|
Land cover classfication using artificial neural networks
Oubrechtová, Veronika ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
Land cover classification using artificial neural networks Abstract This Diploma thesis deals with automatic classification of the satellite high spatial resolution image in the field of land cover. The first half of the work contains the theoretical information about remote sensing and classification methods. The biggest attention is given to the artificial neural networks. In practical part of Diploma thesis are these methods used for the classification of SPOT satellite image. Keywords: remote sensing, image classification, artificial neural networks, SPOT
|
|
Detection options of drenage and ameliorate channels using remote sensing data
Čermák, Jan ; Potůčková, Markéta (advisor) ; Štych, Přemysl (referee)
The purpose of this work is to explore detection options of subsurface drainage systems using remote sensing data. Drainage drains soggy soil and increases its fertility, but also allows transport of nutrients such as nitrogen and phosporus into waterways. Location of drainage systems is often unknown because of missing or inacurrate project documentation. Theoretical part is mostly devoted to the description of remote and ground methods of drainage detection. Then objectives of the work are solved. Drainage indications are described in specialized aerial photographs of visible and infrared part of the spectrum. These indications are compared with historical project plans. Methods aimed to improve indication of drainage including Laplacian filter and NDVI are applied and evaluated. Main output is binary raster expressing location of drains. Accuracy of results is evaluated in relation to vectorized indication of drainage from the source images.
|
|
Laboratory/Field Spectroscopy and Remote Sensing Image Data for Vegetation Studies
Červená, Lucie ; Kupková, Lucie (advisor) ; Pavelka, Karel (referee) ; Müllerová, Jana (referee)
Dominant vegetation species of two structurally and functionally different montane ecosystems were studied by means of laboratory and field spectroscopy and remote sensing image data: (1) a homogeneous human-influenced evergreen coniferous forest represented by a Norway spruce forest in the Krušné hory Mountains and (2) a heterogeneous natural ecosystem of a relict arctic-alpine tundra in the Krkonoše Mountains with predominance of grasses. The first part dealing with the Norway spruce forest is especially focused on the methods of laboratory spectroscopy. The assessment of Norway spruce stands on a regional and a global scales requires detailed knowledge of their spectral properties at the level of needles and shoots in the beginning, but ground research is very time-demanding. Open spectral libraries could help to get more ground-truth data for subsequent analysis of tree species in forests ecosystems. However, the problem may arise with the comparability of spectra taken by different devices. The present thesis focuses on a comparability of spectra measured by a field spectroradiometer coupled with plant contact probe and/or two integrating spheres (Paper 3) and proves the significant differences in spruce needle spectra measured by the contact probe and integrating sphere, spectra of...
|
|
Possibilities of remote sensing in grassland vegetation and management interventions monitoring in the Giant Mountains
Pomahačová, Michaela ; Kupková, Lucie (advisor) ; Hais, Martin (referee)
Possibilities of remote sensing in grassland vegetation and management interventions monitoring in the Giant Mountains Abstract The aim of this thesis was to evaluate suitability of WorldView-2 imagery for grassland associations classification in the model area of Giant Mountains. The classification was based both on the legend compiled by a botanist, and on the legend of Natura 2000. In order to eliminate the effects of other types of land cover on the classification accuracy, a mask of grasslands was created. Using discriminant analysis, the significance of spectral bands of WorldView-2, as well as signifikance of selected vegetation indices and components from Principal Component Analysis (PCA) - to distinguish particular classes of grassland vegetation were evaluated. Based on the results of discriminant analysis, classifications using neural networks method and also maximum likelihood method were performed in ENVI 4.7 version software. The results of the both method were compared Key words: remote sensing, meadows association, classification, Giant mountains, WorldView 2
|
|
Determination of cloud types from satellite radiometric measurements
Opat, Lukáš ; Kolář, Jan (advisor) ; Kaňák, Ján (referee)
The thesis is focused on analysis and possible modifications of methods and procedures allowing the determination of various cloud types using the satellite data. Today, the main methods are concentrated around two the most applied international projects, one being developed for the instrument MODIS on board American Terra and Aqua polar satellites, and the other one being developed for the instrument SEVIRI on the European geostationary satellite Meteosat. The algorithms used for automatic discrimination of several cloud types operationally are created on these models. The American program MODIS Atmosphere have been created by NASA and the European program NWC SAF have been developed by organization EUMETSAT. Content of the thesis is to specify how input parameters influence final result of cloud determination in both models, and how results are depending on the external meteorological and geographical conditions during data acquisition. The effort will be given to identification of main drawbacks at two models and to identify conditions when their respective application is limited, their results different and to make steps towards possible modifications to mitigate the drawbacks. The analysis will use ground data and optimal developed procedure for validation of satellite data processing. The...
|
|
Evaluation of global changes of forest land based on remote sensing
Hladká, Anna ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
Evaluation of global changes in forest area based on remote sensing data Abstract: The aim of this project is using remote sensing data to assess change in global forest area. This work should give the outline of the principles of land cover classification, with a focus on forests based on satellite images, but also show a real solution in the evaluation of changes in forest areas in two selected regions. The first part is performed a literature review of all aspects of this sub-topic from the basic principles of remote sensing across the typology and characteristics of satellite sensors, which are giving the satellite images to land cover classification systems and characteristics of forest area. The next section describes the basic procedure for classification of satellite imagery and its possible variants. In my work there are explain the image corrections, the supervised and unsupervised classification, the method of checking the accuracy of classification or use of software. Selected area for my work was Riau in Indonesia and state of Oregon, USA. To these regions there are demonstrated practical procedure for classifying land cover and then its changes from the forest areas. In conclusion of my work the results are discussed and compared with available land cover databases. Key Words: Remote Sensing,...
|
|
The use of high temporal resolution satellite data for monitoring of water quality
Šmejkalová, Tereza ; Štych, Přemysl (advisor) ; Slačíková, Jana (referee)
The use of high temporal resolution satellite data for monitoring of water quality Abstract Present study compares possibilities of sea water quality monitoring using high temporal resolution satellite data. The theoretical part describes basic principles of remote sensing, the spectral characteristics of water and their change caused by substances present in the water. The analytical modeling methods of chlorophyll-a concentration retrieval from MERIS data are described. In the study three processors are used, standard MERIS processor Case 2 Regional, FUB/Wew Water processor and FLH/MCI processor. In total 10 satellite images are processed, five for each of the two studied areas, the Golfe du Lion in France and Skagerrak and Kattegat straights in Northern Europe. As there is only limited dataset of in situ measurements available to validate the results, it is impossible to decide which of the processors is the most suitable one. It is however clear that none of the globally applicable algorithms can be as accurate as algorithms developed for the exact location and atmospheric actual conditions.
|
|
Remote sensing for evalution of state and development of Spruce stands condition in the Giant Mountains
Musilová, Romana ; Kupková, Lucie (advisor) ; Štych, Přemysl (referee)
Bc. Romana Musilová: Využití dat DPZ pro hodnocení aktuálního stavu a vývoje smrkových porostů v Krkonoších Remote sensing for evaluation of state and development of Spruce stands condition in the Giant Mountains Abstract Monitoring the health status of forest areas using remote sensing methods are still under development. This master thesis focuses on the use of SPOT, Landsat, QuickBird and WorldView-2 images to evaluate condition of spruce stands in Giant Mountains National Park. For these purposes were selected vegetation indices available in the lite- rature. First satellite images were preprocessed and subsequently calculated vegetation indices. From the generally known were used Normalized Difference Vegetation Index, leaf area index and Simple Ratio. Than were calculated Green Vegetation Index and Red Green Index based on the monitoring of needles color changes. To evaluate moistu- re conditions were used indices Foliar Moisture Index and wide-band Normalized Diffe- rential Infrared Index. The goal was a comparison of the results of these indices and assessment of their applicability. Map outputs indices were compared with maps of de- foliation and mortality of coniferous stands by Ing. Milan Stoklasa. Keywords: remote sensing, Norway Spruce stands, Giant Mountains, vegetation indi- ces, SPOT,...
|
|
Identification of potentially suitable habitats for occurrence of European Ground Squirrel (Spermophilus citellus) using remote sensing
Kadeřábková, Tereza ; Kupková, Lucie (advisor) ; Hais, Martin (referee)
The aim of the thesis was to evaluate the possibilities of remote sensing (RS) data with different spatial resolution (UAV data with 5cm resolution, RapidEye satellite data with 5m resolution and Sentinel-2A data with 10m resolution) and of remote sensing methods (unsupervised and supervised classifications, vegetation indices NDVI and TVI) to identify potentially suitable habitats for European ground squirrel. The analyses were first carried out in Velké Pavlovice small area of interest and consequently in a broader area of interest comprised of five regions of Moravia and Slovakia. Data form mapping of biotopes and squirrels' burrows collected within a project "Sysli pro krajinu, krajina pro sysly" (European ground squirrels for landscape, landscape for European ground squirrels) were also used for the analyses. Remote sensing methods were first tested in Velké Pavlovice area using RapidEye data. The method providing the best results in the detection of European ground squirrel burrows was then used for a burrows detection in the broader area of interest (five regions) using Sentinel-2A data. The accuracy of results was defined as a proportion of the burrows detected by the resulting layer derived from RS data to the overall number of burrows mapped in the field. Best results were obtained for...
|
|
The use of vegetation indices to study temporal variation in vegetation phenology
Beránková, Petra ; Štych, Přemysl (advisor) ; Hesslerová, Petra (referee)
1 ABSTRACT The work deals with the use of vegetation indices to study temporal variation in vegetation phenology. The first part was devoted to detailed analysis of domestic and foreign literature, which deals with the work processed in this field. The main research questions were if changed start, end and length of growing period during the analysis period. Other research theme was comparision with ground phenological data. Another objective of this work was search dependencies computed data phenological variables from vegetation indicies with phenological ground data. As a basic data set was used GIMMS set, which distributes the vegetation index NDVI. Other data sets were MERIS MTCI, data MODIS with vegetation indices NDVI, EVI a LAI. The results of analyzes of vegetation phenology show trends in most shifts at the beginning of growing season, where was a shift to an earlier time. Results of the analysis of vegetation remote sensing data with ground-based phenological data ČHMÚ were unfolding always according to the specific forest phenological stations. Interesting results were at the phenological station Svoboda nad Úpou, where the results of trends directives were consistent in almost all data sets. Comparison of process curves vegetation indicies with ground data corresponded most curves at selected...
|