Research Article
Quantitative Analysis of Urban Expansion and Spatial Entropy in Lamka Town, India
Issue:
Volume 14, Issue 2, December 2026
Pages:
25-33
Received:
4 June 2026
Accepted:
13 June 2026
Published:
3 July 2026
Abstract: Urban growth and spatial dispersion are important indications of changing land use dynamics, especially in fast growing municipalities. Rapid population growth and unplanned expansion in developing towns have significantly altered land use patterns, necessitating systematic assessment for sustainable planning. This study aims to evaluate the pattern, intensity and spatial characteristics of urban expansion in Lamka town. It employs geospatial techniques and quantitative analysis to provide a reliable understanding of urban transformation and its implications for future development. This study examines the spatio-temporal dynamics of urban growth and spatial dispersion in Lamka town, Manipur, over a 30-year period (1995-2025) using remote sensing and Shannon entropy analysis. Multi-temporal Landsat datasets were classified into built-up and non-built-up categories using the supervised Maximum Likelihood method. The study found that the built-up area increased from 8.5 km2 in 1995 to 58.5 km2 by 2025, whereas non-built-up land decreased. Accuracy assessment demonstrates strong dependability, with overall accuracy above 88% and Kappa values greater than 0.85. Shannon entropy values increased from 0.10 to 0.44, indicating a shift from compact to dispersed urban growth. The entropy graph shows a constant rising trend, with the most rapid growth occurring between 2015 and 2025. This reflects intensified peri-urban expansion and spatial fragmentation. The study exposes the expanding urban sprawl and highlights the urgent need for effective planning strategies and policy interventions to ensure sustainable urban development.
Abstract: Urban growth and spatial dispersion are important indications of changing land use dynamics, especially in fast growing municipalities. Rapid population growth and unplanned expansion in developing towns have significantly altered land use patterns, necessitating systematic assessment for sustainable planning. This study aims to evaluate the patter...
Show More
Research Article
Spatiotemporal Analysis of Land Use and Land Cover Change over 25 Years Using Landsat Image in Case of Ura District (Assosa), Ethiopia
Tariku Tamiru Gemechu*
Issue:
Volume 14, Issue 2, December 2026
Pages:
34-44
Received:
17 May 2026
Accepted:
27 May 2026
Published:
11 July 2026
Abstract: Land use/ Land cover (LULC) classification plays a vital role in understanding environmental changes and for supporting sustainable land management in Ura District (Assosa town). This study aims to analyse the spatial distribution and patterns of LULC in study area using remote sensing and GIS techniques. Multispectral satellite imagery’s (Landsat 7, Landsat 8 and Landsat 9) was classified using supervised image classification method into major classes including agricultural land, forest, built-up, grassland and bare land. Accuracy assessment was performed using Confusion matrix, resulting overall accuracy (88.00%, 92.00% and 96.00%) and a Kappa Coefficient of (0.8507, 0.8355 and 0.9232) in 2001, 2013 and 2025 respectively. The result indicates that the dominant class forest cover the large portion of the study area 48.934451%, followed by Grassland (25.297372%) and agriculture (13.247733%) in 2001. Built-up, bare land and agricultural areas have increased by 12.970652%, 22.792803% and 2.390367% respectively while forest cover and grassland has decreased by 20.805041% and 17.348774 in past 25 years (2001 – 2025). The study highlights significant land use changes and their environmental implications. These findings provide valuable information for land use planning and sustainable resource management. The integration of advanced approaches such as GIS, Remote sensing and Machin learning technologies are recommended for improving future LULC analysis.
Abstract: Land use/ Land cover (LULC) classification plays a vital role in understanding environmental changes and for supporting sustainable land management in Ura District (Assosa town). This study aims to analyse the spatial distribution and patterns of LULC in study area using remote sensing and GIS techniques. Multispectral satellite imagery’s (Landsat ...
Show More
Research Article
Bayesian-Enhanced Deep Learning and Multi-Sensor Fusion for Spatiotemporal Analysis of Deforestation Frontiers and Landscape Structural Dynamics
Issue:
Volume 14, Issue 2, December 2026
Pages:
45-67
Received:
5 May 2026
Accepted:
2 July 2026
Published:
28 July 2026
DOI:
10.11648/j.ajrs.20261402.13
Downloads:
Views:
Abstract: Monitoring deforestation and forest fragmentation in tropical ecosystems remains challenging due to rapid anthropogenic pressures, understory disturbances, and the temporal limitations of conventional remote-sensing approaches dominated by annual, reflectance-based observations. This study presents an integrated spatiotemporal framework for biannual deforestation mapping in the Akure Forest Reserve (2020–2023), combining high-resolution Planet NICFI optical imagery with Sentinel-1 SAR data to enhance fine-scale temporal detection and reduce classification uncertainty. Three U-Net architectures with ResNet18, ResNet34, and ResNet50 backbones were evaluated across eight biannual datasets and benchmarked against traditional machine learning classifiers. To improve temporal coherence in SAR-derived predictions, a Bayesian updating strategy was applied. The resulting biannual maps enabled a detailed analysis of deforestation frontier dynamics through patch size distribution, patch formation speed, and spatial configuration. To characterize multiscale degradation patterns, conventional landscape metrics (Number of Patches, Patch Density, Mean Patch Size, Edge Density, Aggregation Index, and Forest Fragmentation Index) were integrated with fractal-based indicators, including Fractal Dimension and Local Connected Fractal Dimension. Results indicate that the U-Net model with a ResNet34 backbone achieved the highest classification performance (Precision = 0.9342, IoU = 0.9086), while Bayesian temporal updating further enhanced temporal stability (Precision = 0.9663, IoU = 0.9470), revealing pronounced clustering of deforestation in late 2023 (Coefficient Variation (CV) = 1.939). Fragmentation analysis reveals progressive micro-fragmentation characterized by increasing patch number and density, declining mean patch size, and persistently high local fractal connectivity, indicating intense internal forest erosion despite apparent structural stability. This structural–functional decoupling suggests that forests may remain spatially intact while undergoing substantial functional degradation. By integrating deep learning, Bayesian inference, and multiscale spatial metrics, this study provides a more sensitive and spatially explicit characterization of deforestation dynamics, offering valuable insights for geospatial analysis, conservation planning, and sustainable forest management.
Abstract: Monitoring deforestation and forest fragmentation in tropical ecosystems remains challenging due to rapid anthropogenic pressures, understory disturbances, and the temporal limitations of conventional remote-sensing approaches dominated by annual, reflectance-based observations. This study presents an integrated spatiotemporal framework for biannua...
Show More
