Forecasting severe grape downy mildew attacks using machine learning.
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2020
2020
Historique:
received:
09
08
2019
accepted:
25
02
2020
entrez:
13
3
2020
pubmed:
13
3
2020
medline:
23
6
2020
Statut:
epublish
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 vineyards 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, precipitation 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 temperatures 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%.
Identifiants
pubmed: 32163490
doi: 10.1371/journal.pone.0230254
pii: PONE-D-19-22557
pmc: PMC7067461
doi:
Substances chimiques
Fungicides, Industrial
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0230254Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Occup Environ Med. 1995 Sep;52(9):587-92
pubmed: 7550798
J Stat Softw. 2010;33(1):1-22
pubmed: 20808728
Phytopathology. 2009 Aug;99(8):930-42
pubmed: 19594312
J Environ Monit. 2010 Sep;12(9):1650-7
pubmed: 20697628
Phytopathology. 2005 Dec;95(12):1445-52
pubmed: 18943556
Eur J Epidemiol. 2017 Mar;32(3):203-216
pubmed: 28185034
Plant Dis. 2000 May;84(5):549-554
pubmed: 30841347
Am J Epidemiol. 2016 Mar 1;183(5):415-22
pubmed: 26893297
Biol Lett. 2018 May;14(5):
pubmed: 29769297
Curr Opin Plant Biol. 2016 Aug;32:101-109
pubmed: 27471781
J Environ Manage. 2009 May;90 Suppl 2:S139-46
pubmed: 19128870
Pest Manag Sci. 2015 Sep;71(9):1247-57
pubmed: 25264219
Med Biol Eng Comput. 2000 Jan;38(1):109-12
pubmed: 10829400
Phytopathology. 2019 May;109(5):787-795
pubmed: 30376440
Annu Rev Phytopathol. 2006;44:489-509
pubmed: 16722808
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Plant Dis. 2010 Jun;94(6):709-716
pubmed: 30754303
Environ Int. 2015 Jan;74:291-303
pubmed: 25454246
Environ Health Perspect. 2001 Aug;109(8):839-44
pubmed: 11564621
Plant Dis. 2016 Feb;100(2):241-251
pubmed: 30694129
Occup Environ Med. 2011 Feb;68(2):108-15
pubmed: 21097948