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

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Ana Carolina Cuéllar, Danmarks Tekniske Universitet
  • ,
  • Lene Jung Kjær, Division for Diagnostics and Scientific Advice, DTU
  • ,
  • Andreas Baum, Danmarks Tekniske Universitet
  • ,
  • Anders Stockmarr, Danmarks Tekniske Universitet
  • ,
  • Henrik Skovgard
  • Søren Achim Nielsen, Department of Natural Science and Environment, Roskilde University
  • ,
  • Mats Gunnar Andersson, National Veterinary Institute
  • ,
  • Anders Lindström, National Veterinary Institute
  • ,
  • Jan Chirico, National Veterinary Institute
  • ,
  • Renke Lühken, University of Hamburg, Bernhard Nocht Institute for Tropical Medicine
  • ,
  • Sonja Steinke, University of Oldenburg
  • ,
  • Ellen Kiel, University of Oldenburg
  • ,
  • Jörn Gethmann, Friedrich Loeffler Institute
  • ,
  • Franz J. Conraths, Friedrich Loeffler Institute
  • ,
  • Magdalena Larska, National Veterinary Research Institute
  • ,
  • Marcin Smreczak, National Veterinary Research Institute
  • ,
  • Anna Orłowska, National Veterinary Research Institute
  • ,
  • Inger Hamnes, National Veterinary Institute Norway
  • ,
  • Ståle Sviland, National Veterinary Institute Norway
  • ,
  • Petter Hopp, National Veterinary Institute Norway
  • ,
  • Katharina Brugger, University of Veterinary Medicine
  • ,
  • Franz Rubel, University of Veterinary Medicine
  • ,
  • Thomas Balenghien, UMR ASTRE, Institut Agronomique et Vétérinaire Hassan II
  • ,
  • Claire Garros, Institut Agronomique et Vétérinaire Hassan II
  • ,
  • Ignace Rakotoarivony, Institut Agronomique et Vétérinaire Hassan II
  • ,
  • Xavier Allène, Institut Agronomique et Vétérinaire Hassan II
  • ,
  • Jonathan Lhoir, UMR ASTRE
  • ,
  • David Chavernac, UMR ASTRE
  • ,
  • Jean Claude Delécolle, Universite de Strasbourg
  • ,
  • Bruno Mathieu, Universite de Strasbourg
  • ,
  • Delphine Delécolle, Universite de Strasbourg
  • ,
  • Marie Laure Setier-Rio, EID Méditerranée
  • ,
  • Bethsabée Scheid, EID Méditerranée
  • ,
  • Miguel Ángel Miranda Chueca, University of the Balearic Islands
  • ,
  • Carlos Barceló, University of the Balearic Islands
  • ,
  • Javier Lucientes, Departamento de Anatomía, Embriología y Genética Animal, Facultad de Veterinaria, Universidad de Zaragoza
  • ,
  • Rosa Estrada, Departamento de Anatomía, Embriología y Genética Animal, Facultad de Veterinaria, Universidad de Zaragoza
  • ,
  • Alexander Mathis, Physik-Institut, Universitat Zürich-Irchel
  • ,
  • Roger Venail, Avia-GIS NV
  • ,
  • Wesley Tack, Botanic Garden Meise
  • ,
  • Rene Bødker, Danmarks Tekniske Universitet

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.[Figure not available: see fulltext.]

Original languageEnglish
Article number194
JournalParasites and Vectors
Volume13
Issue1
Number of pages18
ISSN1756-3305
DOIs
Publication statusPublished - 2020

    Research areas

  • Culicoides abundance, Culicoides seasonality, Environmental variables, Europe, Random Forest machine learning, Spatial predictions

See relations at Aarhus University Citationformats

ID: 185772621