A GeoAI-based Land Use Land Cover Segmentation Process to Analyse and Predict Rural Depopulation, Agricultural Land Abandonment, and Deforestation in Bulgaria and Turkey, 1940-2040

Información del proyecto

GeoAI_LULC_Seg

Identificador del acuerdo de subvención: 101100837

DOI

10.3030/101100837

Proyecto cerrado

Fecha de la firma de la CE 22 Septiembre 2022

Fecha de inicio 1 Octubre 2022

Fecha de finalización 31 Marzo 2024

Financiado con arreglo a

• European Research Council (ERC)

Coste total

Sin datos

Aportación de la UE

€ 150 000,00

Coordinado por

KOC UNIVERSITY
Türkiye

Periodic Reporting for period 1 - GeoAI_LULC_Seg (A GeoAI-based Land Use Land Cover Segmentation Process to Analyse and Predict Rural Depopulation, Agricultural Land Abandonment, and Deforestation in Bulgaria and Turkey, 1940-2040)

Período documentado: 2022-10-01 hasta 2024-03-31

Resumen del contexto y de los objetivos generales del proyecto

This project aimed to develop geospatial artificial intelligence (GeoAI) processes to semantically segment panchromatic historical aerial and satellite imagery at an unprecedented scale for a border region shared between the Republic of Bulgaria and the Republic of Türkiye. Our goal was to create accurate land use and land cover change maps for this region and align them with high spatial resolution demographic data. This alignment would enable us to assess, quantify, and analyze major drivers of land use land cover changes such as rural depopulation, agricultural land abandonment, and deforestation over the long term. Additionally, we aimed to predict and model future population geography and land use and land cover changes.

Trabajo realizado desde el comienzo del proyecto hasta el final del período abarcado por el informe y los principales resultados hasta la fecha

Despite limited budgetary and time constraints, we successfully developed our GeoAI methodology tailored for the semantic segmentation of panchromatic historical aerial and satellite imagery. We ensured its interoperability with the current land cover taxonomy of the European Space Agency (ESA) WorldCover 2021. This key achievement enabled us to conduct long-term land cover change analyses in our chosen area.

Avances que van más allá del estado de la técnica e impacto potencial esperado (incluida la repercusión socioeconómica y las implicaciones sociales más amplias del proyecto hasta la fecha)

Our GeoAI methodology and deep learning processes have demonstrated high accuracy in computer vision. More significantly, they enabled us to analyze historical aerial and satellite imagery alongside historical demographic data from an interdisciplinary viewpoint, integrating remote sensing, population geography, and geospatial data science. A major outcome of this project is the scalability of our methodology, showcased by the semantic segmentation and public sharing of a benchmark land cover dataset for KeyHole-9 Hexagon reconnaissance satellite imagery from the 1970s and the 1980s, which provides nearly global high-resolution coverage. This Hexagon imagery was classified and made accessible online as recently as 2020 and 2022. As a result, we believe our methodology is both valuable and timely for future research.

In addition, our benchmark HexaLCSeg dataset (Hexagon-based Historical Land Cover Benchmark Dataset, https://zenodo.org/records/11005344) derived from Hexagon satellite imagery, offers significant potential for various applications. It is particularly useful for environmental and agricultural monitoring and urban planning, as it provides insights into historical land cover conditions and long-term changes such as urbanization, deforestation, and land abandonment. The historical perspective provided by the HexaLCSeg dataset makes it an essential tool for climate change research, allowing the tracking of ecological changes over decades. Furthermore, from the standpoint of geohumanities and human geography, the spatiotemporal characteristics of Hexagon imagery, including urban sprawl in Türkiye and significant rural depopulation in Bulgaria, are invaluable for analyzing and modeling the major dynamics of past and future population geography.