Harmful algal blooms are an increasing problem for human health and ecosystems, especially in freshwater and marine coastal regions. Since 2017, cyanobacteria blooms mainly caused by Microcystis aeruginosa frequently occur in the small European inland river Moselle in late summer and autumn. Despite them being an important indicator for human safety, the temporal and spatial dynamics of these blooms are largely unknown. In order to gain a better understanding of this issue, we developed combined index-based models on Sentinel-2 data with 10 metre spatial resolution (R, G, B, NIR) and corresponding Planet SuperDove data with 3 metre spatial resolution to differentiate algal scum from water and riparian vegetation. Cloud-free almost simultaneous data of Planet SuperDove and Sentinel-2 was retrieved for portions of Moselle River in August 2022. Presence of algal scum in those areas was confirmed by field campaigns in that period. Retrieved satellite scenes were processed using ACOLITE software with the same settings to facilitate intercomparability. Then, areas visually detected in the imagery as "scum", "ambiguous scum", "water" or "vegetation" were digitalized and the spectral information for each class was retrieved. Based on this information, decision-tree based models were developed to differentiate algal scum and validated by analysing spatial overlap with manually digitalized areas from independent satellite scenes. Overall accuracy was substantially higher for the Planet SuperDove model (0.835 versus 0.523), yet accuracy of class "scum" was satisfying for both models (0.972 versus 0.895), thus showing the potential of 10-metre spatial resolution Sentinel-2 data in delineating algal scum.