Abstract: The planting suitability analysis of tropical fruit trees is of great significance for the development of tropical fruit trees and the reduction of disasters’ effect. Aimed at the problem of low adaptability of statistical methods, it is proposed a method for the suitability evaluation of tropical fruit trees planting which combining the improved genetic algorithm and Error Back Propagation neural network (hereinafter referred to as GA-BP neural network method). The adaptive algorithm is firstly used to improve the crossover probability and mutation probability of GA. Then the initial weights and thresholds of BP neural network are optimized by GA algorithm. On this basis, BP neural network is further studied to obtain the solution satisfying the error requirement. The GA-BP neural network was compared with the traditional BP neural network on the twonorm dataset, and the planting suitability analysis of tropical fruit trees was carried out based on actual meteorological data. The experimental results show that the classification accuracy of GA-BP neural network is about 4 percentage points higher than that of traditional BP neural network, and Network training time decreased about 3 steps, This method is valuable for the analysis and evaluation of planting suitability of tropical fruit trees.