Spatial patterns of flower color variation in native and introduced ranges of Convolvulus arvensis (Convolvulaceae) revealed by citizen science data and machine learning.

Flower color polymorphism refers to the presence of multiple color variants in plant populations. Investigation of this phenomenon led to multiple discoveries, including the principles of heredity and the foundations of population genetics. I examined flower color variation across native and introduced ranges of Convolvulus arvensis, which exhibits flower color polymorphism (individuals have white or pink petals). To study flower color variation of the species throughout large geographic scale, I used observations gathered from the iNaturalist platform. To handle a large amount of data, I trained a neural network to classify the plants' morphs based on photographs. Then, I performed spatial analyses to examine the patterns of the color frequency, also in relation to environmental factors. The results show that flower colors are polymorphic across the whole species range, but the frequency of pink versus white flowers varies. In the Palearctic, I observed geographic clines of the color morph frequencies: a higher frequency of the pink morph in populations from Northwestern Europe, whereas in Southern and Eastern Europe, towards the eastern edge of the range, the white morph was dominant. On the contrary, pattern of color distribution in North America (where the species is invasive) seems random, but the model indicates a link between higher proportion of pink morphs in mild and humid climate. The mechanisms behind the observed patterns remain largely unknown, as changes of the morphs' frequency are not strongly linked to abiotic factors. To understand the spatial pattern, a detailed investigation, accounting for the species' phylogeography is needed. The study is another example of how the general public may collect data relevant to ecological studies, even if the data are not collected for a specific project.