The health of forests affects directly global ecological stability and sustainable development.The prediction of forest health is an important means for people to understand forest health status.Based on the selected indicators of forest health,a model has been constructed to predict the health of Jiufeng National Forest Park using a three-layer BP neural network.The results show that the adoption of neural network in forest ecosystem health forecasting was reasonable and reliable.Some important conclusions and recommendations have also been given for constructing a precise and stable prediction model.