Deep learning and citizen science enable automated plant trait predictions from photographs

Schiller, Christoph; Schmidtlein, Sebastian; Boonman, Coline C. F.; Moreno‐Martínez, Alvaro; Kattenborn, Teja

doi:10.1038/s41598-021-95616-0

Cited by 32 publications

(38 citation statements)

References 48 publications

(111 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rubric required student observations to include more and higher quality details for each observation. These observations are more likely to be suitable for use in research studies (Barve et al, 2020; Echeverria et al, 2021; Gazdic & Groom, 2019; Horn et al, 2018; Schiller et al, 2021). It is our hope that moving forward plant taxonomy courses make use of the rubric and continue improving upon it in a student-centered manner.…”

Section: Discussionmentioning

confidence: 99%

Emphasis on quality in iNaturalist plant collections enhances learning and research utility

McNair

Sexton

Zenoble

2023

Preprint

View full text Add to dashboard Cite

Following the switch to remote online teaching in the wake of the COVID-19 pandemic, the plant taxonomy course at the University of Georgia (UGA) switched to iNaturalist for the specimen collection portion of the course requirements. Building off extant rubrics, the instructors designed project guidelines for a fully online plant collection experience to alleviate plant awareness disparity. Researchers collected stratified samples from the UGA iNaturalist project along with four other institutions projects to determine if rubrics and project guidelines could improve the quality of observations to make them useful in plant science research. The specific rubric was shown to improve quality of iNaturalist observations. Researchers found that iNaturalist increased engagement as a student-centered tool but did not enhance their manual keying skills as the app uses automatic identification. Instructors recommend continuing to use iNaturalist to supplement physical collection and keying along with a detailed rubric and guidelines for collection.

show abstract

Section: Discussionmentioning

confidence: 99%

Emphasis on quality in iNaturalist plant collections enhances learning and research utility

McNair

Sexton

Zenoble

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Several studies note that the main weakness of crowd-sourced, geotagged, photo-based vegetation maps is that the spatial density of field data is very diverse, that is, very spatially fragmented data [ 38 , 39 , 40 ]. However, the LUCAS database is based on spatially uniform survey points with uniform data density, and therefore, the representativeness of the data is higher compared to crowd-sourced vegetation databases.…”

Section: Discussionmentioning

confidence: 99%

Applicability of Point- and Polygon-Based Vegetation Monitoring Data to Identify Soil, Hydrological and Climatic Driving Forces of Biological Invasions—A Case Study of Ailanthus altissima, Elaeagnus angustifolia and Robinia pseudoacacia

Visztra

Frei

Hábenczyus

et al. 2023

Plants

View full text Add to dashboard Cite

Invasive tree species are a significant threat to native flora. They modify the environment with their allelopathic substances and inhibit the growth of native species by shading, thus reducing diversity. The most effective way to control invasive plants is to prevent their spread which requires identifying the environmental parameters promoting it. Since there are several types of invasive plant databases available, determining which database type is the most relevant for investigating the occurrence of alien plants is of great importance. In this study, we compared the efficiency and reliability of point-based (EUROSTAT Land Use and Coverage Area Frame Survey (LUCAS)) and polygon-based (National Forestry Database (NFD)) databases using geostatistical methods in ArcGIS software. We also investigated the occurrence of three invasive tree species (Ailanthus altissima, Elaeagnus angustifolia, and Robinia pseudoacacia) and their relationships with soil, hydrological, and climatic parameters such as soil organic matter content, pH, calcium carbonate content, rooting depth, water-holding capacity, distance from the nearest surface water, groundwater depth, mean annual temperature, and mean annual precipitation with generalized linear models in R-studio software. Our results show that the invasion levels of the tree species under study are generally over-represented in the LUCAS point-based vegetation maps, and the point-based database requires a dataset with a larger number of samples to be reliable. Regarding the polygon-based database, we found that the occurrence of the invasive species is generally related to the investigated soil and hydrological and climatic factors.

show abstract

“…Such potentials may be even accelerated with the concurrent developments of big data in ecology (Depauw et al, 2022; Farley et al, 2018). Data gaps of leaf angles across species may be filled with AngleCam and in concert with the ever increasing availability of citizen science photographs and species labels (the iNaturalist project, Di Cecco et al, 2021; Schiller et al, 2021). Likewise, AngleCam may be applicable to data streams from PhenoCam networks (Aasen et al, 2020; Seyednasrollah et al, 2019) to track plant phenology and its relationship with environmental drivers across the globe.…”

Section: Discussionmentioning

confidence: 99%

“…The basis for the CNN model was the EfficientNet-B7 as backbone (Tan & Le, 2019), which was found most accurate and efficient compared to common available backbones (we also tested versions (Schiller et al, 2021).…”

Section: General Considerations and Outlookmentioning

confidence: 99%

AngleCam: Predicting the temporal variation of leaf angle distributions from image series with deep learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

1. Vertical leaf angles and their variation through time are directly related to several ecophysiological processes and properties. However, there is no efficient method for tracking leaf angles of plant canopies under field conditions.2. Here, we present AngleCam, a deep learning-based approach to predict leaf angle distributions from horizontal photographs acquired with low-cost timelapse cameras. AngleCam is based on pattern recognition with convolutional neural networks and trained with leaf angle distributions obtained from visual interpretation of more than 2500 plant photographs across different species and scene conditions.3. Leaf angle predictions were evaluated over a wide range of species and scene conditions using independent samples from visual interpretation (R 2 = 0.84) and compared to leaf angle estimates obtained from terrestrial laser scanning (R 2 = 0.75). AngleCam was tested for the long-term monitoring of leaf angles for two broadleaf tree species in a temperate forest. The plausibility of the predicted leaf angle time series was underlined by its close relationship with environmental variables related to transpiration. 4. The evaluations confirm that AngleCam is a robust and efficient method to track leaf angles under field conditions. The output of AngleCam is compatible with a range of applications, including functional-structural plant modelling, Earth system modelling or radiative transfer modelling of plant canopies. AngleCam may also be used to predict leaf angle distributions for existing data, for instance from PhenoCam networks citizen science projects.

show abstract

Deep learning and citizen science enable automated plant trait predictions from photographs

Cited by 32 publications

References 48 publications

Emphasis on quality in iNaturalist plant collections enhances learning and research utility

Emphasis on quality in iNaturalist plant collections enhances learning and research utility

Applicability of Point- and Polygon-Based Vegetation Monitoring Data to Identify Soil, Hydrological and Climatic Driving Forces of Biological Invasions—A Case Study of Ailanthus altissima, Elaeagnus angustifolia and Robinia pseudoacacia

AngleCam: Predicting the temporal variation of leaf angle distributions from image series with deep learning

Contact Info

Product

Resources

About