Research Articles

Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks

Sanet Eksteen, Gregory D. Breetzke
South African Journal of Science | Vol 107, No 7/8 | a404 | DOI: https://doi.org/10.4102/sajs.v107i7/8.404 | © 2011 Sanet Eksteen, Gregory D. Breetzke | This work is licensed under CC Attribution 4.0
Submitted: 13 August 2010 | Published: 04 July 2011

About the author(s)

Sanet Eksteen, Department of Geography, Geoinformatics and Meteorology, University of Pretoria, South Africa
Gregory D. Breetzke, Department of Geography, University of Canterbury, New Zealand


Share this article

Bookmark and Share

Abstract

African horse sickness (AHS) is a disease that is endemic to sub-Saharan Africa and is caused by a virus potentially transmitted by a number of Culicoides species (Diptera: Ceratopogonidae) including Culicoides imicola and Culicoides bolitinos. The strong association between outbreaks of AHS and the occurrence in abundance of these two Culicoides species has enabled researchers to develop models to predict potential outbreaks. A weakness of current models is their inability to determine the relationships that occur amongst the large number of variables potentially influencing the population density of the Culicoides species. It is this limitation that prompted the development of a predictive model with the capacity to make such determinations. The model proposed here combines a geographic information system (GIS) with an artificial neural network (ANN). The overall accuracy of the ANN model is 83%, which is similar to other stand-alone GIS models. Our predictive model is made accessible to a wide range of practitioners by the accompanying C. imicola and C. bolitinos distribution maps, which facilitate the visualisation of the model’s predictions. The model also demonstrates how ANN can assist GIS in decision-making, especially where the data sets incorporate uncertainty or if the relationships between the variables are not yet known.

Keywords

African horse sickness; artificial neural network; Culicoides; geographic information system; GIS model

Metrics

Total abstract views: 1131
Total article views: 2320

References


Ramirez A. Geographic information systems and its role in biological risk management. Iowa State University [document on the Internet]. c2004 [cited 2011 Jan 18]. Available from: http://www.cfsph.iastate.edu/BRM/resources/General/GeographicInformationSystesRoleBRM_Sept2004.pdf

Rogers DJ, Williams BG. Monitoring trypanosomiasis in space and time. Parasitology. 1993;106:S77–S92.

Boone I, Thys E, Marcotty T, De Borchgrave J, Ducheyne E, Dorny P. Distribution and risk factors of bovine cysticercosis in Belgian dairy and mixed herds. Prev Vet Med. 2007;82:1–11. doi:10.1016/j.prevetmed.2007.05.002, PMid:17559956

Genchi C, Rinaldi L, Cascone C, Martarino M, Cringoli G. Is heartworm disease really spreading in Europe? Vet Parasitol. 2005;133(3–4):137–148. doi:10.1016/j.vetpar.2005.04.009, PMid:15885913

Baylis M, Meiswinkel R, Venter GJ. Preliminary attempt to use climate data and satellite imagery to model the abundance and distribution of Culicoides imicola (Diptera: Ceratopogonidae) in southern Africa. J S Afr Vet Assoc. 1999;70(2):80–89. PMid:10855827

Wittmann EJ, Mellor PS, Baylis M. Using climate data to map the potential distribution of Culicoides imicola (Diptera: Ceratopogonidae) in Europe. Rev Sci Tech Off Int Epizoot. 2001;20:731–740.

7. Meiswinkel R, Venter GJ, Nevill EM. Vectors: Culicoides spp. Infect Dis Livest. 2004;1:93–136.

Davis B. GIS: A visual approach. 2nd ed. Albany: Thomson Delmar Learning; 2001.

Mlisa A, Africa U, Van Niekerk A. GIS in the decision-making process. Position IT. 2008;(Sept/Oct):44–48.< p> 10. Craigie D. Information integration: A GIS perspective. Ecological Circuits. 2008;(Sept/Oct):14–19.

Thurston J. GIS and artificial networks: Does your GIS think? [document on the Internet]. c2002 [cited 2008 Mar 11]. Available from: http://www.integralgis.com/pdf/Neural%20Networks.pdf

McCloy KR. Resource management information systems: Remote sensing, GIS and modelling. 2nd ed. Boca Raton: CRC Press; 2006.

Stergiou C, Siganos D. Neural networks [homepage on the Internet]. c1996 [cited 2008 Mar 11]. Available from: http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html

Hewitson BC, Crane RC. Neural nets: Applications in geography. Dordrecht: Kluwer Academic Publishers; 1994.

Zhang P. Neural networks for classification: A survey. IEEE Trans Syst Man Cybern Part C Appl Rev. 2000;30:451–462. doi:10.1109/5326.897072

Saha A. Introduction to artificial neural network models [homepage on the Internet]. c2003 [cited 2008 Mar 11]. Available from: www.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg

Deadman PJ, Gimblett HR. Applying neural networks to vegetation management plan development. AI Applic. 1997;11(3):107–112.

Yang Y, Rosenbaum M. Artificial neural networks linked to GIS for determining sedimentology in harbors. J Pet Sci Eng. 2001;29:213–220. doi:10.1016/S0920-4105(01)00091-2

Lord CC, Venter GJ, Mellor PS, Paweska JT, Woolhouse MEJ. Transmission patterns of African horse sickness and equine encephalosis in South African donkeys. Epidemiol Infect. 2002;128:265–275. doi:10.1017/S0950268801006471, PMid:12002545, PMid:2869820

Department of Agriculture, Forestry and Fisheries, Chief Directorate Food and Veterinary Science. List of controlled and notifiable diseases [homepage on the Internet]. c2010 [updated 2010 Jun 18; cited 2011 Mar 11] Available from: http://www.nda.agric.za/vetweb/Disease%20Control/List%20of%20controlled%20%20notifiable%20Animal%20Diseases%202007.pdf

ANN software. Needham, MA: Assembla; 2008. Available from: http://trac.assembla.com/inteligentes/browser/BP/NNClass.xls



Reader Comments

Before posting a comment, read our privacy policy.

Post a comment (login required)

Crossref Citations

No related citations found.