Forecasting severe grape downy mildew attacks using machine learning

Chen Mathilde, Brun François, Raynal Marc, Makowski David. 2020. Forecasting severe grape downy mildew attacks using machine learning. PloS One, 15 (3):e0230254, 20 p.

Quartile : Q2, Sujet : MULTIDISCIPLINARY SCIENCES

Liste HCERES des revues (en SHS) : oui

Thème(s) HCERES des revues (en SHS) : Psychologie-éthologie-ergonomie; Staps

Résumé : Grape downy mildew (GDM) is a major disease of grapevine that has an impact on both the yields of the vines and the quality of the harvested fruits. The disease is currently controlled by repetitive fungicide treatments throughout the season, especially in the Bordeaux vine- yards where the average number of fungicide treatments against GDM was equal to 10.1 in 2013. Reducing the number of treatments is a major issue from both an environmental and a public health point of view. One solution would be to identify vineyards that are likely to be heavily attacked in spring and then apply fungicidal treatments only to these situations. In this perspective, we use here a dataset including 9 years of GDM observations to develop and compare several generalized linear models and machine learning algorithms predicting the probability of high incidence and severity in the Bordeaux region. The algorithms tested use the date of disease onset and/or average monthly temperatures and precipitation as input variables. The accuracy of the tested models and algorithms is assessed by year-by- year cross validation. LASSO, random forest and gradient boosting algorithms show better performance than generalized linear models. The date of onset of the disease has a greater influence on the accuracy of forecasts than weather inputs and, among weather inputs, pre- cipitation has a greater influence than temperature. The best performing algorithm was selected to evaluate the impact of contrasted climate scenarios on GDM risk levels. Results show that risk of GDM at bunch closure decreases with reduced rainfall and increased tem- peratures in April-May. Our results also show that the use of fungicide treatment decision rules that take into account local characteristics would reduce the number of treatments against GDM in the Bordeaux vineyards compared to current practices by at least 50%.

Mots-clés Agrovoc : fongicide, système d'aide à la décision, avertissement agricole, vigne, apprentissage machine

Mots-clés géographiques Agrovoc : France

Mots-clés libres : Fungicide, Epidemiology, Grapes, Rain, Risk factors, Leaves, Downy mildew, Machine Learning

Agences de financement hors UE : Ministère de l'Agriculture et de l'Alimentation, Institut Carnot Plant2Pro, Agence Nationale de la Recherche

Projets sur financement : (FRA) SMART-PIC, (FRA) Institut Convergences en Agriculture Numérique

Auteurs et affiliations

• Chen Mathilde, Université Paris Cité (FRA) ORCID: 0000-0002-5982-2143 - auteur correspondant
• Brun François, ACTA (FRA)
• Raynal Marc, IFV (FRA)
• Makowski David, Université Paris-Saclay (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/611344/)

Métriques

[ Page générée et mise en cache le 2024-12-23 ]