National Repository of Grey Literature 36 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Supraglacial lakes detection and volume estimation from remote sensing data
Rusnák, Samo ; Brodský, Lukáš (advisor) ; Šobr, Miroslav (referee)
Supraglacial lakes detection and volume estimation from remote sensing data Abstract Supraglacial lakes play an important role in understanding glacier dynamics, including their response to climate change. This thesis explores the problematics of estimating lake depth and volume using a physical model. This brings challenges in considering the influence of various factors, such as cryoconite on glacier surface and suspended particular matter, which influences physical model, which is in research mostly neglected. Regression analysis of the g parameter of a physical model, representing light attenuation coefficient, and supervised classification of supraglacial lakes is applied in this thesis. The results reveal the variability of parameter Ad, representing lake bottom albedo reflectance, and its impact on predicted supraglacial lakes depth and volume. The results highlight the problem of global parameterisation of the physical model of supraglacial lakes and the need for further research to improve its accuracy and explore future possibilities in this field. Keywords: supraglacial lake, remote sensing, machine learning, physical model, depth estimation, regression analysis
Determination of Snow Cover Area from RADAR imagery
Součková, Jana ; Potůčková, Markéta (advisor) ; Brodský, Lukáš (referee)
This thesis deals with snow cover mapping by using time-series of SAR images of the sensors ENVISAT ASAR and TerraSAR-X. The methodology is based on the so-called Nagler's algorithm, which is based on determination of the change of absorption of radar signal due to the liquid water content in the snow cover. The resulting ratio image is classified into the areas with wet snow or without it according to the selected threshold value. The results are compared with the maps of snow cover derived from MODIS optical data and with data from meteorological stations of CHMI. The main aims of this work are to suggest most suitable conditions (time of the year, weather) for acquisition of reference images, to find the change of the threshold value with respect the chosen reference image and the type of land cover. The same methodology should then be applied on the radar data of shorter wavelength. The obtained results will be further used for improving the methodology of snow cover mapping from SAR data in the Czech Republic.
Determination of Chlorophyll Content in Birch and Pine Trees Using Hyperspectral Data
Zachová, Kateřina ; Potůčková, Markéta (advisor) ; Brodský, Lukáš (referee)
The master thesis deals with the determination of the chlorophyll content in birch foliage (Betula pendula Roth) and Scots pine using hyperspectral data. The first part of the thesis concentrates on the literature search dealing with the methods of chlorophyll content in the foliage of selected plant species. In the practical part the emphasis is on the study of spectral reflectance curves and finding their relation to the chlorophyll content from the laboratory determination. Images taken with the hyperspectral sensor HyMap and spectral reflectance curves obtained with the ground ASD FieldSpec 3 spectrometer were available. Using the derived regression model chlorophyll maps were created for Scots pine for three selected locations in the Sokolov coal basin area.
Flood monitoring using satellite radar data for different land cover categories
Rauch, Tomáš ; Kolář, Jan (advisor) ; Brodský, Lukáš (referee)
The aim of this thesis is to find method for flood monitoring from radar images. The thesis deals with flood in general and with organization of flood protection. There are described principles of radar sensors. There is also summary of satellites with their parameters. Next part of the thesis describes interaction between radar beam and different types of surface. Theoretical part is closed by overview of the existing methods for flood monitoring. In the practical part there is method for flood monitoring applied to areas affected by flood. The process is based on the classification of the radar image. Using classification and digital elevation model is drawn boundary of flooded area. The result boundaries are compared with the existing maximal flooded areas.
Land cover change detection on the agriculture land
Klouček, Tomáš ; Štych, Přemysl (advisor) ; Brodský, Lukáš (referee)
The main purpose of thesis is creation and evaluation of models for change detection of arable land to grassland by Hybrid-based Change Detection method, which combined approaches based on the Vegetation Indices, Image Differencing and Principal Component Analysis. Six locations with different seasonal configuration of images with high resolution and one locality covered by image with very high resolution were used. The areas were spread across the foothill areas of the Czech Republic. The selection of predictors and the most suitable model was supported by statistical calculation. Application selected models were carried out using a multi-temporal object classification and their accuracy were verified using reference data. The benefit of this thesis is finding generally applicable model useful to investigate the land cover change and evaluation of the potentially most appropriate seasonal configuration of images. Valuable is also methodology in this thesis which focus on selection of predictors and calculation the order of the most appropriate models, which is unique in the available literature. The thesis provides useful findings fitting to insufficiently explored issue of Change Detection arable land to grassland. Powered by TCPDF (
Geographical Random Forest model evaluation in agricultural drought assessment
Bicák, Daniel ; Brodský, Lukáš (advisor) ; Brůha, Lukáš (referee)
Drought is a natural disaster, which negatively affects millions of people and causes huge economic losses. This thesis investigates agricultural drought in Czechia using machine learning algorithms. The statistical models utilised were Random Forest (RF), Geographical Random Forest (GRF) and Locally Tuned Geographical Random Forest (LT GRF). GRF consists of several RF models trained on a subset of original data. The final prediction is a weighted sum of the prediction of a local and global model. The size of the subset is determined by the tunable parameter. LT GRF addresses spatial variability of subset size and local weight. During the tuning process, optimal parameters are found for every location and then interpolated for unknown regions. The thesis aims to evaluate the performance of each model and compare GRF feature importance output with the global model. The best model features meteorological impor- tances are used to create a drought vulnerability map of Czechia. Produced assessment is compared to existing drought vulnerability projects. 1

National Repository of Grey Literature : 36 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.