Machine learning-based prediction of future desertification hotspots under climate and land-use change in arid Iran

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.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-14
DOI
https://doi.org/10.1038/s41598-026-79453-7
Primary Topic
Aeolian processes and effects
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine learning-based prediction of future desertification hotspots under climate and land-use change in arid Iran

Mohsen Farahi, Abdolhossein Boali
Scientific Reports
Aeolian processes and effects
article

Machine learning-based prediction of future desertification hotspots under climate and land-use change in arid Iran

Mohsen Farahi, Abdolhossein Boali
article en

Abstract

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.

Scientific Reports
University of Sistan and Baluchestan (IR), Gorgan University of Agricultural Sciences and Natural Resources (IR)
Aeolian processes and effects
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon