Monitoring and Prediction of Land Use and Land Cover Using Remote Sensing and CA-ANN

ORCID

Ong'ondo: https://orcid.org/0000-0002-3550-2110; Malaki: https://orcid.org/0000-0001-6975-5901

MSU Affiliation

College of Arts and Sciences; Department of Geosciences

Creation Date

2026-06-01

Abstract

Human-driven land cover change poses a significant challenge to the sustainability of protected areas worldwide. Monitoring these dynamics and projecting future trends is crucial for effective conservation strategies. This study uses Nairobi National Park and its surrounding areas in Kenya as a case study to assess land cover change from 2016 to 2023 and project trends through 2040. We applied Geographic Information Systems (GIS) and remote sensing techniques, using Landsat imagery classified with the Random Forest (RF) algorithm in Google Earth Engine (GEE), to map land cover across eight classes. We projected future changes using a cellular automata–artificial neural network model, achieving 84.4% accuracy. Results revealed significant increases in built-up areas and agricultural land, accompanied by declines in forest, shrubland, woodland, water bodies, and bare soil. Projections indicate continued urban expansion and woodland growth, while agricultural land, bare soil, water bodies, and forests will decrease sharply. These findings highlight the urgent need for integrated land use planning and proactive conservation policies to manage rapid urban growth while preserving the ecological functions of protected areas and their surrounding landscapes.

Publication Date

7-24-2025

Publication Title

Rangeland Ecology and Management

Publisher

Elsevier

First Page

160

Last Page

171

Rights

© 2025 The Society for Range Management

Link to Full Text

Share

COinS
 

Digital Object Identifier (DOI)

https://doi.org/10.1016/j.rama.2025.06.015