Modelling the monthly abundance of Culicoides biting midges in nine European countries using Random Forests machine learning.
Culicoides abundance
Culicoides seasonality
Environmental variables
Europe
Random Forest machine learning
Spatial predictions
Journal
Parasites & vectors
ISSN: 1756-3305
Titre abrégé: Parasit Vectors
Pays: England
ID NLM: 101462774
Informations de publication
Date de publication:
15 Apr 2020
15 Apr 2020
Historique:
received:
21
05
2019
accepted:
30
03
2020
entrez:
17
4
2020
pubmed:
17
4
2020
medline:
6
6
2020
Statut:
epublish
Résumé
Culicoides biting midges transmit viruses resulting in disease in ruminants and equids such as bluetongue, Schmallenberg disease and African horse sickness. In the past decades, these diseases have led to important economic losses for farmers in Europe. Vector abundance is a key factor in determining the risk of vector-borne disease spread and it is, therefore, important to predict the abundance of Culicoides species involved in the transmission of these pathogens. The objectives of this study were to model and map the monthly abundances of Culicoides in Europe. We obtained entomological data from 904 farms in nine European countries (Spain, France, Germany, Switzerland, Austria, Poland, Denmark, Sweden and Norway) from 2007 to 2013. Using environmental and climatic predictors from satellite imagery and the machine learning technique Random Forests, we predicted the monthly average abundance at a 1 km The predictive power of the resulting models varied according to month and the Culicoides species/ensembles predicted. Model performance was lower for winter months. Performance was higher for the Obsoletus ensemble, followed by the Pulicaris ensemble, while the model for Culicoides imicola showed a poor performance. Distribution and abundance patterns corresponded well with the known distributions in Europe. The Random Forests model approach was able to distinguish differences in abundance between countries but was not able to predict vector abundance at individual farm level. The models and maps presented here represent an initial attempt to capture large scale geographical and temporal variations in Culicoides abundance. The models are a first step towards producing abundance inputs for R
Sections du résumé
BACKGROUND
BACKGROUND
Culicoides biting midges transmit viruses resulting in disease in ruminants and equids such as bluetongue, Schmallenberg disease and African horse sickness. In the past decades, these diseases have led to important economic losses for farmers in Europe. Vector abundance is a key factor in determining the risk of vector-borne disease spread and it is, therefore, important to predict the abundance of Culicoides species involved in the transmission of these pathogens. The objectives of this study were to model and map the monthly abundances of Culicoides in Europe.
METHODS
METHODS
We obtained entomological data from 904 farms in nine European countries (Spain, France, Germany, Switzerland, Austria, Poland, Denmark, Sweden and Norway) from 2007 to 2013. Using environmental and climatic predictors from satellite imagery and the machine learning technique Random Forests, we predicted the monthly average abundance at a 1 km
RESULTS
RESULTS
The predictive power of the resulting models varied according to month and the Culicoides species/ensembles predicted. Model performance was lower for winter months. Performance was higher for the Obsoletus ensemble, followed by the Pulicaris ensemble, while the model for Culicoides imicola showed a poor performance. Distribution and abundance patterns corresponded well with the known distributions in Europe. The Random Forests model approach was able to distinguish differences in abundance between countries but was not able to predict vector abundance at individual farm level.
CONCLUSIONS
CONCLUSIONS
The models and maps presented here represent an initial attempt to capture large scale geographical and temporal variations in Culicoides abundance. The models are a first step towards producing abundance inputs for R
Identifiants
pubmed: 32295627
doi: 10.1186/s13071-020-04053-x
pii: 10.1186/s13071-020-04053-x
pmc: PMC7161244
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
194Références
PLoS One. 2010 Dec 06;5(12):e14236
pubmed: 21151914
Parasitol Res. 2007 Jun;101(1):219-28
pubmed: 17385085
Med Vet Entomol. 2012 Jun;26(2):168-77
pubmed: 22103842
Parasit Vectors. 2018 Nov 29;11(1):608
pubmed: 30497537
Med Vet Entomol. 2008 Jun;22(2):124-34
pubmed: 18498611
PLoS One. 2008 Jan 09;3(1):e1408
pubmed: 18183289
Prev Vet Med. 2011 Jun 1;100(1):15-28
pubmed: 21496932
Int J Health Geogr. 2015 Feb 27;14:10
pubmed: 25888755
Ecology. 2007 Nov;88(11):2783-92
pubmed: 18051647
Parasitol Res. 2017 Mar;116(3):881-889
pubmed: 28054179
Geospat Health. 2015 Mar 26;9(2):261-70
pubmed: 25826307
Sci Rep. 2019 Dec 2;9(1):18144
pubmed: 31792296
Adv Parasitol. 2006;62:37-77
pubmed: 16647967
Prev Vet Med. 2008 Oct 15;87(1-2):55-63
pubmed: 18640734
Geospat Health. 2013 Nov;8(1):241-54
pubmed: 24258899
Vet Rec. 2007 Oct 20;161(16):564-5
pubmed: 17951565
Vet Rec. 2006 Sep 2;159(10):327
pubmed: 16950894
Parasitol Res. 2009 Aug;105(2):351-7
pubmed: 19319571
Vet Microbiol. 2003 Dec 2;97(1-2):13-29
pubmed: 14637035
Am Nat. 2009 Aug;174(2):282-91
pubmed: 19519279
Trends Microbiol. 2009 Apr;17(4):172-8
pubmed: 19299131
PLoS One. 2014 May 29;9(5):e96084
pubmed: 24875496
Rev Sci Tech. 2001 Dec;20(3):731-40
pubmed: 11732415
J R Soc Interface. 2008 Mar 6;5(20):363-71
pubmed: 17638649
Vet Rec. 2015 May 2;176(18):464
pubmed: 25841165
Emerg Infect Dis. 2009 Sep;15(9):1481-4
pubmed: 19788820
Parasit Vectors. 2018 Feb 27;11(1):112
pubmed: 29482593
Parasit Vectors. 2012 Nov 22;5:270
pubmed: 23174043
Vet Rec. 2008 Mar 29;162(13):422
pubmed: 18375991
Vet Rec. 2001 Nov 24;149(21):639-43
pubmed: 11764324
Epidemics. 2009 Sep;1(3):153-61
pubmed: 21352762
Vet Ital. 2015 Oct-Dec;51(4):401-6
pubmed: 26741252
Parasit Vectors. 2013 Nov 22;6(1):333
pubmed: 24267276