelligent model using support vector regression (SVR) with test-set-cross validation optimisation technique. SVR-based model was developed by training and testing SVR using experimental data of selected thirty-four periodic metals. The developed SVR-based model was used to estimate average surface energies of face-centred cubic (fcc) metals and the obtained values were compared with the available experimental results. Average surface energies obtained from the developed SVR-based model show consistent closeness with the experimental values than the results of other existing theoretical models. The accuracy attained by the developed model shows its excellent potential in circumventing the difficulties associated with experimental determination of average surface energies of materials.