Due to the technological advances in the last thirty years more and more data become available. In many fields scientists monitor huge numbers of variables. But incorporating these extra information into classical statistical models often leads to bad results due to the increasing amount of uncertainty resulting from the exploding number of model parameters. Hence, it is necessary to develop more parsimonious models to handle the new data situation effectively. This book focusses on Dynamic Factor Models for forecasting of high-dimensional time-series. It will be shown how well this model family performes in the context of water temperature and energy demand forecasts. However, their use is not limited to these areas. Dynamic Factor Models have been applied in many different scientific fields. They implement a modern technique for data compression and dimension reduction.