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.
Native and nonnative plant species can exhibit differences in the timing of their reproductive phenology and their phenological sensitivity to climate. These contrasts may influence species' interactions and the invasion potential of nonnative species; however, a limited number of phenology studies expressly consider phenological mismatches among native and nonnative species over broad spatial or temporal scales. To fill this knowledge gap, we used two complementary approaches: First, we quantified the flowering phenology of native and nonnative plants at five old‐field sites across a spatially extensive range of eastern North America. Second, we used herbarium records to compare the sensitivity of flowering and fruiting phenology to climate across a 114‐yr time period in a subset of common old‐field species in southwestern Pennsylvania. Across the study region, nonnatives reproduced substantially earlier in the growing season than natives, suggesting that nonnatives occupy a unique phenological niche (0.55 months earlier flowering across the North American study sites; 50.1 d earlier flowering and 17.5 d earlier fruiting in southwestern Pennsylvania). Both natives and nonnatives advanced their reproductive phenology between 1900 and 2014 but exhibited contrasting phenological sensitivity to climate factors. During the flowering stage of phenology, nonnatives were more sensitive to changes in precipitation than natives and generally delayed flowering in wetter years. Nonnative plants had greater sensitivity and advanced fruiting when the month preceding fruiting was warmer, while native plants had greater sensitivity and advanced fruiting when the three‐month period preceding fruiting was warmer. Our findings suggest that nonnative old‐field species occupy an earlier phenological niche relative to native species, which may facilitate their invasion into old‐field communities. However, given the different sensitivities of native and nonnative plants to climate factors, present‐day patterns of phenology are likely to shift with future climate changes, potentially leading to novel species interactions that may influence the outcomes of invasion.
Premise We developed a novel low‐cost method to visually phenotype belowground structures in the plant rhizosphere. We devised the method introduced here to address the difficulties encountered growing plants in seed germination pouches for long‐term experiments and the high cost of other mini‐rhizotron alternatives. Methods and Results The method described here took inspiration from homemade ant farms commonly used as an educational tool in elementary schools. Using compact disc (CD) cases, we developed mini‐rhizotrons for use in the field and laboratory using the burclover Medicago lupulina. Conclusions Our method combines the benefits of pots and germination pouches. In CD mini‐rhizotrons, plants grew significantly larger than in germination pouches, and unlike pots, it is possible to measure roots without destructive sampling. Our protocol is a cheaper, widely available alternative to more destructive methods, which could facilitate the study of belowground phenotypes and processes by scientists with fewer resources.
Question: Natural areas are commonly managed for multiple purposes, including both conservation and recreational use. Hiking trails are an extremely common feature in natural areas that enable recreational use, but trail construction and use can also facilitate the spread of non-native species by altering trailside conditions, creating disturbances, and acting as a conduit for non-native propagules to be carried into the backcountry.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.