Little Ice Age lateral moraines represent one of the most important sediment storages and dynamic areas in glacier forelands. Following glacier retreat, simultaneous paraglacial adjustment and vegetation succession affect the moraine slopes. Geomorphic processes (e.g. debris flows, interrill erosion, gullying, solifluction) disturb and limit vegetation development, while increasing vegetation cover decreases geomorphic activity. Thus, feedbacks between geomorphic and vegetation dynamics strongly control moraine slope development. However, the conditions under which these biogeomorphic feedbacks can occur are insufficiently understood and major knowledge gaps remain. This study determines feedback conditions through the analysis of geomorphic and vegetation data from permanent plots in the Turtmann glacier foreland, Switzerland. Results from multivariate statistical analysis (i) confirm that Dryas octopetala L. is an alpine ecosystem engineer species which influences geomorphic processes on lateral moraines and thereby controls ecosystem structure and function, and (ii) demonstrate that biogeomorphic feedbacks can occur once geomorphic activity sufficiently decreases for D. octopetala to establish and cross a cover threshold. In the subsequent ecosystem engineering process, the dominant geomorphic processes change from flow and slide to bound solifluction. Increasing slope stabilization induces a decline in biogeomorphic feedbacks and the suppression of D. octopetala by shrubs. We conceptualize this relationship between process magnitude, frequency and species resilience and resistance to disturbances in a 'biogeomorphic feedback window' concept. Our approach enhances the understanding of feedbacks between geomorphic and alpine vegetation dynamics on lateral moraine slopes and highlights the importance of integrating geomorphic and ecological approaches for biogeomorphic research.

Recent technological advances in remote sensing sensors and platforms, such as high-resolution satellite imagers or unmanned aerial vehicles (UAV), facilitate the availability of fine-grained earth observation data. Such data reveal vegetation canopies in high spatial detail. Efficient methods are needed to fully harness this unpreceded source of information for vegetation mapping. Deep learning algorithms such as Convolutional Neural Networks (CNN) are currently paving new avenues in the field of image analysis and computer vision. Using multiple datasets, we test a CNN-based segmentation approach (U-net) in combination with training data directly derived from visual interpretation of UAV-based high-resolution RGB imagery for fine-grained mapping of vegetation species and communities. We demonstrate that this approach indeed accurately segments and maps vegetation species and communities (at least 84% accuracy). The fact that we only used RGB imagery suggests that plant identification at very high spatial resolutions is facilitated through spatial patterns rather than spectral information. Accordingly, the presented approach is compatible with low-cost UAV systems that are easy to operate and thus applicable to a wide range of users.

No abstract

Vegetation is an important factor influencing solifluction processes, while at the same time, solifluction processes and landforms influence species composition, fine‐scale distribution and corresponding ecosystem functioning. However, how feedbacks between plants and solifluction processes influence the development of turf‐banked solifluction lobes (TBLs) and their geomorphic and vegetation patterns is still poorly understood. We addressed this knowledge gap in a detailed biogeomorphic investigation in the Turtmann glacier foreland (Switzerland). Methods employed include geomorphic and vegetation mapping, terrain assessment with unmanned aerial vehicle (UAV) and temperature logging. Results were subsequently integrated with knowledge from previous geomorphic and ecologic studies into a conceptual model. Our results show that geomorphic and vegetation patterns at TBLs are closely linked through the lobe elements tread, risers and ridge. A conceptual four‐stage biogeomorphic model of TBL development with ecosystem engineering by the dwarf shrub Dryas octopetala as the dominant process can explain these interlinked patterns. Based on this model, we demonstrate that TBLs are biogeomorphic structures and follow a cyclic development, during which the role of their components for engineer and non‐engineer species changes. Our study presents the first biogeomorphic model of TBL development and highlights the applicability and necessity of biogeomorphic approaches and research in periglacial environments. Copyright © 2016 John Wiley & Sons, Ltd.

Unmanned Aerial Vehicles (UAV) greatly extended our possibilities to acquire high resolution remote sensing data for assessing the spatial distribution of species composition and vegetation characteristics. Yet, current pixel-or texturebased mapping approaches do not fully exploit the information content provided by the high spatial resolution. Here, to fully harness this spatial detail, we apply deep learning techniques, that is, Convolutional Neural Networks (CNNs), on regular tiles of UAV-orthoimagery (here 2-5 m) to identify the cover of target plant species and plant communities. The approach was tested with UAV-based orthomosaics and photogrammetric 3D information in three case studies, that is, (1) mapping tree species cover in primary forests, (2) mapping plant invasions by woody species into forests and open land and (3) mapping vegetation succession in a glacier foreland. All three case studies resulted in high predictive accuracies. The accuracy increased with increasing tile size (2-5 m) reflecting the increased spatial context captured by a tile. The inclusion of 3D information derived from the photogrammetric workflow did not significantly improve the models. We conclude that CNN are powerful in harnessing high resolution data acquired from UAV to map vegetation patterns. The study was based on low cost red, green, blue (RGB) sensors making the method accessible to a wide range of users. Combining UAV and CNN will provide tremendous opportunities for ecological applications.