The acceleration in the effects of global warming and the recent turbulences in the energy market are further highlighting the need to act quicker and smarter in terms of decisions to transition to greener energy and reduce our overall energy consumption. With buildings accounting for about 40% of the energy consumption in Europe, it is crucial to have a comprehensive understanding of the building stock and their energy-related characteristics, including their age, in order to make informed decisions for energy savings. This study introduces a novel way to approach the age estimation of buildings at scale, using a machine learning method that integrates satellite-based imagery with morphological features of buildings. The findings demonstrate the benefits of combining these data sources and underscore the importance of incorporating local data to enable accurate prediction across different cities.