Abstract: Aiming at the ecological problems such as vegetation damage and soil erosion in the mining area, a mining area in Luoyang, Henan province is used as the research object.The PSR model is used to construct the ecological safety evaluation index system of the mining area to evaluate the ecological security of the mining area from 2008 to 2017.Combining the advantages of genetic algorithm and Elman neural network, the genetic algorithm is used to optimize the weight and threshold of neural network, and the GA-Elman prediction model is constructed to predict and analyze the ecological security trend of mining area from 2018 to 2025.The results show that the comprehensive ecological security index of the mining area from 2008 to 2017 shows a W-shaped curve, which changes from a moderately unsafe level to a mild unsafe level.From 2018 to 2025, the overall ecological security of the mining area is on the rise, basically at a safer level.