.. _paper-magat:

Spotting Virus From Satellites: Modeling the Circulation of West Nile Virus Through Graph Neural Networks
=========================================================================================================

    - :fa:`circle-check` `10.1109/TGRS.2023.3293270 <https://doi.org/10.1109/TGRS.2023.3293270>`_
    - :fa:`calendar` July 2022
    - :fa:`scroll` `IEEE TGRS <https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36>`_
    - :fa:`tags` :bdg-primary:`Remote Sensing` :bdg-primary:`Graph Neural Networks` :bdg-primary:`Virus Spread Forecasting`

The article explores predicting the circulation of the West Nile virus using Deep Learning and satellite images. In particular, the spread of the virus is modeled through a graph neural network that considers the spatial and environmental relations between different locations. The proposed **MultiAdjacency Graph ATtention network** (**MAGAT**) outperforms other methods, especially when pretraining is used. The results show that the proposed model can be used to predict the spread of the virus with high accuracy.