Artificial neural networks as a tool for seasonal forecast of attack intensity of Spodoptera spp. in Bt soybean.

Soybean (Glycine max) is the world's most cultivated legume; currently, most of its varieties are Bt. Spodoptera spp. (Lepidoptera: Noctuidae) are important pests of soybean. An artificial neural network (ANN) is an artificial intelligence tool that can be used in the study of spatiotemporal dynamics of pest populations. Thus, this work aims to determine ANN to identify population regulation factors of Spodoptera spp. and predict its density in Bt soybean. For two years, the density of Spodoptera spp. caterpillars, predators, and parasitoids, climate data, and plant age was evaluated in commercial soybean fields. The selected ANN was the one with the weather data from 25 days before the pest's density evaluation. ANN forecasting and pest densities in soybean fields presented a correlation of 0.863. It was found that higher densities of the pest occurred in dry seasons, with less wind, higher atmospheric pressure and with increasing plant age. Pest density increased with the increase in temperature until this curve reached its maximum value. ANN forecasting and pest densities in soybean fields in different years, seasons, and stages of plant development were similar. Therefore, this ANN is promising to be implemented into integrated pest management programs in soybean fields.

Mapping Brazilian Expansion Risk Levels of Mango Weevil (Sternochetus mangiferae Fabricius) Based on MaxEnt.

The mango weevil, Sternochetus mangiferae (Fabricius) (Curculionidae), pest present in Brazil and is restricted to some municipalities in the Rio de Janeiro State. This curculionid attacks the mango crop exclusively and puts mango production globally at risk, especially those destined for export. Using ecological modeling tools, this study is the first to map the potential risk of S. mangiferae in Brazil. We aimed to identify the potential distribution of this pest in Brazilian states, drawing up thematic maps of regions that present suitable and unsuitable climatic conditions for the establishment of the pest using the MaxEnt ecological niche model. The average annual temperature, the annual precipitation, the average daytime temperature range, and the annual temperature range were the variables that contributed most to the selected model. The MaxEnt model predicted highly suitable areas for S. mangiferae throughout the Brazilian coast, especially on the northeast coast. The region responsible for more than 50% of mango production in Brazil, the São Francisco Valley, was classified by the model with suitability for the pest; it can impacts exportations due to the imposition of phytosanitary barriers. This information can be used in strategies to prevent the introduction and establishment of this pest in new areas and monitor programs in areas with recent occurrence. In addition, the model results can be used in future research plans on S. mangiferae in worldwide modeling studies and climate change scenarios.