Accurate recognition of the reproductive development status and prediction of oviposition fecundity in Spodoptera frugiperda (Lepidoptera: Noctuidae) based on computer vision

Spodoptera frugiperda (Lepidoptera: Noctuidae) is an important migratory agricultural pest worldwide, which has invaded many countries in the Old World since 2016 and now poses a serious threat to world food security. The present monitoring and early warning strategies for the fall army worm (FAW) mainly focus on adult population density, but lack an information technology platform for precisely forecasting the reproductive dynamics of the adults. In this study, to identify the developmental status of the adults, we first utilized female ovarian images to extract and screen five features combined with the support vector machine (SVM) classifier and employed male testes images to obtain the testis circular features. Then, we established models for the relationship between oviposition dynamics and the developmental time of adult reproductive organs using laboratory tests. The results show that the accuracy of female ovary development stage determination reached 91%. The mean standard error (MSE) between the actual and predicted values of the ovarian developmental time was 0.2431, and the mean error rate between the actual and predicted values of the daily oviposition quantity was 12.38%. The error rate for the recognition of testis diameter was 3.25%, and the predicted and actual values of the testis developmental time in males had an MSE of 0.7734. A WeChat applet for identifying the reproductive developmental state and predicting reproduction of S. frugiperda was developed by integrating the above research results, and it is now available for use by anyone involved in plant protection. This study developed an automated method for accurately forecasting the reproductive dynamics of S. frugiperda populations, which can be helpful for the construction of a population monitoring and early warning system for use by both professional experts and local people at the county level.