The monitoring of ecosystems alterations has become a crucial task in order to develop valuable habitats for rare and threatened species. The information extracted from hyperspectral remote sensing data enables the generation of highly spatially resolved analyses of such species’ habitats. In our study we combine information from a species ordination with hyperspectral reflectance signatures to predict occurrence probabilities for Natura 2000 habitat types and their conservation status. We examine how accurate habitat types and habitat threat, expressed by pressure indicators, can be described in an ordination space using spatial correlation functions from the geostatistic approach. We modeled habitat quality assessment parameters using floristic gradients derived by non-metric multidimensional scaling on the basis of 58 field plots. In the resulting ordination space, the variance structure of habitat types and pressure indicators could be explained by 69% up to 95% with fitted variogram models with a correlation to terrestrial mapping of >0.8. Models could be used to predict habitat type probability, habitat transition, and pressure indicators continuously over the whole ordination space. Finally, partial least squares regression (PLSR) was used to relate spectral information from AISA DUAL imagery to floristic pattern and related habitat quality. In general, spectral transferability is supported by strong correlation to ordination axes scores (R² = 0.79–0.85), whereas second axis of dry heaths (R² = 0.13) and first axis for pioneer grasslands (R² = 0.49) are more difficult to describe.

Recent developments in high‐resolution ecosystem mapping using unmanned aerial vehicles (UAV) open up promising perspectives for the monitoring of fine‐scale vegetation patterns and ecological functioning. In this study, we examine the potential of UAV imagery to track the structural composition and related phenological traits of the dwarf shrub Calluna vulgaris on a former military training area. On a European Natura 2000 heathland site, habitat management is shown to be evaluated on the basis of flowering dynamics and reproductive recovery as a proxy of functional changes that are generated after fire destruction. In particular, we utilize true color camera information and digital surface models to determine the spatiotemporal evolution of Calluna life‐cycle phases and flowering phenology 2 years after controlled burning. A stepwise methodological framework is presented that extracts Calluna pixels, spatially separates juvenile and mature life‐cycle phases, differentiates between generative and vegetative shoot extension and finally quantifies proportions of flowers, fruits and vegetative growth in two consecutive peak flowering periods. We show that Calluna life‐cycle phases can be spatially differentiated in pioneer, building and mature phases in UAV imagery. In the juvenile phase, regeneration from germination is low (<10%) and sprouting from the stem base dominates recovery patterns after fire management. The study further reveals that the distribution of flowering and fruiting during peak flowering time is spatially heterogeneous with high variations between years. In the fire unaffected mature phase, proportions of flowers and fruits are reduced indicating a decrease in reproductive capacity of unmanaged Calluna stands. A phenological phase shift is detected from flowering to fruiting that is related to an increase of Calluna growth height. The study shows that the functional patterns of growth and reproduction can be mapped for heathland ecosystems using simple true color drone cameras.

In Europe, the interest in introducing megaherbivores to achieve ambitious habitat restoration goals is increasing. In this study, we present the results of a one-year monitoring program in a rewilding project in Germany (Doeberitzer Heide), where European bison (Bison bonasus) and Przewalski´s horses (Equus ferus przewalskii) were introduced for ecological restoration purposes. Our objectives were to investigate diet and habitat preferences of Przewalski´s horses and European bison under free-choice conditions without fodder supplementation. In a random forest classification approach, we used multitemporal RapidEye time series imagery to map the diversity of available habitats within the study area. This spatially explicit habitat distribution from satellite imagery was combined with direct field observations of seasonal diet preferences of both species. In line with the availability of preferred forage plants, European bison and Przewalski´s horses both showed seasonal habitat preferences. Because of their different preferences for forage plants, they did not overlap in habitat use except for a short time in the colder season. European bison used open habitats and especially wet open habitats more than expected based on available habitats in the study area. Comparative foraging and feeding niches should be considered in the establishment of multispecies projects to maximize the outcome of restoration processes.

A dramatic decrease of biodiversity is currently questioning human‐environment interactions that have shaped ecosystems over thousands of years. In old cultural landscapes of Central and East European (CEE) countries, a vast species decline has been reported for various taxa although intensive land cultivation has been reduced in favor of agroecological transformation, nature conservation and sustainable land management in the past 30 years. Thus, in the recent history, agricultural intensification cannot solely be discussed as the major driver controlling biodiversity. In cultural landscapes, we state that drivers and pressures mainly emerge from the backyards of rural settlements that act as interconnected rural hotspots and therefore form an ecological metapopulation in which small‐scale backyard habitats are capable of preserving and exchanging species pools of the historical cultural landscape. We further argue that shifting sociocultural norms significantly affecting the survival of source populations in rural hotspots and drastically limit their dispersal pathways, which triggers the degradation of the rural metapopulation in recent times. Pressures of cultivation shift, landscape decoupling, structural homogenization, and use of technology and agrochemicals are identified as backyard ecological drivers negatively affecting biodiversity preservation, particularly in the surrounding rural landscape. Spatiotemporal dimensions of backyard pressures involving material fluxes, species exchange and retention, alternation of site conditions, and local genetic adaptation are delineated for different backyard features, including building structures, gardens, lawns, and paved grounds. Finally, we propose a future research agenda to quantify effects and trends of rural hotspots and followed patterns of altered species dynamics. We give an example on the use of satellite time series to remotely map rural backyard habitats and reveal significant spatiotemporal trends induced by small‐scale human behavior that may lead to a new socioecological perception and stimulate actions to shape ecological dynamics emerging from the backyards of human settlements.

Aim: The management of habitats for the conservation and restoration of biodiversity in protected area networks requires an appropriate monitoring to increase our understanding of processes and dynamics in managed ecosystems. Remote sensing offers a unique potential for the derivation of coherent spatiotemporal information to report on natural or management‐induced habitat change. However, the methods used for the delineation of habitat types in remote sensing imagery depend on the extensive process of ground truth sampling as reference to construct image classifiers. In fact, the number of required reference samples is intrinsically unknown in complex scenes due to the heterogeneity of varying habitat conditions. Thus, most classifiers are not transferable in retrospective image analysis or between different ecosystems that is, however, required for an operational use of remote sensing‐based monitoring systems.Innovation: A new procedure is introduced that autonomously generates representative reference samples for a predictive modelling of habitat type probabilities. The procedure, termed Habitat Sampler, is provided as a tool that can be applied to any image input that display vegetation structures and dynamics on multiple temporal and spatial scales. The Habitat Sampler provides many labelled point locations for the training of image classifiers and enables a fast and easy to implement model transfer for the delineation of habitat dynamics in various ecosystems.Main conclusions: The Habitat Sampler outperforms standard machine learning classifiers when the distribution of reference samples is unknown or insufficient. It was shown that particularly in retrospective image analyses patterns of successional and cyclic habitat development can be mapped for large heathland areas. The procedure is feasible for application in biodiversity conservation monitoring using various habitat typologies that are associated over ecosystem processes, particularly to report on protected area networks using cost‐free satellite imagery.