Open Access

ARTICLE

Forecasting LULC Dynamics of Soran under Future Climate Scenarios Using Machine Learning

Abdulqadeer Rash^1,*, Yaseen T. Mustafa^2,3,4, Rahel Hamad⁵

1 Department of Petroleum Geosciences, Faculty of Science, Soran University, Soran, Erbil, 44008, Iraq
2 Department of Environmental Science, College of Science, University of Zakho, Zakho, 42002, Iraq
3 Department of Environmental Engineering, College of Engineering, Knowledge University, Erbil, 44001, Iraq
4 Applied Remote Sensing & GIS Center, University of Zakho, Zakho, 42002, Iraq
5 Faculty of Research Centre, Soran University, Soran, Erbil, 44008, Iraq

* Corresponding Author: Abdulqadeer Rash. Email:

Revue Internationale de Géomatique 2025, 34, 381-414. https://doi.org/10.32604/rig.2025.065870

Received 24 March 2025; Accepted 26 June 2025; Issue published 29 July 2025

Abstract

Changes in land use/land cover (LULC) are a substantial environmental subject with considerable consequences for human well-being, climate, and ecosystems. Innovative investigations for predicting LULC changes are essential for effective land management and sustainable development. This study used Landsat images and supplementary spatial factors to evaluate spatiotemporal LULC changes in Erbil Province, Kurdistan Region-Iraq. It predicts future changes in 2040 using four climates scenario-based Shared Socioeconomic Pathways (SSPs). The Random Forest (RF) model was used to classify and forecast LULC changes, which are crucial for effective land management and sustainable development. The RF model was assessed using performance metrics, such as the overall accuracy, F1-score, and kappa coefficient. The simulated LULC outcomes demonstrated the efficiency of the selected model, achieving an overall accuracy of 94.34%, a perfect agreement in the kappa statistic of 0.92, and a high F1-score between 0.71 and 0.93. The study revealed that agricultural land declines under SSP126 but increases under other scenarios, with SSP585 showing the highest gain (+209.98 sq. km, 23.32%). Barren land increased across all scenarios, whereas built-up areas consistently increased. Forest gains in SSP126 but declined in all other scenarios, with the most significant loss in SSP585 (−101.20 sq. km, −5.31%). The riparian zone gains in SSP126 but declines in all the other scenarios. Snow remained stable, but minor losses were observed in SSP245, SSP370, and SSP585. Water showed a slight increase in SSP126 but declined in all other scenarios. SSP126 showed minor changes, whereas SSP scenarios 370 and 585 show severe land transformations, forest loss, rangeland degradation, and urban expansion, indicating increased deforestation and degradation. This study highlights the importance of integrating a scenario-based RF model with hyperparameter tuning in remote sensing applications to improve LULC dynamics predictions, benefiting land-use planning, environmental management, and rational decision-making.

---

Keywords

---