|
| |
|
|
Prostorová analýza heterogenity pozemků z družicových dat
Kouřil, Jiří
Field heterogeneity is one of the prerequisites for many methods of precision agriculture, like for example variable sowing or variable application of fertilizers. One method of determining heterogeneity is an analysis of multispectral satellite images. The main aim of this thesis is to verify the hypothesis that there is at least a medium positive correlation between values of vegetation indices calculated from multispectral images and yields measured on four fields of a total area of approximately 75 ha during seasons 2019–2021. All fields are managed by the company Spearhead Czech s.r.o. which also provided data for preparing yield maps. These were statistically compared with three vegetation indices NDVI, EVI, and NDRE, which were calculated from Sentinel-2 satellite images. Results of correlation analysis show a medium correlation between vegetation indices and yields on two of four fields, whereas only weak positive and in some cases weak negative correlation can be observed on the other two. This was probably caused by droughts that influenced vegetation in these fields in 2019 and 2021. The thesis shows the potential of satellite images to determine field heterogeneity despite the comparison of vegetation indices and yields of different crops.
|
|
|
Evaluation of forest vegetation based on time series of remote sensing data
Laštovička, Josef ; Štych, Přemysl (advisor) ; Brom, Jakub (referee) ; Bucha, Tomáš (referee)
Příloha k disertační práci: Abstrakt v AJ (Mgr. Josef Laštovička) Abstract This dissertation thesis deals with the study of forest ecosystems in the central Europe with the time series of multispectral optical satellite data. These forest ecosystems have been influenced by biotic and abiotic disturbances for the last decade. The time series of the satellite data with high spatial resolution allow the detection and analysis of forest disturbances. This thesis is mainly focused primally on free available Landsat and Sentinel-2 data, these two data types were compared. From methods, the difference time series analyses / algorithms were used. The whole thesis can be divided into two main parts. The first one analyses usability of classifiers for detection of forest ecosystems with per-pixel and sub-pixel methods. Specifically, the Neural Network, the Support Vector Machine and the Maximum Likelihood per-pixel classifiers were used and compared for different types of data (for data with high spatial resolution - Landsat or Sentinel-2; very high spatial resolution - WorldView-2) and for classification of protected forest areas. The Support Vector Machine were selected as the most suitable method for forest classifications (with most accurate outputs) from the list of selected per-pixel classifiers. Also, Spectral...
|
|
| |
|
| |
|
|
Changes in the coverage and orography of the 4th order basin in relation to the construction of the motorway evaluated from Sentinel-2 satellite data and aerial LiDAR data
ŽŮČEK, Petr
This research is focused on changes of land cover and orography in fourth order river basin. For this purpose, satellite multispectral Sentinel-2 data and airborne LiDAR data were used. The main goal of this work was to verify to which extent can free and publicly available Sentinel-2 data be used to assessment of landscape changes for the use of land planning. To verify the goal the timeseries of the Sentinel-2 satellite data was used for the assessment of the land cover in a relation to the construction of the D3 highway on the selected area. Sentinel-2 data were downloaded, resampled, and classified. Maximum Likelihood method of supervised classification was used. The categories of land cover were created using training areas in the ArcMap software. The accuracy of the classi-fication from 22. 09. 2020 was verified using validation points, which were generated randomly. By field survey classes of land cover were defined. From final classification data, new data about the change of land cover were obtained. The LiDAR data were resampled to the same spatial resolution and differences were evaluated. Areas with significant variances in orography were retrieved. From LiDAR, drainage network models were created. The results of models were compared and discussed. The results of comparison of Sentinel-2 data from 2017 to 2020 shows significant increase in representation of areas with sparse vegetation by 46,39 ha and areas with grass and shrub vegetation by 38,39 ha. Furthermore, there was an increase in meadow areas by 7,02 ha and forest clearing by 1,95 ha. The representation of arable land was decreased by 34,78 ha, forests by 29,05 ha, water areas by 12,12 ha, urbanization by 13,39 ha and areas with ongoing construction by 4,38 ha. The results of Li-DAR data comparison showed several areas with significant orography alteration. The compari-son of drainage network models revealed a distinct variation. Significant part of the runoff water flowed into the neighboring 1-06-03-0030 basin. After the recultivation of former waste pond, divided parts of the Hodějovice stream water gate were connected and the water from the whole basin ends in an outlet of the basin on which this research is focused on. The overall accuracy 0,914 and Kappa coefficient of 0,902 show that used ap-proach of Sentinel-2 data processing provides with sufficiently spatially and themati-cally accurate classification of land cover, apart from the area of urbanization. Classi-fication in built-up area had the user-accuracy of 0,867. Data obtained from Sentinel-2 may be used in several parts of land planning. It is also possible to use them for: updates of land usage, determination of actual growth condition, monitoring of forest complexes or for monitoring of recultivations. LiDAR data may be effectively used for the monitoring of orography variations, modelling of drainage network models, and determining of critical points.
|
|
|
Possibilities of using satellite data Sentinel-2 in landscape planning
TOMS, Petr
The diploma thesis focuses on the analysis of land cover changes and characteristics of humidity in the Dobřejovický stream basin, using Sentinel-2 data. The aim of the work was to find out how the obtained results can be used for landscape planning. The first part of the thesis deals with the literature search, which is based on the principles of remote sensing, electromagnetic spectrum, spectral expression of objects, multispectral data and and satellite data Sentinel-2, provided by the European Space Agency. The practical part contains the description of the area of interest, the methods used in processing Sentinel-2 data. An important part is focused on the classification of data from which the outputs are created, the results are interpreted and the evaluated accuracy of the classification of land cover changes. Furthermore, the practical part is devoted to the calculation of vegetation indices, thanks to which we can obtain information about humidity characteristics. Part of the work also points to the usability of the obtained results in the forms of landscape planning.
|
|
|
Testing possibilities to extract selected landscape characteristics for description of indication-relevant bird species habitats in the Krkonoše Mts. from remote sensing data
Polák, Mojmír ; Kupková, Lucie (advisor) ; Janík, Tomáš (referee)
The thesis uses remote sensing data from two spatial scales (Sentinel-2 with a 10 x 10 m pixel and PlanetScope 3 x 3 m. It explores the possibilities of extracting selected landscape characteristics (spectral indices, land cover type, landscape metrics). In order to evaluate which characteristics and at what scale are statistically significant for the occurrence of 23 selected bird species, species richness in quadrats and the number of species of the order Passeriformes in the Krkonoše Mountains. Data on species occurrence were mapped in the year 2012-2014 The strength of the relationship between characteristics and abundance was determined by Pearson's correlation coefficient. It could not be confirmed that data with higher spatial resolution would be more beneficial for extracting landscape characteristics. Overall, the landscape characteristics did not prove functional relationships for all selected species, but for some species, species richness, and order of Passeriformes, the assumption of elevation and land cover as important factors was confirmed. Land cover was analysed using the Random Forest supervised classification method in Google Earth Engine with an overall accuracy of 78 % for Sentinel-2 data, both in tundra and in the rest of the area, and 77 % for PlanetScoce data in tundra, 66...
|
|
| |
|
|
Classification of selected agricultural crops from time series of Sentinel-2 and PlanetScope imagery in Kutnohorsko model area
Kuthan, Tomáš ; Kupková, Lucie (advisor) ; Potůčková, Markéta (referee)
Classification of selected agricultural crops from time series of Sentinel-2 and PlanetScope imagery in Kutnohorsko model area Abstract The thesis is focused on the analysis of spectral characteristics of selected agricultural crops druring agriculutural season from time series of Sentinel -2 (A and B) and PlanetScope sensors in the model area situated around the settlements of Kolín and Kutná Hora. It is based on the assumption that the use of multiple dates of image data acquired crops in different phenological phases of the crops allows better identification of crop species (Lu et al., 2004). The aim of the thesis was to analyse the characteristics of the seasonal course of spectral features of selected agricultural crops (sugar beet, spring barley, winter barley, maize, spring wheat, winter wheat, winter rape) and to determine the period of the year suitable for the differentiation of individual crops. Another aim of the thesis was to classify these crops in the model area from time series of two above-mentioned sensors and to compare the accuracy of the pixel and object-oriented classification approach for multitemporal composites and the accuracy for monotemporal image from the term when the individual crops are clearly distinguishable. The training and validation datasets and the classification mask...
|
guest ::
