Research on Forecasting Flowering Phase of Pear Tree Based on Neural Network

Predicting the blooming season of ornamental plants is significant for guiding adjustments in production decisions and providing viewing periods and routes.The current strategies for observation of ornamental plant booming periods are mainly based on manpower and experience,which have problems such as inaccurate recognition time,time-consuming and energy sapping.Therefore,this paper proposes a neural network-based method for predicting the flowering phase of pear tree.Firstly,based on the meteorological observation data of Shijiazhuang Meteorological Station from 2000 to 2019,three principal components(the temperature factor,weather factor,and humidity factor)with high correlation coefficient with the flowering phase of pear tree are obtained by using the principal component analysis method.Then,the three components are used as input factors for the BP neural network.A BP neural network prediction model is constructed based on genetic algorithm optimization.The crossover operator and mutation operator in the adaptive genetic algorithm are improved.Finally,the meteorological sample data from 2013 to 2019 are used to test and verify the algorithm in this paper.The results demonstrate that,the model can solve the local optimization problem of the BP neural network model.The prediction results of the flowering phase of pear tree are evaluated in terms of relevance and prediction accuracy.Both are superior to the traditional effective accumulated temperature and the prediction results of the stepwise regression method.This method can provide more reliable forecast information for the blooming period,which can provide decision-making reference for improving the development of tourism industry.

Seed and Wasp Production in the Mutualism of Figs and Fig Wasps

Figs (Moracea: Ficus) and fig wasps (Hymenoptera: Chlocloids: Agaonideae) depend on each other to complete their reproduction. Monoecious fig species and their pollinating wasps are in conflict over the use of fig ovaries which can either produce one seed or one wasp. From observation on Ficus virens Ait., we showed that female flowers with outer layer of ovaries (near to the wall of syconium) had no significant difference from that with inner and interval layer of ovaries (near to the syconium cavity), in which most seeds and wasps were produced. This meant that fig tree provided the same potential resource for seed and wasps production. Observation indicated that there was usually only one foundress in syconium at female flower phase and no com- petition pollinators. Measurement of the style length of female flowers and the ovipositor of pollinators indicated that most ovaries could be reached by pollinator’s ovipositor. However, at the male flower phase, production of seeds was significantly more than that of wasps including non-pollinating wasps but there was no significant difference between seed and pollinating wasp production when without non-pollinating wasps produced. This result indicated that non-pollinating wasps competed ovaries not with seeds but with pollinating wasps for ovipositing. Bagged experiment showed that the sampling fig species was not self-sterile which was important for figs and wasps to survive bad season. Seed production in self-pollinated figs was not significantly different from total wasps in- cluding non-pollinating ones. This might be related with the weaker competition among wasps since bagged figs were not easy to reach by wasps from outside.