Answers are grounded in this paper and cite their sources.
Desertification is a major environmental hazard threatening ecosystems, natural resources, and human communities worldwide, with its impacts expected to intensify under climate and land-use change. This study aimed to predict future desertification hazard hotspots under climate and land-use change scenarios in southeastern Iran, using an integrated framework that combines the Iranian Model for Desertification Potential Assessment (IMDPA), a standardized desertification assessment framework, with remote sensing, Google Earth Engine, and machine learning techniques. Field observations and satellite-derived datasets were integrated to improve the reliability of desertification assessment and spatial prediction. Six machine learning algorithms were used and evaluated using the Area Under the Curve (AUC), Kappa coefficient, True Skill Statistic (TSS), F1-score and Deviance metrics. Future land-use changes for 2040 were simulated using a Markov chain model under the SSP2–4.5 and SSP5–8.5 climate scenarios. Among the evaluated models, Random Forest achieved the highest predictive performance (AUC = 0.94, Kappa = 0.72, TSS = 0.82, F1-score = 0.86). Spatial predictions identified Zahedan, Khash, Fanuj, Nikshahr, Chabahar, and Saravan major cities in the study area as future desertification hazard hotspots. The projections indicated an expansion of approximately 88,678 ha of desertified land by 2040, highlighting the increasing environmental risk associated with climate and land-use change. These findings provide valuable support for hazard mitigation, climate adaptation, and sustainable land management in arid regions.
No takes yet. Share an insight, caveat, or question.
Farahi et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: