|
|
Estimation of winter wheat yield using machine learning from airborne hyperspectral data
Švik, Marian ; Pikl, Miroslav ; Janoutová, Růžena ; Veselá, Barbora ; Slezák, Lukáš ; Klem, Karel ; Homolová, Lucie
Methods based on optical remote sensing allow nowadays to assess crop conditions over larger areas. The assessment of crop conditions and potential estimation of crop yields in the early growth\nstages can help farmers to better target their management practice such as application of fertilizers. In this study we analysed airborne hyperspectral images acquired several times during the growing season over two experimental sites in the Czech Republic (Ivanovice and Lukavec). The field experiments on winter wheat included 12 levels of fertilisation (combination of organic and mineral fertilisers). Such an experiment design and the possibility of combining the data from two sites together increased the variability in our wheat yield dataset, which varied between 2.8 and 10.0 t/ha. Further, we used a machine learning method – namely gaussian process regression from the ARTMO toolbox to train two variants of models: a) combining the spectral data from both sites and from the multiple acquisition days and b) combining the spectral data from both sites for individual acquisition days.The results showed that it was feasible to predict wheat yield already at the beginning of April with R2 > 0.85. This promising result, however, requires more thorough validation and therefore we plan to include more data from other sites in the next steps.
|
|
|
UAV monitoring of montane peatbogs
Kevešová, Adriana ; Langhammer, Jakub (advisor) ; Lendzioch, Theodora (referee)
This thesis deals with UAV imagery analysis as used to monitor environmental settings, in this case a particularly sensitive ecosystem of a peatbog. The non-destructive aspect of UAV monitoring based on remote access to the studied area is crucial in this scenario. Introduction to the topic, examples of the employment of UAV technologies and the possibilities of their application in monitoring peatbogs are followed by examples of visual data analysis with the help of various software on the multispectral data acquired at peatbog Rokytka in the Šumava National Park. Key words: UAV, monitoring, peatbogs, remote sensing, multispectral imaging, classification
|
|
|
Vliv vegetace na letní teplotní extrémy ve městech hodnocené z pozemních a leteckých dat
ROHÁČ, Václav
This thesis examines the effect of surface types and vegetation types on ambient temperature during summer temperature extremes. The theoretical part targets the topics of remote sensing, electromagnetic radiation, urban and global climate. Within the practical part, 3 areas of interest were selected from aerial hyperspectral data from the territory of the statutory city of České Budějovice, each representing a different part of the city in terms of land use. By means of data analysis, graphs showing the influence of the relative representation of the variant surfaces on the temperature were created using the linear regression method. From the maps of tree species occurring in the parks of the first two areas, the most abundant species were selected and the average temperature within 2 meters of them was examined. The thesis also includes an evaluation of a questionnaire answered by city residents on the topic of preferences and knowledge about the urban green space.
|
|
|
Přirozená obnova lesa po disturbanci lýkožroutem smrkovým \kur{ (Ips typographus} L.)
ROTOVÁ, Alžběta
This master's thesis focuses on evaluation of natural regeneration of forest in the non-intervention zone near Březník. Spectral data and spectral vegetation indices are examined and put in relation to terrain data for evaluation of the forest recovery. The highest gradation of bark beetle in the study area occurred between 1995 and 1998. Since then the tree defoliation accelerated the natural forest recovery. I assessed the forest recovery in 15 research plots and compared the recovery with the data collected by the Šumava national park in 2008 and 2009. Results of terrain measurement showed slight decrease in number of seedlings and saplings compared to years 2008 and 2009. Comparison of the field recovery data with the spectral indices revealed a regression relation between the natural regeneration and the vegetation indices. When comparing these data, the most suitable index for evaluating the natural regeneration was the index FRI2. The optimal time within the vegetation period for the evaluation of natural forest recovery using spectral data was also tested in this thesis. Results showed the optimum is at the end of spring and at the end of vegetation season. The highest rate of natural regeneration in our study area is on the west slopes of area Mokrůvky and on the south-west slopes exposed to high amounts of sunlight. Areas of closed forest formations are followed by areas where the forest regeneration is pure but the herbaceous vegetation is greatly developed. Results of the thesis show that spectral data and spectral indices are suitable for evaluation of forest recovery. The remote sensing methods bring the systematic data coverage for better understanding of the forest processes.
|
|
|
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.
|
|
|
Analýza energetické bilance intravilánu města pomocí metod dálkového průzkumu Země
ŠOUREK, David
The energy balance of each urban area depends on the specifics of active surface and other complex phenomena. In general, compared to the surrounding rural landscape, dry and impermeable surfaces predominate in urban areas. Different types of built-up areas have various properties determining how distributed solar radiation is. Overall, it is through energy fluxes defined by the sensible heat flux, the latent heat flux of evaporation, and the soil heat flux. Besides, vegetation plays a significant role in the proportions of fluxes. Plants can effectively transform the obtained solar radiation and thus influence the microclimatic situation through the cooling effect of evapotranspiration or other ecosystem services. Nevertheless, the efficiency depends on the state of vegetation and other prevailing conditions (weather, etc.). As the study area was selected the town of Písek. The research took place on two summer and two autumn days using remote sensing and statistical evaluation. The results showed the growing dependence of the latent heat flux of evaporation in localities with a higher vegetation density and a sufficient water supply. High values of surface temperature and sensible heat flux occurred in built-up areas with predominant materials with a large specific heat capacity, i.e. concrete, asphalt, sheet metal, stone etc. These indicators thus defined some problematic types of built-up areas, especially in terms of surface overheating or of the occurrence of local heat islands. Specifically, it was the historic centre, industrial zones and shopping centres. A better microclimatic situation prevailed in the park with a water surface, suburbs and built-up areas of family houses.
|
|
|
Vliv způsobu využití krajiny na místní klima
RŮŽIČKA, Vít
The aim of this diploma thesis is to analyze the influence of farming in the protected landscape area Třeboňsko on the local climate, and to search for mutual connections. Current and historical data from Earth remote sensing from Landsat satellites were used for the work itself and the subsequent presentation of the results using graphs. For the evaluation, it was necessary to master the practical procedure of processing satellite data obtained from the Landsat program, including the analysis of dynamic quantities. The evaluation indicators were mainly surface temperature and spectral in-dices NDVI and NDMI. While the amount of vegetation and humidity in the landscape increased slightly over the observed period, the temperature remained the same or decreased slightly. Based on the obtained data, it is possible to assume that the local climate in the Třeboň region is influenced by vegetation through evapotranspiration and regional climate change.
|
|
|
Tepelný ostrov města - analýza stavu a možnosti zlepšení
CHVOJKOVÁ, Aneta
Increasing surface temperature in urban environments along with the creation of heat islands is one of the most visible phenomena of a worsening climate in general. This phenomenon is inherently linked to the increasing rate of urbanisation and urban development. Heat islands in cities are formed by an accumulation of high surface temperatures and differ significantly from areas in their rural surroundings. The surface temperature depends on several factors. These include, including but not limited to, colour, permeability or material of the surface, as well as the presence of vegetation in the given area or the layout of the streets. Anthropogenic activity caused by fossil fuel combustion or transport also has a significant impact on the temperature in urban environments. One of the most efficient tools to reduce the rise in temperatures is in particular high-quality vegetation and water retention in urban environments and the landscape in general. The area of interest of this work, which deals with the topic described above, is Kardašova Řečice with twelve determined locations. Using satellite data analysis, problematic areas in terms of surface temperature and several smaller heat islands were identified. The results of the spectral vegetation indices analysis showed a mutual correlation between the surface temperature and the presence of vegetation, which was analysed by NDVI and NDMI spectral vegetation indices data. The highest temperatures and the lowest surface humidity were found in areas with the least vegetation (greenery). The situation was the opposite in areas with sufficient vegetation cover and water for evapotranspiration. Since vegetation has been proved to have a significant positive impact on reducing the surface temperature in urban environments, a strategy was suggested to improve the urban living conditions by implementing a suitably selected green and green-blue infrastructure.
|
|
| |
guest ::
