|
|
Forest health assessment in Czech Republic using Sentinel-2 satellite data
Lukeš, Petr ; Strejček, R. ; Křístek, Š. ; Mlčoušek, M.
This methodology aims to design a comprehensive system of nationwide assessment of the state of health of the Czech Republic based on Sentinel-2 satellite data analysis. The methodology addresses the entire process from the pre-processing of source satellite data using a novel approaches based on analysis of all-available satellite observations and their processing in the form of cloud-free mosaics of the Czech Republic using big data approach. In the next step, the products derived from cloud-free mosaics (vegetation indexes and other image analysis) are compared against extensive database of ground survey of forest health status (values of the leaf area index sampled as part of the development of the methodology - further denoted as LAI, database of tree defoliation ICPForests, airborne hyperspectral data acquired for selected study area, global forest losses database). For products with the best relationship to in-situ data, a predictive statistical model to yield LAI from satellite observations is developed. Forest health status is evaluated on the basis of yearly changes of the LAI values for cloud-free mosaics generated in the vegetation maximum. Individual pixels are classified into four health classes according to LAI growth rate or decrease in the observed period. The final assessment of the state of health is applied at the cadastral level, where each cadastral area is classified into four health classes based on the fraction of the lowest health status stands with significant LAI decrease to the total forest cover for stands up to 80 years of age
|
|
|
Tree species classification using sentinel-2 and Landsat 8 data
Havelka, Ondřej ; Štych, Přemysl (advisor) ; Kupková, Lucie (referee)
The main objectives of this master thesis are to evaluate and compare chosen classification algorithm for the tree species classification. With usage of satellite imagery Sentinel-2 and Landsat 8 is examined whether the better spatial resolution affects the quality of the resulted classification. According to past case studies and literature was chosen supervised algorithms Support Vector Machine, Neural Network and Maximum Likelihood. To achieve the best possible results of classification is necessary to find a suitable choice of parameters and rules. Based on literate was applied different settings which were subsequently evaluated by cross validation. All results are accompanied by tables, charts and maps which comprehensively and clearly summarize the answers to the main objectives of the thesis.
|
|
|
Evaluation of methods and input data for land cover classification: case study of the former military areas Ralsko and Brdy
Paluba, Daniel ; Štych, Přemysl (advisor) ; Brom, Jakub (referee)
Taking advantage of Earth Observation (EO) data for monitoring land cover has attracted the attention of a broad spectrum of researchers and end-users in recent decades. The main reason of increased interest in EO can be found mainly in open data of Landsat and Sentinel archive. The main objective of this study is to evaluate the accuracy of the classification algorithms Maximum Likelihood (ML) and Support Vector Machine (SVM) using Landsat 8 and Sentinel-2 data in the case studies of the former military training areas Brdy and Ralsko, which have undergone a very specific land cover development. The study evaluates the land cover in both case studies in 2016 and based on the obtained results discussing a usefulness of the selected data and methods. The results of the land cover classification achieved satisfactory accuracy - the overall accuracy was higher than 85 %. Based on the expectation, the results of accuracy based on SVM algorithm are higher than results obtained by ML algorithm. The highest accuracy has reached in the land cover classes of water bodies and coniferous forests, on the contrary, the lowest accuracy in built-up areas, sparse vegetation and bare soil. Keywords: Earth Observation, Support Vector Machine, Maximum Likelihood, Czechia, Sentinel-2, Landsat 8
|
|
|
MONITORING OF DEFOLIATION USING REMOTE SENSING TECHNIQUES
Prokopec, Karel ; Kolář, Jan (advisor) ; Fabiánek, Petr (referee)
The aim of this diploma thesis is a proposal of a methodology used for an assessment of the measure of defoliation based on the multispectral satellite images from missions Landsat and Sentinel-2. The first part of the thesis is dedicated to the introduction of the problematics of remote sensing using multispectral sensors and the basics of research into forest vegetation. Following on this part, there is a chapter considering possibilities of monitoring defoliation using resources of remote sensing, and the closely connected problematics of the health condition of forest vegetation. After that comes a description of the used data (the satellite images and the data of ground investigation by VÚLHM) and logically compounded process of transformation of the data from satellite images on the levels of defoliation. Outcomes of the thesis include analysis of the ability of single spectral bands and vegetation indices to predict defoliation of Norway spurce (Picea abeis) and Scots pine (Pius sylvestris) vegetation. The assessment of the measure of defoliation is demonstrated on single band in near-infrared region with used of linear regression model.
|
guest ::
