Forecasting Dengue, Chikungunya and Zika cases in Recife, Brazil: a spatio-temporal approach based on climate conditions, health notifications and machine learning

Dengue has become a challenge for many countries. Arboviruses transmitted by Aedes aegypti spread rapidly over the last decades. The emergence chikungunya fever and zika in South America poses new challenges to vector monitoring control. This situation got worse from 2015 2016, with rapid of chikungunya, causing muscle weakness, Zika virus, related cases microcephaly newborns occurrence Guillain-Barret syndrome, an autoimmune disease that affects nervous system. objective this work was construct tool forecast distribution arboviruses mosquito implementing dengue, transmission predictors based on machine learning, focused multilayer perceptrons neural networks, support machines linear regression models. As case study, we investigated forecasting models predict spatio-temporal primary health notification data climate variables (wind velocity, temperature pluviometry) Recife, Brazil, 2013 including 2015’s outbreak. use analysis results proved be very effective predicting arbovirus cases. indicate southern western regions Recife were susceptible outbreaks period under investigation. proposed approach could useful managers epidemiologists prevent promote public policies promotion sanitation.