Geovisualisation in social studies 1600-SZD-GEO-GBSP

Description of the substantive content;
Remote sensing in monitoring contaminated areas by heavy metals.
The lecture presents research areas of Hungary and Spain, where were located industrial activities, which caused significant environmental contaminations. Field and airborne remote sensing measurements were used allowing to identify the contamination of plants growing on the degraded soils. Biometric methods were used as a verification of obtained results. Students will be introduced to the possibilities of implementing presented methods in other areas.
Optimization of the generalization level for effective spatial pattern recognition in thematic mapping
Recognition and preservation of the characteristic elements of visualization are one of the fundamental principles in map design, especially in cartographic generalization. Cartographic generalization assumes tailoring the map and other graphics to the map purpose, detail level as well as intended audience requirements. In thematic mapping, especially in choropleth maps, cartographic generalization takes place when either the number of classes or the enumeration unit size is decreasing. While the aspects related to the optimal data classification methods, a number of classes and diagram size has been extensively examined, the size of the enumeration unit, as well as its influence on the pattern, conveying, and recognition has not been the subject of empirical studies so far.
During the lecture, the preliminary results of the conducted empirical study will be presented. The goal of this study was to verify if choropleth maps with particular enumeration unit sizes result in the optimal perception of characteristic patterns in data and also if the users prefer choropleth maps with specific enumeration unit sizes.
Remote sensing techniques in the visualisation of the vegetation condition
The vegetation condition is important in natural areas, agricultural lands, and cities. Remote sensing techniques are data sources that allow to obtain up-to-date and repeatable information. The lecture will present methods of data selection, processing and visualization of the condition of vegetation.
Satellite data time series in environmental monitoring
Satellite imagery of the Earth Surface has been acquired since the 1960s, which allows to study recent state but also gives the opportunity to look into the past and analyze the changes have occurred in a given period. During the lecture, basic information on the functioning of satellite missions will be presented, along with the characteristics of a few selected of them. Applications of the use of time-series imagery will be discussed, based on examples related to the study of vegetation and atmosphere.
Cartographic visualization of historical data
The classes will be devoted to the methods of historical data cartographic visualizations. Digital tools which are more often used in historical geography and spatial history, enable scholars to gather, analyze, and visualize historical phenomena. During the classes, the methods and tools for digital historical cartography will be presented as well as possibilities and constraints behind them.
Diagnosis as a part of the revitalization process of urbanized areas
Diagnosing the condition of a commune as part of undertaking revitalization processes requires the use of objective and verifiable measures and research methods adapted to local conditions. The scope of the diagnosis covers all spheres of the commune's activity. The analysis requires communes to define basic fields - spatial units to which all collected information will be related. The basis for the decision on the selection of specific data and their presentation should be the assessment of the necessary detail of diagnosis, selected classification methods, and confirmation of the intensity of phenomena in various source materials, also from a practical perspective.
The use of machine learning in the identification of asbestos-cement roofs as
a challenge for local government
Presentation of the possibility of developing an innovative method for remote recognition of asbestos-cement roofs. A unique neural network architecture for identifying asbestos roofs is being developed using machine learning methods (convolutional neural networks), spatial data (orthophotomaps) and statistical data.