**Peer Review Journal ** DOI on demand of Author (Charges Apply) ** Fast Review and Publicaton Process ** Free E-Certificate to Each Author

Current Issues
     2026:7/2

International Journal of Multidisciplinary Research and Growth Evaluation

ISSN: (Print) | 2582-7138 (Online) | Impact Factor: 9.54 | Open Access

Modeling Landcover and Landuse Change between 2000 and 2025 in Sapele LGA Using Artificial Neural Network

Full Text (PDF)

Open Access - Free to Download

Download Full Article (PDF)

Abstract

The landscape of Sapele LGA, is currently in the throes of transformative changes propelled by an amalgamation of factors, including rapid population growth, industrialization, and the ongoing expansion of urban areas. Despite the discernible evolution taking place, a noticeable void exists in our comprehensive understanding of the intricate spatio-temporal dynamics underpinning these urban development processes within Sapele LGA. Hence this study is aimed at a Spatio-temporal analysis of landcover/landuse dynamics in Sapele LGA, using gradient direction analysis and artificial neural network with the view of providing a framework for sustainable development. The objectives are to: investigate the spatial pattern of landcover/landuse in Sapele LGA over the last 25 years (2000 – 2025) using gradient direction analysis; ascertain the trend of the landcover/landuse dynamics over the last 25 years; determine the Landuse Intensity across Sapele LGA over the last 25 years. and predict the future landcover/landuse dynamics of Sapele LGA in 2040 using artificial neural network. A multi-temporal and multi-sensor approach was adopted to analyze landcover and landuse dynamics in Sapele Local Government Area between 2000 and 2025. Satellite imagery from Landsat 5, Landsat 7 ETM+, Landsat 8 OLI, and Sentinel-2 were used alongside ground control data for classification and accuracy validation. Supervised classification was conducted using the Random Forest algorithm in QGIS, while change detection, land use intensity analysis, and directional transition trends were assessed using post-classification comparison, gradient direction analysis, and land use intensity index computations. Future landcover prediction to the year 2050 was carried out using an Artificial Neural Network (ANN) model in the MOLUSCE plugin. The results revealed a significant increase in Built-Up Area from 18.78 km² in 2000 to 82.05 km² in 2025, while Open Space and Vegetation declined substantially. The Land Use Intensity Index rose from 1.334 in 2000 to 1.722 in 2025, indicating increasing anthropogenic pressure. Gradient direction analysis showed a consistent north-northeastward orientation of landcover change, aligning with urban expansion corridors. The ANN model predicted further transformation by 2050, projecting Built-Up Area to reach 123.62 km² and Open Space to reduce to less than 1 km². The findings of this study are recommended as a decision-support framework for guiding landcover and landuse management strategies within Sapele Local Government Area. 

How to Cite This Article

Ossai EN, Nnabuife CO, Ezeh FC (2025). Modeling Landcover and Landuse Change between 2000 and 2025 in Sapele LGA Using Artificial Neural Network . International Journal of Multidisciplinary Research and Growth Evaluation (IJMRGE), 6(4), 293-305.

Share This Article: