Abstract: The BP model for mass evaluation of forestland was established by integrating the BP neural network with the mass appraisal method, and by dealing with the data of factors influencing upon the appraisal value of forestland assets.The generalization ability of BP network model was enhanced by estimating the regularization parameter with Bayesian method. The results showed that the BP neural network model based on Bayesian regularization was able to evaluate the value of forestland assets in batch, with an accurate result and good generalization ability.This model could provide the collective forestland assets evaluation with a new thinking and approach.