Plant phenology, the study of the timing of seasonal biological events in a plant’s lifetime—such as budburst, flowering, fruiting, and senescence—is closely linked to climatic conditions and plays a critical role in carbon and nutrient cycling. Given its ecological significance, various cultures and countries have systematically recorded phenological events for decades. In Germany, since the early 1950s, the German Weather Service (DWD) has systematically collected phenological data with the support of trained citizen volunteers. These volunteers adhere to a well-defined protocol, monitoring specific species twice weekly until the target phenophase is observed. Despite its historical importance, the number of volunteer observers has declined since the 1970s, posing a challenge to phenological monitoring. This trend is not unique to Germany; many phenological networks worldwide face similar issues, often exacerbated by financial constraints. However, recent advancements in technology, particularly in machine learning and smartphone applications, have opened new opportunities for phenological monitoring. Among these, plant identification apps have enabled citizens to identify plant species without prior botanical expertise. This dissertation investigates the potential of leveraging opportunistic plant observation data, particularly from the Flora Incognita app, as a new data source to monitor phenological stages.
Negin Katal (Wed,) studied this question.