EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Assessing Spatiotemporal Dynamics of AI-based Land Use and Land Cover through Sentinel-2 Time-Series Imagery: A Case Study of the Shimbay District, Republic of Karakalpakstan, Uzbekistan

Ilyaskhoja Jumaniyazov, Mukhiddin Juliev, Mamanbek Reimov, Rustam Oymatov, Aziz Inamov, Begench Yunusov, Dilbar Abdramanova

Forum Geografi · 2026

DOI: 10.23917/forgeo.8724 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forum Geografi, 2026. Verfasst von Ilyaskhoja Jumaniyazov und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Land use and land cover (LULC) change is a vital indicator of environmental transformation and sustainable land management, particularly in arid and semi-arid regions such as Karakalpakstan. Although several studies have explored LULC dynamics across Central Asia, most have focused on large-scale or regional assessments, leaving a gap in district-level analyses that capture localized land transformation processes. This study addresses this gap by examining the temporal dynamics of LULC in the Shimbay district, one of the most populous districts in the northern part of the Republic of Karakalpakstan, Uzbekistan. The research aims to identify changes in LULC using Sentinel-2 satellite imagery over 6 years, from 2017 to 2022. The study area was selected based on 10 years of government “Land Fund” data, indicating significant changes in bare land. The satellite images and field measurements were analyzed using ArcGIS 10.4.1. LULC was categorized into five classes: water bodies; vegetation and agricultural land (including flooded mangroves, emergent vegetation, paddy fields, irrigated agricultural lands, cereals, grasses, and non-tree crops); built-up areas; saline land; and bare land. Following classification, 100 random sample points were generated in ArcGIS and verified using Google Earth Pro to ensure classification accuracy. The results showed that the overall accuracy of the LULC classification was 81% (Kappa coefficient= 0.74) in 2017 and 71% (Kappa coefficient= 0.66) in 2022, both considered within the “substantial” agreement range. The most significant change occurred in vegetation and agricultural lands, with 13,183.38 ha (9.4% of the study area) converted into bare land. These findings provide a detailed understanding of landscape transformation in the Shimbay district and offer policymakers and planners valuable insights to enhance sustainable land management and prevent further land degradation.

Zitieren

APA

Jumaniyazov, I., Juliev, M., Reimov, M., Oymatov, R., Inamov, A., Yunusov, B., & Abdramanova, D. (2026). Assessing Spatiotemporal Dynamics of AI-based Land Use and Land Cover through Sentinel-2 Time-Series Imagery: A Case Study of the Shimbay District, Republic of Karakalpakstan, Uzbekistan. Forum Geografi. https://doi.org/10.23917/forgeo.8724

Vancouver

Jumaniyazov I, Juliev M, Reimov M, Oymatov R, Inamov A, Yunusov B, et al. Assessing Spatiotemporal Dynamics of AI-based Land Use and Land Cover through Sentinel-2 Time-Series Imagery: A Case Study of the Shimbay District, Republic of Karakalpakstan, Uzbekistan. Forum Geografi. 2026. doi:10.23917/forgeo.8724

BibTeX
@article{Jumaniyazov2026,
  author = {Jumaniyazov, Ilyaskhoja and Juliev, Mukhiddin and Reimov, Mamanbek and Oymatov, Rustam and Inamov, Aziz and Yunusov, Begench and Abdramanova, Dilbar},
  title = {Assessing Spatiotemporal Dynamics of AI-based Land Use and Land Cover through Sentinel-2 Time-Series Imagery: A Case Study of the Shimbay District, Republic of Karakalpakstan, Uzbekistan},
  journal = {Forum Geografi},
  year = {2026},
  doi = {10.23917/forgeo.8724}
}
Kostenlos starten →