Brito, AndréMachado, AusendaRodrigues, Ana PaulaPatrício, PaulaBispo, Regina2026-03-022026-03-022025-07-17http://hdl.handle.net/10400.18/11019The COVID-19 pandemic underscored the vital role of mathematical modelling in epidemiology, aiding in forecasting disease trends and informing public health strategies. In Portugal, modelling efforts demonstrated the effectiveness of physical distancing in curbing transmission and provided key insights into the impacts of deconfinement and vaccination on disease burden. The period also saw increased use of non-traditional data, particularly human mobility data, which served as a proxy for contact patterns and helped refine models of disease spread. In this work, we aim to evaluate the predictive performance of neural network models in capturing mobility patterns across Portuguese districts during the COVID-19 pandemic, using data from Google Mobility Reports.engMobilitySpatio-Temporal ModellingNeural NetworksEstados de Saúde e de DoençaCOVID-19conference object