- Remote Sensing in Agriculture
- Botany and Plant Ecology Studies
- Integrated Water Resources Management
- Remote Sensing and LiDAR Applications
- Species Distribution and Climate Change
- Remote-Sensing Image Classification
- Spectroscopy and Chemometric Analyses
- Geology and Environmental Impact Studies
- Land Use and Ecosystem Services
- Remote Sensing and Land Use
- Soil Geostatistics and Mapping
- Geochemistry and Geologic Mapping
- Fire effects on ecosystems
- Plant Ecology and Soil Science
- Lichen and fungal ecology
- Data-Driven Disease Surveillance
- Climate change and permafrost
- Diverse Scientific Research in Ukraine
- Peatlands and Wetlands Ecology
- Agriculture, Plant Science, Crop Management
- Occupational and environmental lung diseases
- Urban Heat Island Mitigation
- Engine and Fuel Emissions
- Heavy metals in environment
- Smart Agriculture and AI
University of Warsaw
2015-2024
University of Warmia and Mazury in Olsztyn
2010
University of Dundee
2005
APPLIC (Czechia)
2002
Knowledge of tree species composition in a forest is an important topic management. Accurate maps allow for much more detailed and in-depth analysis biophysical variables. The paper presents comparison three classification algorithms: support vector machines (SVM), random (RF) artificial neural networks (ANN) using airborne hyperspectral data from the Airborne Prism EXperiment sensor. aim this to evaluate nonparametric algorithms (SVM, RF ANN) attempt classify five most common Szklarska...
Invasive and expansive plant species are considered a threat to natural biodiversity because of their high adaptability low habitat requirements. Species investigated in this research, including Solidago spp., Calamagrostis epigejos, Rubus successfully displacing native vegetation claiming new areas, which turn severely decreases ecosystem richness, as they rapidly encroach on protected areas (e.g., Natura 2000 habitats). Because the damage caused, European Union (EU) has committed all its...
Land cover information is essential in European Union spatial management, particularly that of invasive species, natural habitats, urbanization, and deforestation; therefore, the need for accurate objective data tools critical. For this purpose, Union’s flagship program, Corine Cover (CLC), was created. Intensive works are currently being carried out to prepare a new version CLC+ by 2024. The geographical, climatic, economic diversity raises challenge verify various test areas’ methods...
Europe’s mountain forests, which are naturally valuable areas due to their high biodiversity and well-preserved natural characteristics, experiencing major alterations, so an important component of monitoring is obtaining up-to-date information concerning species composition, extent, location. An aspect mapping tree stands the selection remote sensing data that vary in temporal, spectral, spatial resolution, as well open commercial access. For Tatra Mountains area, a unique alpine ecosystem...
A proliferation of invasive species is displacing native species, occupying their habitats and degrading biodiversity. One these the goldenrod (Solidago spp.), characterized by aggressive growth that results in habitat disruption as it outcompetes plants. This invasiveness also leads to altered soil composition through release allelopathic chemicals, complicating control efforts making challenging maintain ecological balance affected areas. The research goal was develop methods allow...
Climate change is significantly affecting mountain plant communities, causing dynamic alterations in species composition as well spatial distribution. This raises the need for constant monitoring. The Tatra Mountains are highest range of Carpathians which considered biodiversity hotspots Central Europe. For this purpose, microwave Sentinel-1 and optical multi-temporal Sentinel-2 data, topographic derivatives, iterative machine learning methods incorporating classifiers random forest (RF),...
Mountain forests are exposed to extreme conditions (e.g., strong winds and intense solar radiation) various types of damage by insects such as bark beetles, which makes them very sensitive climatic changes. Therefore, continuous monitoring is crucial, remote-sensing techniques allow the transboundary areas where a common policy needed protect monitor environment. In this study, we used Sentinel-2 Landsat 8 open data assess forest stands classification UNESCO Krkonoše/Karkonosze Transboundary...
This study is focused on the assessment of potential Sentinel-2 satellite images and Random Forest classifier for mapping forest cover types in northwest Gabon. The main goal was to investigate impact various spectral bands collected by satellite, normalized difference vegetation index (NDVI) digital elevation model (DEM), their combination accuracy classification type. Within area, five classes type were delineated: semi-evergreen moist forest, lowland freshwater swamp mangroves, disturbed...
• Involving citizens in science through mobile data collection and online analysis. We propose modern system architecture (SaaS & desktop GIS). describe a toolbox which transfers GIS geoprocessing to ArcGIS Online. test our WebGIS solution on OOH media visual pollution as use case.
Cambiophagous insects, fires and windthrow cause significant forest disturbances, generating ecological changes economical losses. The bark beetle (Ips typographus L.), inhabiting coniferous forests eliminating weakened trees, plays a key role in posing threat to tree stands, which are dominated by Norway spruce (Picea abies) covers large part of mountain areas, as well the lowlands Northern, Central Eastern Europe. Due dynamics phenomena taking place, EU recommends constant monitoring terms...
Climate change and anthropopression significantly impact plant communities by leading to the spread of expansive alien invasive plants, thus reducing their biodiversity. Due significant elevation gradients, high-mountain in a small area allow for monitoring most important environmental changes. Additionally, being tourist attraction, they are exposed direct human influence (e.g., trampling). Airborne hyperspectral remote sensing is one best data sources vegetation mapping, but flight...
The characterization of vegetation is a very important ecological task, especially in sensitive mountain areas, as alpine regions often respond to small short-term variations abiotic and biotic components well long-term global changes. Spatial techniques, such imaging spectroscopy, allow for detailed classification different syntaxonomic categories their status. Based on the Airborne Prism Experiment (APEX) simulated Environmental Mapping Analysis Program (EnMAP) data, this study focused...
Remote sensing is a suitable candidate for monitoring rapid changes in Polar regions, offering high-resolution spectral, spatial and radiometric data. This paper focuses on the spectral properties of dominant plant species acquired during first week August 2015. Twenty-eight plots were selected, which could easily be identified field as well RapidEye satellite imagery. Spectral measurements individual acquired, heavy metal contamination stress factors measured contemporaneously. As result,...
Mapping plant communities is a difficult and time consuming endeavor. Methods relying on field surveys deliver high quality data but are usually limited to relatively small areas. In this paper we apply airborne hyperspectral vegetation mapping in remote hard reach We classified 22 the Giant Mountains 3.12-m Airborne Prism Experiment (APEX) images, registered 288 spectral bands (10 September 2012). As classification algorithm, Support Vector Machines (SVM) was used. APEX were corrected...
The mapping of invasive plant species is essential for effective ecosystem control and planning, especially in protected areas. One the widespread plants that threatens richness Natura 2000 habitats Europe large-leaved lupine (Lupinus polyphyllus). In our study, this was identified at two sites southern Poland using airborne HySpex hyperspectral images, support vector machine (SVM) random forest (RF) classifiers. Aerial field campaigns were conducted three times during 2016 growing season...
The aim of this study was to evaluate and compare suitability aerial hyperspectral data (AISA Dual APEX sensors) Sentinel-2A for classification tundra vegetation cover in the Krkonoše Mts. National Park. We compared results (accuracy, maps) pixel-based (Maximum Likelihood, Suport Vector Machine Neural Net) object-based approaches. best (overall accuracy 84.3%, Kappa coefficient = 0.81) were achieved AISA using per-pixel SVM classifier 40 PCA bands. though only 1.7 percentage points lower. To...
This research focuses on the effect of trampling vegetation in high-mountain ecosystems through electromagnetic spectrum’s interaction with plant pigments, cell structure, water content and other substances that have a direct impact leaf properties. The aim study was to confirm use fluorescence methods variability state previously measured spectrometrically. most heavily visited part High Tatras Poland divided into polygons and, after selecting dominant species within alpine swards, detailed...
Recent developments in computer hardware made it possible to assess the viability of permutation-based approaches image classification. Such sample a reference dataset multiple times order train an arbitrary number machine learning models while assessing their accuracy. So-called iterative accuracy assessment techniques or Monte-Carlo-based can be useful tool when comes algorithm/model performance but are lacking actual classification and map creation. Due multitude trained, one has somehow...
Abstract Heavy metals and radioactive compounds are potentially hazardous substances for plants, animals humans in the Arctic. A good knowledge of spatial variation these soil primary producers, their sources, is therefore essential. In samples lichen Thamnolia vermicularis, Salix polaris Cassiope tetragona, collected 2014 Svalbard near Longyearbyen, concentrations following heavy were determined: Mn, Ni, Cu, Zn, Cd, Pb Hg, as well activity following: K-40, Cs-137, Pb-210, Pb-212, Bi-212,...
Knowledge of tree species composition is obligatory in forest management. Accurate maps allow for detailed analysis a ecosystem and its interactions with the environment. The research presented here focused on developing methods identification using aerial hyperspectral data. area located Southwestern Poland covers Karkonoski National Park (KNP), which was significantly damaged by acid rain pest infestation 1980s. High-resolution (3.35 m) Airborne Prism Experiment (APEX) images (288 spectral...
The objective of this study was to assess the relationship between hyperspectral reflectance soils and their albedo, measured under various roughness conditions. 108 soil surface measurements were conducted in Poland Israel. Each characterised by its diurnal albedo variation field as well spectra obtained laboratory. best fit model achieved post-processing manipulation spectra, namely second derivate transformation. Using a stepwise elimination process, four spectral wavelengths index...
Abstract Information about vegetation condition is needed for the effective management of natural resources and estimation effectiveness nature conservation. The aim study was to analyse non-forest mountain communities: synanthropic communities grasslands. UNESCO’s M&B Karkonosze Transboundary Biosphere Reserve selected as research area. analysis based on 40 field test polygons APEX hyperspectral images. measurements allowed collection biophysical parameters - Leaf Area Index (LAI),...
Abstract This research aims to discover the potential of hyperspectral remote sensing data for mapping mountain vegetation ecosystems. First, importance ecosystems global system should be stressed due mountainous forming a very sensitive indicator climate change. Furthermore, variety biotic and abiotic factors influence spatial distribution in mountains, producing diverse mosaic leading high biodiversity. The area covers Szrenica Mount region on border between Poland Czech Republic - most...