Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm
This addresses the challenge of predicting energetically optimal crystal structures for materials science, representing a strong specific gain rather than a foundational advancement.
The paper tackled crystal structure prediction by introducing ParetoCSP, a novel algorithm combining a multi-objective genetic algorithm with a neural network potential, which outperformed a state-of-the-art method by a factor of 2.562 across 55 benchmark structures.
While crystal structure prediction (CSP) remains a longstanding challenge, we introduce ParetoCSP, a novel algorithm for CSP, which combines a multi-objective genetic algorithm (MOGA) with a neural network inter-atomic potential (IAP) model to find energetically optimal crystal structures given chemical compositions. We enhance the NSGA-III algorithm by incorporating the genotypic age as an independent optimization criterion and employ the M3GNet universal IAP to guide the GA search. Compared to GN-OA, a state-of-the-art neural potential based CSP algorithm, ParetoCSP demonstrated significantly better predictive capabilities, outperforming by a factor of $2.562$ across $55$ diverse benchmark structures, as evaluated by seven performance metrics. Trajectory analysis of the traversed structures of all algorithms shows that ParetoCSP generated more valid structures than other algorithms, which helped guide the GA to search more effectively for the optimal structures