Abstract: The ionic rare earth in situ leaching process changes the mechanical properties of the soil, leading to an increased risk of landslides. To address the problems of low accuracy and large error in predicting slope displacement of rare earth mines in existing studies, the genetic algorithm was used to optimize the initial weights and thresholds of the BP neural network to build a new slope displacement prediction model for rare earth mines. Taking an ionic rare earth mine in Longnan, Jiangxi as the research object, a displacement meter was arranged in the mine to monitor the displacement changes of the whole process of rare earth mining in real time. At first, BP neural network was trained with 125 sets displacement monitoring data to build a prediction model, which was validated with 5 sets of data. Then the prediction model was optimized by GA-BP neural network. The predicted and measured values of the two prediction models were compared and error analyzed. The study showed that GA-BP neural network model could be used as an auxiliary means for slope displacement monitoring and analysis of rare earth mines when the mean relative error, mean absolute error, mean square error and mean absolute percentage error were reduced to 1/3 of those before optimization.