Modelling the monthly abundance of Culicoides biting midges in nine European countries using Random Forests machine learning

Parasites & Vectors

Miguel Ángel Miranda Chueca¹  Carlos Barceló¹  Roger Venail²  Jonathan Lhoir³  Thomas Balenghien³  David Chavernac³  Henrik Skovgard⁴  Javier Lucientes⁵  Rosa Estrada⁵  Andreas Baum⁶  Anders Stockmarr⁶  Ellen Kiel⁷  Sonja Steinke⁷  Søren Achim Nielsen⁸  Marcin Smreczak⁹  Anna Orłowska⁹  Magdalena Larska⁹  Lene Jung Kjær^1,10  Ana Carolina Cuéllar^1,10  Rene Bødker^1,10  Bethsabée Scheid^1,11  Marie-Laure Setier-Rio^1,11  Renke Lühken^1,12  Ignace Rakotoarivony^1,13  Claire Garros^1,13  Xavier Allène^1,13  Franz J. Conraths^1,14  Jörn Gethmann^1,14  Bruno Mathieu^1,15  Delphine Delécolle^1,15  Jean-Claude Delécolle^1,15  Alexander Mathis^1,16  Wesley Tack^1,17  Jan Chirico^1,18  Mats Gunnar Andersson^1,18  Anders Lindström^1,18  Ståle Sviland^1,19  Petter Hopp^1,19  Inger Hamnes^1,19  Katharina Brugger^2,20  Franz Rubel^2,20 

[1] Applied Zoology and Animal Conservation Research Group, University of the Balearic Islands;Avia-GIS NV;CIRAD, UMR ASTRE;Department of Agroecology - Entomology and Plant Pathology, Aarhus University;Department of Animal Pathology, University of Zaragoza;Department of Applied Mathematics and Computer Science, Technical University of Denmark (DTU);Department of Biology and Environmental Sciences, Carl von Ossietzky University;Department of Science and Environment, Roskilde University;Department of Virology, National Veterinary Research Institute;Division for Diagnostics and Scientific Advice, National Veterinary Institute, Technical University of Denmark (DTU);EID Méditerranée;Faculty of Mathematics, Informatics and Natural Sciences, Universität Hamburg;IAV Hassan II, Unité MIMC;Institute of Epidemiology, Friedrich-Loeffler-Institut;Institute of Parasitology and Tropical Pathology of Strasbourg, UR7292, Université de Strasbourg;Institute of Parasitology, National Centre for Vector Entomology, Vetsuisse FacultyInstitute of Parasitology, National Centre for Vector Entomology, Vetsuisse Faculty, University of Zürich;Meise Botanic Garden;National Veterinary Institute (SVA);Norwegian Veterinary Institute;Unit of Veterinary Public Health and Epidemiology, University of Veterinary Medicine;

关键词: Culicoides abundance;    Random Forest machine learning;    Spatial predictions;    Europe;    Environmental variables;    Culicoides seasonality;   

DOI  :  10.1186/s13071-020-04053-x

来源: DOAJ

【 摘 要 】

Abstract 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 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 km2 resolution. We used independent test sets for validation and to assess model performance. 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 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 R0 modelling of Culicoides-borne infections at a continental scale.

【 授权许可】

Unknown