EUVIMEDEUVIMED entdecken
Crossref

Cellular Automata–Based Modeling and Prediction of Land Use/Land Cover Change using MOLUSCE in QGIS

Eswar Sala, Durga Prasanna M., Ramana K.V., Sri Satya G., Sridhar P.

Disaster Advances · 30.06.2026 · 103

DOI: 10.25303/198da1030113 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Disaster Advances, online erschienen am 30.06.2026. Verfasst von Eswar Sala und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid and unplanned urbanization has significantly altered land use and land cover (LULC) patterns, resulting in the loss of natural landscapes, depletion of surface water resources and degradation of ecosystem services. Understanding these changes is essential for sustainable urban planning and environmental management. This study investigates spatio-temporal LULC dynamics and predicts future land use patterns using multi-temporal Landsat satellite imagery for the years 2000, 2010 and 2020, integrated with a Cellular Automata (CA)–based modelling framework implemented through the MOLUSCE plugin in QGIS. Five major LULC classes, water bodies, vegetation, settlements, forest and open land, were classified using supervised classification techniques. The results show that settlement areas increased substantially from 634.79 km² in 2000 to 1018.25 km² in 2020, indicating rapid urban expansion. Vegetation cover also increased from 155.42 km² to 261.45 km², mainly due to agricultural expansion and greening initiatives. In contrast, forest cover declined from 949.56 km² to 708.28 km² while open land decreased from 1743.24 km² to 1507.15 km², reflecting large-scale land conversion. Water bodies showed a reduction from 39.85 km² to 27.54 km², highlighting growing stress on surface water resources. Future LULC prediction using an ANN-based CA model revealed further expansion of settlements to 1221.85 km² and vegetation to 365.85 km² by 2020, while forest and open land are expected to decline to 560.56 km² and 1344.55 km² respectively. Model validation using regression analysis demonstrated strong agreement between simulated and predicted areas (R² = 0.83). The integration of remote sensing, GIS and CA-based modelling provides a robust framework for analyzing urban growth and supporting sustainable land use planning.

Zitieren

APA

Sala, E., M., D. P., K.V., R., G., S. S., & P., S. (2026). Cellular Automata–Based Modeling and Prediction of Land Use/Land Cover Change using MOLUSCE in QGIS. Disaster Advances, 103. https://doi.org/10.25303/198da1030113

Vancouver

Sala E, M. DP, K.V. R, G. SS, P. S. Cellular Automata–Based Modeling and Prediction of Land Use/Land Cover Change using MOLUSCE in QGIS. Disaster Advances. 2026:103. doi:10.25303/198da1030113

BibTeX
@article{Sala2026,
  author = {Sala, Eswar and M., Durga Prasanna and K.V., Ramana and G., Sri Satya and P., Sridhar},
  title = {Cellular Automata–Based Modeling and Prediction of Land Use/Land Cover Change using MOLUSCE in QGIS},
  journal = {Disaster Advances},
  year = {2026},
  pages = {103},
  doi = {10.25303/198da1030113}
}
Kostenlos starten →