Climate change can affect different aspects of human life directly and indirectly. One of the most important areas affected by climate change is human health. The occurrence of floods, droughts, extreme temperatures, heat waves, pests, and outbreaks of diseases put human lives at risk. In the case of diseases, especially vector-borne diseases (=arboviral), climate change can result in increased disease prevalence and severity, e.g., by changing temperature, humidity and precipitation patterns. There is an urgent need to predict and study climate change effects on disease outbreaks. Together with the RKI, we investigate the impact of climate change and multiple other socio-economic factors on the distribution, frequency and amplitude of arboviral disease outbreaks as Dengue, Malaria and Lyme. For this reason, we apply Machine Learning (ML) methods which allow us to capture complex correlations among variables and the complex temporal dynamics of the vectors and the diseases. Various ML methods as random forests, LSTM and graph neural networks are combined and applied to predict vector-born disease incidence. The sensitivity of the outbreaks with respect to several climate and socio-economic input factors and their dynamic nature is quantized. After identifying the most important input factors and after model training with actual disease data, the outbreaks of arboviral disease are predicted under future climate conditions. Will the diseases become endemic in new areas?