Search for: All records

Abstract The success of plant species under climate change will be determined, in part, by their phenological responses to temperature. Despite the growing need to forecast such outcomes across entire species ranges, it remains unclear how phenological sensitivity to temperature might vary across individuals of the same species. In this study, we harnessed community science data to document intraspecific patterns in phenological temperature sensitivity across the multicontinental range of six herbaceous plant species. Using linear models, we correlated georeferenced temperature data with 23 220 plant phenological records from iNaturalist to generate spatially explicit estimates of phenological temperature sensitivity across the shared range of species. We additionally evaluated the geographic association between local historic climate conditions (i.e. mean annual temperature [MAT] and interannual variability in temperature) and the temperature sensitivity of plants. We found that plant temperature sensitivity varied substantially at both the interspecific and intraspecific levels, demonstrating that phenological responses to climate change have the potential to vary both within and among species. Additionally, we provide evidence for a strong geographic association between plant temperature sensitivity and local historic climate conditions. Plants were more sensitive to temperature in hotter climates (i.e. regions with high MAT), but only in regions with high interannual temperature variability. In regions with low interannual temperature variability, plants displayed universally weak sensitivity to temperature, regardless of baseline annual temperature. This evidence suggests that pheno-climatic forecasts may be improved by accounting for intraspecific variation in phenological temperature sensitivity. Broad climatic factors such as MAT and interannual temperature variability likely serve as useful predictors for estimating temperature sensitivity across species’ ranges. 

Community science image libraries offer a massive, but largely untapped, source of observational data for phenological research. The iNaturalist platform offers a particularly rich archive, containing more than 49 million verifiable, georeferenced, open access images, encompassing seven continents and over 278,000 species. A critical limitation preventing scientists from taking full advantage of this rich data source is labor. Each image must be manually inspected and categorized by phenophase, which is both time-intensive and costly. Consequently, researchers may only be able to use a subset of the total number of images available in the database. While iNaturalist has the potential to yield enough data for high-resolution and spatially extensive studies, it requires more efficient tools for phenological data extraction. A promising solution is automation of the image annotation process using deep learning. Recent innovations in deep learning have made these open-source tools accessible to a general research audience. However, it is unknown whether deep learning tools can accurately and efficiently annotate phenophases in community science images. Here, we train a convolutional neural network (CNN) to annotate images of Alliaria petiolata into distinct phenophases from iNaturalist and compare the performance of the model with non-expert human annotators. We demonstrate that researchers can successfully employ deep learning techniques to extract phenological information from community science images. A CNN classified two-stage phenology (flowering and non-flowering) with 95.9% accuracy and classified four-stage phenology (vegetative, budding, flowering, and fruiting) with 86.4% accuracy. The overall accuracy of the CNN did not differ from humans ( p = 0.383), although performance varied across phenophases. We found that a primary challenge of using deep learning for image annotation was not related to the model itself, but instead in the quality of the community science images. Up to 4% of A. petiolata images in iNaturalist were taken from an improper distance, were physically manipulated, or were digitally altered, which limited both human and machine annotators in accurately classifying phenology. Thus, we provide a list of photography guidelines that could be included in community science platforms to inform community scientists in the best practices for creating images that facilitate phenological analysis.