Given the continuous growth in demand for ornamental flowers, flower bases are facing the dual challenge of scientifically planning planting layouts to enhance both aesthetic value and economic benefits. The aim of this study is to combine neural network and genetic algorithm to establish a flower base layout optimization model to solve this need. Through the collection and analysis of flower planting data, the input parameters of the model are defined, and the corresponding neural network structure and genetic algorithm flow are designed to optimize the flower layout. The experimental results show that the aesthetic value of the optimized flower base is significantly improved, the economic growth is significant, and the satisfaction of tourists is improved. This research not only confirms the legitimacy of the proposed framework, but also introduces a fresh viewpoint and tool for overseeing flower cultivation. It advocates for the implementation of scientific managerial approaches in the field of horticulture and encourages the enduring growth of flower cultivation.