Project description
Analysing historical population geography and its effect on land use
Urbanisation has led to radical changes in population distribution and is directly linked to environmental changes such as deforestation and abandonment of farmland. Although contemporary mapping of land use and land cover (LULC) compared with dynamic population geography in Europe exists, similar correlations prior to 1970 are limited. Funded by the European Research Council, the GeoAI_LULC_Seg project aims to employ geospatial AI to accurately map LULC from 1940 onward in a border region between Bulgaria and Turkey. Early aerial photographs, satellite imagery and census data will be correlated. This will create a comprehensive view of LULC to help researchers predict future population geography and land use changes.
Objective
Rural depopulation, agricultural land abandonment, and deforestation are massive concerns for Europe and elsewhere today and our planet's future. These interlinked phenomena can be analysed using land use and land cover (LULC) maps combined with dynamics of population geography, especially regarding urban sprawl. Modern LULC and spatially disaggregated population datasets go back to the 1980s and 1970s. Although we have earlier population data, these are not geomatched to locations in LULC maps. Earlier LULC maps are either not very reliable (extracted from historical maps) or limited in their geographical coverage (based on selected aerial photos or satellite imagery). These are severe limitations to developing longer and deeper perspectives and understanding the root causes of these detrimental changes in population geography and land use practices in large territories.
GeoAI_LULC_Seg will develop an advanced, modular, and customizable geospatial artificial intelligence-based land use land cover segmentation process to accurately map LULC conditions for around 30,000 km2 in a border region between Bulgaria and Turkey, including the cities Edirne, Istanbul, and Plovdiv, from historical aerial photographs and early reconnaissance satellite images (dating back to the 1950s and the 1970s respectively) by pairing them with geotagged historical population census data.
Our methodological novelties are not limited to GeoAI-based object segmentation and super-resolution applications for panchromatic imagery for our research area. Our project will create transferable knowledge and scalable methods for global applications for the 1970s, thanks to worldwide coverage of high-spatial-resolution satellite imagery we will process. Furthermore, we will build long-term LULC maps series commensurable with current satellite data (1950-2020), allowing us to improve predictions for future population geography and LULC changes.
Fields of science
- engineering and technologymechanical engineeringvehicle engineeringaerospace engineeringsatellite technology
- natural sciencesphysical sciencesopticsmicroscopysuper resolution microscopy
- natural sciencesphysical sciencesastronomyplanetary sciencesplanets
- natural sciencesearth and related environmental sciencessoil sciencesland-based treatment
- social sciencessociologydemographycensus
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Funding Scheme
HORIZON-AG-LS - HORIZON Lump Sum GrantHost institution
34450 Istanbul
Türkiye