Search

Terrestrial biomes and their biogeographic patterns have been derived from a large variety of variables including species distributions and bioclimate or remote sensing products. However, classifying the biosphere into biomes from a functional perspective using biophysical traits has rarely been tested. Such a trait-based biome classification has been limited by data availability. Here, we aimed to exploit crowd-sourced plant observations and trait databases to systematically assess which traits are most suitable for biome classification. We derived global patterns of 33 biophysical traits covering around 50 % of the land surface by combining crowd-sourced species distribution data from the Global Biodiversity Information Facility (GBIF) and trait observations from the TRY database. Using these trait maps as predictors for supervised cluster analyses, we tested to what extent we can reconstruct 31 published biome maps. A sensitivity analysis with randomly sampled combinations of traits was performed to identify the traits that are most appropriate for biome classification. Performance was quantified by comparing modeled biome maps and the respective observation-based biome maps. Finally, spatial gaps in the resulting biome maps were filled using species distribution models to obtain continuous global biome maps. We showed that traits can be used for biome classification and that the most appropriate traits are conduit density; rooting depth; height; and different leaf traits, including specific leaf area and leaf nitrogen content. The best performance of the biome classification was obtained for biome maps based on biogeographic zonation and species distributions, in contrast to biome maps derived from optical reflectance. The availability of crowd-sourced plant observations is heterogeneous, and, despite its exponential growth, large data gaps are prevalent. Nonetheless, it was possible to derive biome classification schemes from these data to predict global biome patterns with good agreement. Therefore, our analysis is a valuable approach towards understanding biome patterns based on biophysical traits and associated ecological strategies. [ABSTRACT FROM AUTHOR]

Phenological shifts across plant species is a powerful indicator to quantify the effects of climate change. Today, mobile applications with automated species identification open new possibilities for phenological monitoring across space and time.Here, we introduce an innovative spatio‐temporal machine learning methodology that harnesses such crowd‐sourced data to quantify phenological dynamics across taxa, space and time. Our algorithm links individual phenological responses across thousands of species and geographical locations, using a similarity measure. The analysis draws on nearly ten million plant observations collected through the AI‐based plant identification app Flora Incognita in Germany from 2018 to 2021.Our method quantifies changes in synchronisation across the annual cycle. During the growing season, synchronised behaviour can be encoded by a few characteristic macrophenological patterns. Nonlinear spatio‐temporal changes of these patterns can be efficiently quantified using a data compressibility measure. Outside the growing season, the phenological synchronisation diminishes introducing noise into the patterns.Despite biases and uncertainties associated with crowd‐sourced data, for example due to human data collection behaviour, our study demonstrates the feasibility of deriving meaningful indicators for monitoring plant macrophenology from individual plant observations. As crowd‐sourced databases continue to expand, our approach holds promise to study climate‐induced phenological shifts and feedback loops. [ABSTRACT FROM AUTHOR]

Knowledge of plant species distributions is essential for various application fields, such as nature conservation, agriculture, and forestry. Remote sensing data, especially high-resolution orthoimages from unoccupied aerial vehicles (UAVs), paired with novel pattern-recognition methods, such as convolutional neural networks (CNNs), enable accurate mapping (segmentation) of plant species. Training transferable pattern-recognition models for species segmentation across diverse landscapes and data characteristics typically requires extensive training data. Training data are usually derived from labor-intensive field surveys or visual interpretation of remote sensing images. Alternatively, pattern-recognition models could be trained more efficiently with plant photos and labels from citizen science platforms, which include millions of crowd-sourced smartphone photos and the corresponding species labels. However, these pairs of citizen-science-based photographs and simple species labels (one label for the entire image) cannot be used directly for training state-of-the-art segmentation models used for UAV image analysis, which require per-pixel labels for training (also called masks). Here, we overcome the limitation of simple labels of citizen science plant observations with a two-step approach. In the first step, we train CNN-based image classification models using the simple labels and apply them in a moving-window approach over UAV orthoimagery to create segmentation masks. In the second phase, these segmentation masks are used to train state-of-the-art CNN-based image segmentation models with an encoder–decoder structure. We tested the approach on UAV orthoimages acquired in summer and autumn at a test site comprising 10 temperate deciduous tree species in varying mixtures. Several tree species could be mapped with surprising accuracy (mean F1 score =0.47). In homogenous species assemblages, the accuracy increased considerably (mean F1 score =0.55). The results indicate that several tree species can be mapped without generating new training data and by only using preexisting knowledge from citizen science. Moreover, our analysis revealed that the variability in citizen science photographs, with respect to acquisition data and context, facilitates the generation of models that are transferable through the vegetation season. Thus, citizen science data may greatly advance our capacity to monitor hundreds of plant species and, thus, Earth's biodiversity across space and time. [ABSTRACT FROM AUTHOR]

Knowledge of plant species distributions is essential for various applications, such as nature conservation, agriculture, and forestry. Remote sensing data, especially high4 resolution orthoimages from Unoccupied Aerial Vehicles (UAVs), were demonstrated to be an effective data source for plant species mapping. Particularly, in concert with novel pat6 tern recognition methods, such as Convolutional Neural Networks (CNNs), plant species can be accurately segmented in such high-resolution UAV images. Training such pattern recognition models for species segmentation that are transferable across various landscapes and remote sensing data characteristics often requires excessive training data. Training data are usually derived in the form of segmentation masks from field surveys or visual interpretation of the target species in remote sensing images. Still, both methods are laborious and constrain the training of transferable pattern recognition models. Alterna13 tively, pattern recognition models could be trained on the open knowledge of how plants look as available from smartphone-based species identification apps, that is, millions of citizen science-based smartphone photographs and the corresponding species label. How16 ever, these pairs of citizen science-based photographs and simple species labels (one label for the entire image) cannot be used directly for training state-of-the-art segmentation models used for UAV image analysis, which require per-pixel labels for training (also called masks). Here, we overcome the limitation of simple labels of citizen science plant observations with a two-step approach: In the first step, we train CNN-based image classi21 fication models using the simple labels and apply them in a moving-window approach over UAV orthoimagery to create segmentation masks. In the second phase, these segmenta23 tion masks are used to train state-of-the-art CNN-based image segmentation models with an encoder-decoder structure. We tested the approach on UAV orthoimages acquired in summer and autumn on a test site comprising ten temperate deciduous tree species in varying mixtures. Several tree species could be mapped with surprising accuracy (mean F1-score = 0.47). In homogenous species assemblages, the accuracy increased considerably (mean F1-score 0.55). The results indicate that many tree species can be mapped without generating training data and by integrating pre-existing knowledge from citizen science. Moreover, our analysis revealed that citizen science photographs' variability in acquisition data and context facilitates the generation of models that are transferable through the vegetation season. Thus, citizen science data may greatly advance our capacity to monitor hundreds of plant species and, thus, Earth's biodiversity across space and time. Keywords: Remote Sensing, Convolutional Neural Network, Citizen Science Data, Plant species, Transfer learning. [ABSTRACT FROM AUTHOR]