Spatiotemporal Analysis of Land Cover Changes Using Remote Sensing and the Random Forest Algorithm in Fayoum Center (2000–2023) | ||
| The International Journal of Informatics, Media and Communication Technology | ||
| Articles in Press, Accepted Manuscript, Available Online from 31 October 2025 | ||
| Document Type: Research from theses | ||
| DOI: 10.21608/ijimct.2025.394211.1079 | ||
| Authors | ||
| Ahmed Hussein Abd El Ghany Abd El wahed Hussein Abd El wahed* ; Sayed Ramadan Sayed Abd El Aal | ||
| Department of Geography, Faculty of Arts, Beni Suef University | ||
| Abstract | ||
| This study aims to analyze the spatiotemporal changes in land cover patterns in the Fayoum District, Egypt, during the period from 2000 to 2023. The analysis utilizes remote sensing techniques and Geographic Information Systems (GIS), relying on the Google Earth Engine platform and the Random Forest algorithm as a supervised machine learning classifier. Satellite imagery from the Landsat series (TM, ETM+, OLI) was used to classify five main land cover categories: old agricultural lands, reclaimed agricultural lands, urban areas, barren lands, and water bodies. Classification was conducted for five-time intervals (2000, 2005, 2010, 2015, 2020, and 2023). The accuracy of the classification was evaluated using the confusion matrix, overall accuracy, and the Kappa coefficient, which ranged from 86% to 91%. The results reveal significant changes in land cover, including rapid urban expansion at the expense of traditional agricultural land, increasing reclaimed areas due to desert reclamation projects, a gradual decline in water bodies, and a reduction in barren lands due to conversion to other land uses. The study also highlights the influence of political and social events—particularly the 2011 revolution—on land use dynamics. The research recommends activating continuous monitoring systems for land cover changes, supporting sustainable reclamation policies, balancing urban development with the conservation of agricultural resources, and promoting the application of artificial intelligence techniques in future geographic studies. | ||
| Keywords | ||
| Land cover; Remote Sensing; Random Forest; Google Earth Engine; Spatiotemporal Change | ||
|
Statistics Article View: 4 |
||
