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

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 th...

Full description

Bibliographic Details
Main Authors: Sanet Eksteen, Gregory Breetzke
Format: Article
Language:English
Published: Academy of Science of South Africa 2011-07-01
Series:South African Journal of Science
Subjects:
Online Access:http://192.168.0.115/index.php/sajs/article/view/9825
id doaj-9aad63b744344ed0a9a4aa5a65546c2b
record_format Article
spelling doaj-9aad63b744344ed0a9a4aa5a65546c2b2021-04-03T15:46:24ZengAcademy of Science of South AfricaSouth African Journal of Science1996-74892011-07-011077/8Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networksSanet Eksteen0Gregory Breetzke1Department of Geography, Geoinformatics and Meteorology, University of PretoriaDepartment of Geography, University of CanterburyAfrican 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.http://192.168.0.115/index.php/sajs/article/view/9825African horse sicknessartificial neural networkCulicoidesgeographic information systemGIS model
collection DOAJ
language English
format Article
sources DOAJ
author Sanet Eksteen
Gregory Breetzke
spellingShingle Sanet Eksteen
Gregory Breetzke
Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks
South African Journal of Science
African horse sickness
artificial neural network
Culicoides
geographic information system
GIS model
author_facet Sanet Eksteen
Gregory Breetzke
author_sort Sanet Eksteen
title Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks
title_short Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks
title_full Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks
title_fullStr Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks
title_full_unstemmed Predicting the abundance of African horse sickness vectors in South Africa using GIS and artificial neural networks
title_sort predicting the abundance of african horse sickness vectors in south africa using gis and artificial neural networks
publisher Academy of Science of South Africa
series South African Journal of Science
issn 1996-7489
publishDate 2011-07-01
description 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.
topic African horse sickness
artificial neural network
Culicoides
geographic information system
GIS model
url http://192.168.0.115/index.php/sajs/article/view/9825
work_keys_str_mv AT saneteksteen predictingtheabundanceofafricanhorsesicknessvectorsinsouthafricausinggisandartificialneuralnetworks
AT gregorybreetzke predictingtheabundanceofafricanhorsesicknessvectorsinsouthafricausinggisandartificialneuralnetworks
_version_ 1721543938350776320