Traditional methods for individual tree-crown (ITC) detection (image classification, segmentation, template matching, etc.) applied to very high-resolution remote sensing imagery have been shown to struggle in disparate landscape types or image resolutions due to scale problems and information complexity. Deep learning promised to overcome these shortcomings due to its superior performance and versatility, proven with reported detection rates of ~90%. However, such models still find their limits in transferability across study areas, because of different tree conditions (e.g., isolated trees vs. compact forests) and/or resolutions of the input data. This study introduces a highly replicable deep learning ensemble design for ITC detection and species classification based on the established single shot detector (SSD) model. The ensemble model design is based on varying the input data for the SSD models, coupled with a voting strategy for the output predictions. Very high-resolution unmanned aerial vehicles (UAV), aerial remote sensing imagery and elevation data are used in different combinations to test the performance of the ensemble models in three study sites with highly contrasting spatial patterns. The results show that ensemble models perform better than any single SSD model, regardless of the local tree conditions or image resolution. The detection performance and the accuracy rates improved by 3–18% with only as few as two participant single models, regardless of the study site. However, when more than two models were included, the performance of the ensemble models only improved slightly and even dropped.

The evaluation of spatial planning results, or outcomes, has been rather neglected by scholars and practitioners. The causes of this neglect are linked to the characteristics of the planning systems in use or difficulties in quantifying results. To advance the state of the art of outcome evaluation, this paper focuses on assessing the implementation of national spatial planning objectives in urban landscapes through the use of an evaluation framework, which makes use of spatially explicit information. The framework is built around four dimensions, which reflect the main domains of spatial planning: efficient built-up development, conservation of agricultural land, landscape preservation and human perception. Indicators that are capable of capturing landscape changes in both time and space are used to verify the degree of conformance between adopted objectives and actual development patterns. We make use of spatially explicit data, as well as assess whether and where landscape changes occurred, by integrating the framework into a multi-criteria analysis. In the present study, the framework is tested in two study areas located in Switzerland and Romania, while the results are interpreted from the perspective of spatial planning approaches in the two countries. The efficiency and utility of the framework are demonstrated by the ability to provide valuable information that facilitates improvement in the performance of planning processes, such as identifying where the implementation of objectives is less effective, and the domains of affected spatial planning. Our findings indicate that the distance between objectives and outcomes can be attributed to differences in countries’ spatial planning approaches, which should also be placed into the wider economic, institutional and legislative context. Our study provides valuable insights for the integration of time series of spatial data into the evaluation procedure.

While sustainable forest management (SFM) policy processes are well developed, implementation on the ground remains a challenge. Given the diversity of biophysical conditions, economic histories and governance systems on the European continent, regionally and temporally adapted and adaptive solutions are needed for both social and ecological systems. To illustrate this, we apply (1) a biographic forest and woodland history approach to central Sweden’s Bergslagen region, where boreal sustained yield forestry was widely applied first and (2) a comparative case study approach using five European landscapes that represent different forest history phases in Scotland, Germany, Ukraine and Russia. Additionally, we illustrate the need to learn from reference landscapes for natural forest and cultural woodland systems such as in economically remote regions in Romania, Russia and on the Iberian Peninsula. We conclude that there is great opportunity for innovative knowledge production about both governance and management for different SFM dimensions based on comparisons among concrete landscapes. In addition, there is a need to develop local place-based social learning processes that are characterized by a focus on a geographical area, commitment to SFM policy visions and collaborative approaches to development that include both ecological and social systems.

Global changes impact the human-environment relationship, and, in particular, they affect the provision of ecosystem services. Mountain ecosystems provide a wide range of such services, but they are highly sensitive and vulnerable to change due to various human pressures and natural processes. We conducted a literature survey that focused on two main issues. The first was the identification of quantitative methods aimed at assessing the impact of land use changes in mountain regions and the related ecosystem services. The second was the analysis of the extent to which the outcomes of these assessments are useful and transferable to stakeholders. We selected papers through a keyword-driven search of the ISI Web of Knowledge and other international databases. The keywords used for the search were mountain land use change and ecosystem service. Quantitative approaches to ecosystem service assessment rely on suitable indicators, therefore land use/land cover can be used as an appropriate proxy. Landscape metrics are a powerful analytical tool; their use can increase the accuracy of assessments and facilitate the mitigation of specific phenomena, such as fragmentation or the reduction of core habitat areas. Mapping is essential: it is the basis for spatial analyzes and eases the interactions between stakeholders. Land use/land cover change is a temporal process, so both past and future approaches are meaningful. It is necessary to enhance information transfer from theory to practice. Increasing stakeholder awareness can lead to suitable management solutions, and, reciprocally, stakeholder feedback can help improve current assessment methodologies and contribute to developing new tools that are suitable for specific problems.