Specific Surface Area Characterization of Spinel Ferrite Nanostructure Based Compounds for Photocatalysis and Other Applications Using Extreme Learning Machine Method

Nanocrystalline spinel ferrite based compounds are technological driven materials with interesting potentials in photocatalysis for renewable energy generation, gas sensing pollution control, magnetic drug delivery, rod antennas, storage media (high density) and supercapacitive materials, among others. Specific surface area of contributes immensely to the application this semiconductor industrial domains. Experimental determination specific is laborious costly consumes appreciable time. Compositional substitutions crystal structure effectively improve physical properties enhance through alteration moment distribution between tetrahedral oxygen sites octahedral coordination. With aid distorted lattice parameters due compositional substitution nanocrystallite size as model descriptors, present work models nanomaterial extreme learning machine (ELM) intelligent modeling method. The developed sigmoid activation function-based ELM (S-ELM) shows superior performance over genetic algorithm support vector regression (GBSVR) stepwise (STWR) existing literature improvement 61.31% 70.01%, respectively, using root mean square error metric. significances cobalt lanthanum on nanomaterials were investigated S-ELM model. Ease implementation compared GBSVR model, coupled demonstrated improved persistent closeness its predictions experimental values, would be highly meritorious quick precise characterization various desired applications.