A self-adapting fuzzy inference system for the evaluation of agricultural land

► The study integrates a genetic algorithm with a multi-criteria evaluation based fuzzy inference system. ► The criteria for land evaluation are encoded into chromosomes of the GA. ► The subsets in chromosomes are used as basic units in crossover and mutation. ► The GA-optimized model calibrates the original evaluation criteria by self-learning from land samples. ► 3 CV shows that the model is effective and robust.