The role of plankton communities in important environmental issues is an active research question. Large amounts of plankton images collected using modern devices call for automated analysis methods. We consider classification of phytoplanktons using compact convolutional neural networks allowing fast model training. We analyse the confused classes and their practical implications to aquatic research. We show that good accuracy can be obtained with a limited amount of unbalanced training data.

Ocean acidification is challenging phenotypic plasticity of individuals and populations. We studied phenotypic plasticity of the calanoid copepod Acartia bifilosa in the course of a pelagic, large-volume mesocosm study in the Baltic Sea. We found significant negative effects of ocean acidification on adult female copepod size and egg hatching success. Overall, these results indicate that A. bifilosa could be affected by projected near-future CO₂ levels.