|
|
Modeling population with topographic data
Šimbera, Jan ; Brůha, Lukáš (advisor) ; Hudeček, Tomáš (referee)
Accurate spatial population data are an important requirement in many applications. In this thesis, the problem of disaggregating the spatial distribution of population density and rent costs using a machine learning model is studied. An approach based on freely available ancillary data such as OpenStreetMap and Urban Atlas is proposed and implemented in the form of an automated Python toolbox for ArcGIS. The applications on the urban areas of Prague, Vienna and Ljubljana show promising results, overperforming the competing population disaggregation solutions in spatial resolution and displaying a satisfying degree of transferability. A number of further improvements is suggested. Powered by TCPDF (www.tcpdf.org)
|
|
|
Spatial disaggregation of population data using 3D city model
Kovačka, Vít ; Brůha, Lukáš (advisor) ; Štych, Přemysl (referee)
The thesis studies the use of existing 3D models as a source of information about the volume of buildings, which is further used in statistical modeling of spatial data. Existing approaches to the spatial data disaggregation are presented, including those utilizing three- dimensional data. The method of obtaining volume information is implemented employing ArcPy libraries for multipatch format. Open source PostgreSQL PostGIS database functions were put in use to retrieve the volumes from rasters containing information about the height of the building. Disaggregation, performed with both 2D and 3D data, is evaluated in terms of accuracy, model performance, and the ability of 3D data to replace some 2D data. The proposed calculation methods and model results are critically evaluated. Keywords: 3D data, volume, Prague, disaggregation, modeling, ArcPy, PostGIS, machine learning
|
|
|
Modeling population with topographic data
Šimbera, Jan ; Brůha, Lukáš (advisor) ; Hudeček, Tomáš (referee)
Accurate spatial population data are an important requirement in many applications. In this thesis, the problem of disaggregating the spatial distribution of population density and rent costs using a machine learning model is studied. An approach based on freely available ancillary data such as OpenStreetMap and Urban Atlas is proposed and implemented in the form of an automated Python toolbox for ArcGIS. The applications on the urban areas of Prague, Vienna and Ljubljana show promising results, overperforming the competing population disaggregation solutions in spatial resolution and displaying a satisfying degree of transferability. A number of further improvements is suggested. Powered by TCPDF (www.tcpdf.org)
|
guest ::
