 |
| Titel |
Using remote sensing and machine learning for the spatial modelling of a bluetongue virus vector |
| VerfasserIn |
J. Van doninck, J. Peters, B. De Baets, E. Ducheyne, N. E. C. Verhoest |
| Konferenz |
EGU General Assembly 2012
|
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| Digitales Dokument |
PDF |
| Erschienen |
In: GRA - Volume 14 (2012) |
| Datensatznummer |
250060012
|
|
|
|
|
|
| Zusammenfassung |
| Bluetongue is a viral vector-borne disease transmitted between hosts, mostly cattle and small
ruminants, by some species of Culicoides midges. Within the Mediterranean basin, C. imicola
is the main vector of the bluetongue virus. The spatial distribution of this species is limited by
a number of environmental factors, including temperature, soil properties and land cover. The
identification of zones at risk of bluetongue outbreaks thus requires detailed information
on these environmental factors, as well as appropriate epidemiological modelling
techniques.
We here give an overview of the environmental factors assumed to be constraining the
spatial distribution of C. imicola, as identified in different studies. Subsequently, remote
sensing products that can be used as proxies for these environmental constraints are
presented. Remote sensing data are then used together with species occurrence
data from the Spanish Bluetongue National Surveillance Programme to calibrate a
supervised learning model, based on Random Forests, to model the probability of
occurrence of the C. imicola midge. The model will then be applied for a pixel-based
prediction over the Iberian peninsula using remote sensing products for habitat
characterization. |
|
|
|
|
|
|