Federated learning (FL) has the potential to mitigate privacy risks and communication costs associated with classical machine learning and data science approaches. Given the distributed nature of FL, many of its use cases face challenges related to spatiotemporal data, geographical analysis, and spatial statistics. However, so far, FL has received little attention by the GIScience community. In this paper, we provide a first overview of the key challenges in FL and how they relate to spatial data science. This paper thus aims to provide the basis for future contributions to federated learning practices by the (geo)spatial research community.