Predicting WNV Circulation in Italy Using Earth Observation Data and Extreme Gradient Boosting Model

Abstract

West Nile Disease (WND) is one of the most spread zoonosis in Italy and Europe caused by a vector-borne virus. Its transmission cycle is well understood, with birds acting as the primary hosts and mosquito vectors transmitting the virus to other birds, while humans and horses are occasional dead-end hosts. Identifying suitable environmental conditions across large areas containing multiple species of potential hosts and vectors can be difficult. The recent and massive availability of Earth Observation data and the continuous development of innovative Machine Learning methods can contribute to automatically identify patterns in big datasets and to make highly accurate identification of areas at risk. In this paper, we investigated the West Nile Virus (WNV) circulation in relation to Land Surface Temperature, Normalized Difference Vegetation Index and Surface Soil Moisture collected during the 160 days before the infection took place, with the aim of evaluating the predictive capacity of lagged remotely sensed variables in the identification of areas at risk for WNV circulation. WNV detection in mosquitoes, birds and horses in 2017, 2018 and 2019, has been collected from the National Information System for Animal Disease Notification. An Extreme Gradient Boosting model was trained with data from 2017 and 2018 and tested for the 2019 epidemic, predicting the spatio-temporal WNV circulation two weeks in advance with an overall accuracy of 0.84. This work lays the basis for a future early warning system that could alert public authorities when climatic and environmental conditions become favourable to the onset and spread of WNV.

Culex pipiens distribution in Tunisia: Identification of suitable areas through Random Forest and MaxEnt approaches

“…Actually, it remains yet to be fully understood whether the mechanisms and conditions that caused the extraordinary increase in West Nile virus cases in Tunisia during 2007 and triggered the WNV outbreak in 2012 were singular or potentially forecastable. Among other variables, the spatial distribution and seasonality of vectors, as well as their interconnections with hosts, are key factors that can significantly impact the risk of dissemination (Gould and Higgs, 2009 ; Candeloro et al., 2020 ). Hence, it is crucial to understand how Cx.…”

Epidemiological and Evolutionary Analysis of West Nile Virus Lineage 2 in Italy

“…The eco-climatic model developed by Candeloro et al [ 28 ] confirms the presence of suitable conditions for WNV L2 2022 early spread. Compared to 2021, the 2022 epidemic season is characterised by a higher probability of WNV circulation and by an earlier start of the vector season (1–1.5 months).…”

“…These findings underline the importance of the national surveillance plan and the urgent need for the development of mathematical models able to predict, early on, the WNV behaviour in the following vector season [ 28 , 53 ]. The eco-climatic model developed by Candeloro et al [ 28 ], which is based on environmental covariates such as daytime and nighttime land surface temperature, normalised difference vegetation index, and surface soil moisture, is capable of generating risk maps for WNV spatial distribution probability throughout the Italian territory with 16 day-forecast periods ( , accessed on 20 October 2022). In the 2022 WNV epidemic, it was able to indicate the presence of suitable conditions for an earlier (1–1.5 months) and wider spread of WNV in Italy (in particular, in Emilia-Romagna, Lombardy and Veneto regions (Results, Figure 6 )).…”

“…In [ 28 ], the authors presented a model based on climatic and environmental factors (daytime and nighttime land surface temperature, normalised difference vegetation index, and surface soil moisture) that produces, two weeks in advance, risk maps for WNV circulation throughout Italy using a decision-tree-based ensemble machine learning algorithm (XGBoost, , accessed on 20 October 2022).…”

“…The epidemiological trend of WNV L2, since its first appearance in the country in 2011, is also described by analysing the seasonal patterns and the viral prevalence in mosquitoes, birds, horses, and humans over the years. These analyses gave us the opportunity to assess the accuracy of the recent early warning system based on the environmental and climate model [ 28 ] in predicting WND epidemic behaviour during the 2021 and 2022 vector seasons.…”