The Apuseni Mountains possess a wide range of mountain grassland types that have a natural and aesthetic value. In this traditional cultural landscape, small-scale farming structure and a traditional system of land use exist. Landscapes change with the prevailing socio-economic and social framework conditions. An inter- and trans-disciplinary, project, known as 'Project Apuseni' studied the land use system, vegetation, landscape patterns and their actual changes within the process of societal transformation, and predicted the future outlook for the Apuseni Mountains, which are located in north-western Romania and cover an area of ca. 11,000 km. The actual state of species and landscape diversity is high in the whole area of the Apuseni Mountains and results from traditional and extensive management practices. Within the Project Apuseni, land use scenarios, the future alternatives for grassland management and the opportunities and risks in the context of nature conservation and agriculture were evaluated.Keywords: Apuseni mountains grassland; Romania; small-scale farming structure
The forest vegetation Of the montane and subalpine belt (800-2300 m a.s.1.) of eastern Mt.Olympus, Greece, was analysed using site description and phytosociological methods.Based on these results, conclusions were drawn about structure, successions, and stability of these forests.lt could be demonstrated, that beech (Fagus)-forest is not forming a continuous belt, it is restricted to "extrazonal" islands inmidst of Pinus-forest.A subalpine scrub belt ("Krummholz") is absent, tau l Pinus heldreichii-trees are forming an open forest up to the treeline.On the eastern-slope Mt.Olympus, the main canopy trees are Fagus sylavatica (beech), Abies X borisii-regis (fir), Pinus nigra ssp.pallasiana (black pine), and Pinus heldreichii.Twelfe forest types could be distinguished: Six forest types were dominated by Fagus sylvatica.They included in the montane belt a Lathyr o alpestris -Fagetum (having three elevation-related subtypes), and in the upper montane and subalpine belt an Orthilio-Fagetum and the Fagus sylvatica-Satureja grandiflora-community.Very locally, transitional stands to Tilio-Acerion forests with Acer pseudo-platanus in the canopy occurred.Six forest types dominated by Pinus trees were distinguished.The "montane" Staehelino-Pinetum pallasianae and the "subalpine" Pinus heldreichii-community could be related to different elevation.Each of them was subdivided into two subtypes.Two forest types dominated by pine trees most likely were seral communities: In the Pinus nigra-Quercetalia pubescenti-petraeae-community (< 1200 m a.s.1.),Pinus nigra is "associated" with Fraxinus ornus and Ostrya carpinifolia, less frequently with Quercus pubescens.The Pinus he/dreichii-F agetalia -community was found at higher altitudes, and contained Fagus sylvatica in the lower tree tier.Main objective of that study was to investigate the ecological situation of the Fagusforests of Mt.Olympus.These forests are growing on a solid, dolomitic triassic limestone formation.lt could be shown, that the ground vegetation of these deciduous forests is completely changing with increasing elevation.At all elevations, Fagus sylvatica forests prefer shady, north-exposed sites.lt appears, that beech on Mt.Olympus is restricted by its limited physiological drought tolerance.
Arnica montana L. is a medicinal plant with significant conservation importance. It is crucial to monitor this species, ensuring its sustainable harvesting and management. The aim of this study is to develop a practical system that can effectively detect A. montana inflorescences utilizing unmanned aerial vehicles (UAVs) with RGB sensors (red–green–blue, visible light) to improve the monitoring of A. montana habitats during the harvest season. From a methodological point of view, a model was developed based on a convolutional neural network (CNN) ResNet101 architecture. The trained model offers quantitative and qualitative assessments of A. montana inflorescences detected in semi-natural grasslands using low-resolution imagery, with a correctable error rate. The developed prototype is applicable in monitoring a larger area in a short time by flying at a higher altitude, implicitly capturing lower-resolution images. Despite the challenges posed by shadow effects, fluctuating ground sampling distance (GSD), and overlapping vegetation, this approach revealed encouraging outcomes, particularly when the GSD value was less than 0.45 cm. This research highlights the importance of low-resolution image clarity, on the training data by the phenophase, and of the need for training across different photoperiods to enhance model flexibility. This innovative approach provides guidelines for mission planning in support of reaching sustainable management goals. The robustness of the model can be attributed to the fact that it has been trained with real-world imagery of semi-natural grassland, making it practical for fieldwork with accessible portable devices. This study confirms the potential of ResNet CNN models to transfer learning to new plant communities, contributing to the broader effort of using high-resolution RGB sensors, UAVs, and machine-learning technologies for sustainable management and biodiversity conservation.
