Foraminifera are promising bioindicators in coastal environments, yet their manual identification is slow and relies on taxonomic expertise. Deep learning and neural networks can quickly recognize morphological differences. Here, fjord foraminifera were imaged, labeled, and classified in the Roboflow application programming interface, resulting in 22 138 labelled individuals. These were used to train a deep learning model, which successfully distinguished among 29 species with up to 90.3 % precision.