Models Applied to Grapevine Pests: A Review

Climate change and the potential distribution of the glassy-winged sharpshooter (Homalodisca vitripennis), an insect vector of Xylella fastidiosa

Biological invasions represent a major threat for biodiversity and agriculture. Despite efforts to restrict the spread of alien species, preventing their introduction remains the best strategy for an efficient control. In that context preparedness of phytosanitary authorities is very important and estimating the geographical range of alien species becomes a key information. The present study investigates the potential geographical range of the glassy-winged sharpshooter (Homalodisca vitripennis), a very efficient insect vector of Xylella fastidiosa, one of the most dangerous plant-pathogenic bacteria worldwide. We use species distribution modeling (SDM) to analyse the climate factors driving the insect distribution and we evaluate its potential distribution in its native range (USA) and in Europe according to current climate and different scenarios of climate change: 6 General Circulation Models (GCM), 4 shared socioeconomic pathways of gas emission and 4 time periods (2030, 2050, 2070, 2090). The first result is that the climate conditions of the European continent are suitable to the glassy-winged sharpshooter, in particular around the Mediterranean basin where X. fastidiosa is present. Projections according to future climate conditions indicate displacement of climatically suitable areas towards the north in both North America and Europe. Globally, suitable areas will decrease in North America and increase in Europe in the coming decades. SDM outputs vary according to the GCM considered and this variability indicated areas of uncertainty in the species potential range. Both potential distribution and its uncertainty associated to future climate projections are important information for improved preparedness of phytosanitary authorities.

Big Data and Machine Learning to Improve European Grapevine Moth (Lobesia botrana) Predictions

Machine Learning (ML) techniques can be used to convert Big Data into valuable information for agri-environmental applications, such as predictive pest modeling. Lobesia botrana (Denis & Schiffermüller) 1775 (Lepidoptera: Tortricidae) is one of the main pests of grapevine, causing high productivity losses in some vineyards worldwide. This work focuses on the optimization of the Touzeau model, a classical correlation model between temperature and L. botrana development using data-driven models. Data collected from field observations were combined with 30 GB of registered weather data updated every 30 min to train the ML models and make predictions on this pest's flights, as well as to assess the accuracy of both Touzeau and ML models. The results obtained highlight a much higher F1 score of the ML models in comparison with the Touzeau model. The best-performing model was an artificial neural network of four layers, which considered several variables together and not only the temperature, taking advantage of the ability of ML models to find relationships in nonlinear systems. Despite the room for improvement of artificial intelligence-based models, the process and results presented herein highlight the benefits of ML applied to agricultural pest management strategies.