A5049575974- Land Use and Ecosystem Services
- Remote Sensing in Agriculture
- Soil and Land Suitability Analysis
- Urban Planning and Valuation
- Remote Sensing and Land Use
- Wildlife-Road Interactions and Conservation
- Urban Green Space and Health
- Historical and Environmental Studies
- Remote Sensing and LiDAR Applications
- Remote-Sensing Image Classification
- Crop Yield and Soil Fertility
- Urban Planning and Landscape Design
- Economic and Environmental Valuation
- Wheat and Barley Genetics and Pathology
- Soil and Water Nutrient Dynamics
- Ecology and Vegetation Dynamics Studies
- Mediterranean and Iberian flora and fauna
- Impact of Light on Environment and Health
- Species Distribution and Climate Change
- Geographic Information Systems Studies
- Diverse Aspects of Tourism Research
- Smart Agriculture and AI
- Soil Geostatistics and Mapping
- Irrigation Practices and Water Management
- Agricultural Development and Policies
University of Perugia
2015-2024
Google Earth Engine (GEE) is a versatile cloud platform in which pixel-based (PB) and object-oriented (OO) Land Use–Land Cover (LULC) classification approaches can be implemented, thanks to the availability of many state-of-art functions comprising various Machine Learning (ML) algorithms. OO approaches, including both object segmentation textural analysis, are still not common GEE environment, probably due difficulties existing concatenating proper functions, tuning parameters overcome...
With the general objective of producing a 2018–2020 Land Use/Land Cover (LULC) map Maiella National Park (central Italy), useful for future long-term LULC change analysis, this research aimed to develop Landsat 8 (L8) data composition and classification process using Google Earth Engine (GEE). In process, we compared two pixel-based (PB) object-based (OB) approaches, assessing advantages integrating textural information in PB approach. Moreover, tested possibility L8 panchromatic band...
PlanetScope (PL) high-resolution composite base maps have recently become available within Google Earth Engine (GEE) for the tropical regions thanks to partnership between and Norway’s International Climate Forest Initiative (NICFI). Object-based (OB) image classification in GEE environment has increased rapidly due broadly recognized advantages of applying these approaches medium- images. This work aimed assess land cover (a) adopting an OB approach with PL data; (b) integrating datasets...
Understanding grassland habitat dynamics in space and time is crucial for evaluating the effectiveness of protection measures developing sustainable management practices, specifically within Natura 2000 network light European Biodiversity Strategy. Land cover maps, derived from remote sensing data, are essential understanding long-term changes vegetation land use assessing impact on ecosystems. In this study, we conducted a 20-year analysis landscapes Umbria, Italy, using Random Forest...
Abstract. The most recent and significant transformations of European landscapes have occurred as a consequence series diffused, varied often connected phenomena: urban growth sprawl, agricultural intensification in the suitable areas abandonment marginal areas. These phenomena can affect dramatically ecosystems' structure functioning, since certain modifications cause landscape fragmentation while others tend to increase homogeneity. Thus, thorough comprehension evolution trends landscapes,...
SUMMARY This study was aimed at comparing in-field parameters and remote sensing NDVI (normalized difference vegetation index) by both satellite (SAT) unmanned aerial vehicle (UAV) for the assessment of early nitrogen (N) status prediction yield in winter wheat ( Triticum aestivum L.). Six increasing N rates, i.e., 0, 40, 80, 120, 160, 200 kg ha −1 were applied, half tillering shooting. Thus, when crop monitored between two applications, consecutive treatments differentiated from each other...
Precision agriculture (PA) is a management strategy that analyzes the spatial and temporal variability of agricultural fields using information communication technologies with aim to optimize profitability, sustainability, protection agro-ecological services. In context PA, this research evaluated reliability multispectral (MS) imagery collected at different resolutions by an unmanned aerial vehicle (UAV) PlanetScope Sentinel-2 satellite platforms in monitoring onion crops over three dates....
This study aimed to compare standard and precision nitrogen (N) fertilization with variable rate technology (VRT) in winter wheat (Triticum aestivum L.) by combining data of NDVI (Normalized Difference Vegetation Index) from the Sentinel 2 satellite, grain yield mapping, protein content. Precision N rates were calculated using simple linear models that can be easily used non-specialists agriculture, starting widely available data. To remove effects not measured or unknown factors, area about...
Despite ecosystem services having been broadly studied in the scientific literature, they are still hardly integrated policy-making and landscape management. The lack of operative tools for their application is a main limiting factor such operationalization. In this work, framework including 53 livability produced by biophysical socioeconomic subsystem, or interaction, was developed considering local study area. All were characterized terms need to access Service Benefiting Areas (SBAs,...
In contemporary agriculture and environmental management, the need for precise accurate crop maps has never been more vital. Although object-based (OB) methods within Google Earth Engine (GEE) improve accuracy output quality in contrast to pixel-based approaches, their application classification remains relatively rare. Therefore, this study aimed develop an OB methodology crops located central Italy's Lake Trasimeno area. This employed spectral bands, indices (Normalized Difference...
This study compares simplified and advanced precision nitrogen (N) fertilization approaches for winter wheat relying on Sentinel-2 NDVI, grain yield maps, protein content. Five N treatments were compared: (1) a standard rate, calculated by typical balance (Flat-N); (2) variable rate using linear model, adopting proportional strategy (NDVI directly related) (Var-N-dir); (3) compensative inversely (Var-N-inv); (4) the AgroSat model (Var-N-Agrosat); (5) applying Agricolus (Var-N-Agricolus). The...
Grasslands cover a substantial portion of the earth’s surface and agricultural land is crucial for human well-being livestock farming. Ranchers grassland management authorities face challenges in effectively controlling herders’ grazing behavior utilization due to underdeveloped infrastructure poor communication pastoral areas. Cloud-based decision support systems (DSS) are needed address this issue, promote sustainable use, preserve their ecosystem services. These should enable rapid...
Seminatural grasslands are among the most threatened habitats in Europe and worldwide, mainly due to changes in/abandonment of their traditional extensive use by grazing animals. This study aimed develop an innovative model that integrates plant biodiversity, animal husbandry, geo-informatics manage preserve seminatural protected areas. With this objective, integrated was conducted on hilly, montane, (to a minimum extent) subalpine belts Maiella National Park, one Europe’s biodiversity-rich...
Mapping informal settlements’ diverse morphological patterns remains intricate due to the unavailability and huge costs of high-resolution data, as well spatial heterogeneity urban environments. The accessibility high-spatial-resolution PlanetScope imagery, coupled with convenience simple non-iterative clustering (SNIC) algorithm within Google Earth Engine (GEE), presents potential for Geographic Object-Based Image Analysis (GEOBIA) map morphology deprivation pockets in a complex built-up...
Soil-sample collection and strategy are costly time-consuming endeavors, mainly when the goal is in-field variation mapping that usually requires dense sampling. This study developed tested a streamlined soil methodology, applicable at field scale, based on an unsupervised classification of Sentinel-2 (S2) data supporting definition reduced soil-sampling schemes. The occurred in two agricultural fields 20 hectares each near Deruta, Umbria, Italy. S2 images were acquired for bare fields....