Modeling heavy-ion fusion cross section data via a novel artificial intelligence approach

Abstract We perform a comprehensive analysis of complete fusion cross section data with the aim to derive, in completely data-driven way, model suitable predict integrated between light-to-medium mass nuclei at above barrier energies. To this end, we adopted novel artificial intelligence approach, based on hybridization genetic programming and neural networks, capable derive an analytical for description experimental data. The approach enables global search computationally simple models over several variables considerable body nuclear derived phenomenological formula can serve reproduce trend large variety light intermediate collision systems energy domain ranging approximately from Coulomb onset multi-fragmentation phenomena.