An official website of the United States government
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.
more »
« less
Ten best practices for effective phenological research
Abstract The number and diversity of phenological studies has increased rapidly in recent years. Innovative experiments, field studies, citizen science projects, and analyses of newly available historical data are contributing insights that advance our understanding of ecological and evolutionary responses to the environment, particularly climate change. However, many phenological data sets have peculiarities that are not immediately obvious and can lead to mistakes in analyses and interpretation of results. This paper aims to help researchers, especially those new to the field of phenology, understand challenges and practices that are crucial for effective studies. For example, researchers may fail to account for sampling biases in phenological data, struggle to choose or design a volunteer data collection strategy that adequately fits their project’s needs, or combine data sets in inappropriate ways. We describe ten best practices for designing studies of plant and animal phenology, evaluating data quality, and analyzing data. Practices include accounting for common biases in data, using effective citizen or community science methods, and employing appropriate data when investigating phenological mismatches. We present these best practices to help researchers entering the field take full advantage of the wealth of available data and approaches to advance our understanding of phenology and its implications for ecology.
more »
« less
- PAR ID:
- 10443092
- Date Published:
- Journal Name:
- International Journal of Biometeorology
- ISSN:
- 0020-7128
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This check sheet provides advice for being empathetic, respectful, and understanding when entering a disaster-affected community. These best practices can help researchers to be mindful of participants’ emotional well-being, collect ethically informed data, and develop more caring interactions and relationships in the field. About the CONVERGE Extreme Events Research Check Sheets Series: The National Science Foundation-supported CONVERGE facility at the Natural Hazards Center at the University of Colorado Boulder has developed a series of short, graphical check sheets that are meant to be used as researchers design their studies, prepare to enter the field, conduct field research, and exit the field. The series offers best practices for extreme events research and includes check sheets that are free to the research community. More information is available at: https://converge.colorado.edu/resources/check-sheets.more » « less
-
Abstract Data availability limits phenological research at broad temporal and spatial extents. Butterflies are among the few taxa with broad-scale occurrence data, from both incidental reports and formal surveys. Incidental reports have biases that are challenging to address, but structured surveys are often limited seasonally and may not span full flight phenologies. Thus, how these data source compare in phenological analyses is unclear. We modeled butterfly phenology in relation to traits and climate using parallel analyses of incidental and survey data, to explore their shared utility and potential for analytical integration. One workflow aggregated “Pollard” surveys, where sites are visited multiple times per year; the other aggregated incidental data from online portals: iNaturalist and eButterfly. For 40 species, we estimated early (10%) and mid (50%) flight period metrics, and compared the spatiotemporal patterns and drivers of phenology across species and between datasets. For both datasets, inter-annual variability was best explained by temperature, and seasonal emergence was earlier for resident species overwintering at more advanced stages. Other traits related to habitat, feeding, dispersal, and voltinism had mixed or no impacts. Our results suggest that data integration can improve phenological research, and leveraging traits may predict phenology in poorly studied species.more » « less
-
Phenology refers to the seasonal timing patterns commonly exhibited by life on Earth, from blooming flowers to breeding birds to human agriculture. Climate change is altering abiotic seasonality (e.g., longer summers) and in turn, phenological patterns contained within. However, how phenology should evolve is still an unsolved problem. This problem lies at the crux of predicting future phenological changes that will likely have substantial ecosystem consequences, and more fundamentally, of understanding an undeniably global phenomenon. Most studies have associated proximate environmental variables with phenological responses in case-specific ways, making it difficult to contextualize observations within a general evolutionary framework. We outline the complex but universal ways in which seasonal timing maps onto evolutionary fitness. We borrow lessons from life history theory and evolutionary demography that have benefited from a first principles-based theoretical scaffold. Lastly, we identify key questions for theorists and empiricists to help advance our general understanding of phenology.more » « less
-
This check sheet offers guidance on writing a data management plan based on National Science Foundation requirements. This guidance can help researchers who are applying for external funding and who intend to publish their data, data collection protocols, or instruments via the DesignSafe Cyberinfrastructure. About the CONVERGE Extreme Events Research Check Sheets Series: The National Science Foundation-supported CONVERGE facility at the Natural Hazards Center at the University of Colorado Boulder has developed a series of short, graphical check sheets that are meant to be used as researchers design their studies, prepare to enter the field, conduct field research, and exit the field. The series offers best practices for extreme events research and includes check sheets that are free to the research community. More information is available at: https://converge.colorado.edu/resources/check-sheets.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s00484-023-02502-7
