[Objective]  To develop a model to predict the abundance of larvae of the next generation of Dendrolimus punctatus from the number of adults caught in light traps. [Methods]  For five consecutive years from 2013-2017 the number of adult females and males captured in light-traps, and the sex ratio of the overwintering and first generations of D. punctatus, were collected. During the same period the abundance (density) of the first and second (overwintering) larval generations were investigated in the field. Factors correlated with the abundance of the next larval generation, such as the number of adults, and sex ratio, were identified using Excel 2016. A predictive model using neural networks was established with Matlab 2016. [Results]  The predictive model had a better than 0.92 fit to the actual data and was more than 0.90 accurate. [Conclusion]  The Matlab model for predicting the abundance of the next larval generation of D. punctatus on the basis of adult light trapping data is very suitable for short-term, fine prediction. This method is simple and practical, and worth popularizing for the control of D. punctatus.