Marine microalgae are widely distributed in the ocean as a part of the “blue carbon sink” that uses solar energy and dissolved CO2 to grow and proliferate and produce oxygen as well as carbohydrates through photosynthesis. They are thus involved in the global ocean-atmosphere carbon cycle to mitigate anthropogenic CO2 emission, which is the leading cause of escalating climate change. Healthy and viable algal growth is critical to the prosperity of diverse marine ecosystems in the ocean and carbon capture, utilization, and storage. Also, species and quantities of microalgae are widely used as indicators for marine ecological environment monitoring and water quality evaluation worldwide. For example, Symbiodiniaceae are closely related to their host corals and thus affect the aquatic environment. The diversity of Symbiodiniaceae also has a potential relationship with coral thermal adaptability.
Compared to current manual microscopic identification, which has problems of high professional level requirements, discontinuity of classifiers, and time-consuming, automatic marine microalgae identification by using machine learning methods can meet the needs of rapid monitoring and provide convenience for researchers in marine and environmental science. In this analysis of microalgae images, automatic localization and identification are expected to be achieved simultaneously, which would facilitate the downstream cell analysis. As the joint tasks of classification and localization, object detection can provide the basis for algae identification based on image information combined with biomorphological features.