The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Share
Publications Copernicus
Download
Citation
Share
Articles | Volume XLVIII-G-2025
https://doi.org/10.5194/isprs-archives-XLVIII-G-2025-1159-2025
https://doi.org/10.5194/isprs-archives-XLVIII-G-2025-1159-2025
31 Jul 2025
 | 31 Jul 2025

Past Expansion and Future Prediction of Land Use and Land Cover of Sofia City

Darin Pavlov, Lidia Lazarova Vitanova, and Dessislava Petrova-Antonova

Keywords: Land Use and Land Cover, Urbanization, Urban Change Prediction, Artificial Neural Network, Cellular Automata

Abstract. Rapid urbanisation impacts land use and land cover (LULC), contributing to environmental challenges such as urban heat islands (UHIs) and air pollution. This study investigates the morphological changes in Sofia’s LULC from 1990 to 2018, predicts future LULC patterns, and evaluates the effectiveness of Cellular Automata-Artificial Neural Network (CA-ANN) models for LULC forecasting. Historical LULC data from Urban Atlas (UA) and Corine Land Cover (CLC) and predictive variable data such as population density, road networks, water bodies, and elevation are used to model transition potential and simulate future land cover. The analysis revealed a slight increase in urban areas, primarily at the expense of cropland, between 1990–2018. Simulations for 2074 suggest a continued urban expansion, with a significant cropland decline. Validation of CA-ANN models showed high accuracy but limited ability to predict small-scale transitions due to low transition potential. This study highlights the importance of input data quality and temporal range in predictive accuracy. Furthermore, it provides valuable insights for urban planning, sustainable development, and climate adaptation strategies by offering a data-driven approach to forecasting LULC changes. Future research should integrate additional socio-economic factors and alternative approaches to enhance prediction reliability.

Share