Flood susceptibility is projected to rise in the Kabul River Basin

What the study found: Flood susceptibility in the Kabul River Basin is projected to increase over time through 2100. The study reports that the area classified as “Very Highly” susceptible rose in the projections, while “Very Low” susceptibility declined.

Why the authors say this matters: The authors conclude that dynamic environmental and demographic changes should be integrated into flood management strategies in the Kabul River Basin. They also say the research offers a transferable outline for flood assessment in climate-sensitive mountainous regions and provides insights for land use planning and climate adaptation policy.

What the researchers tested: The researchers assessed projected flood susceptibility in the transboundary, ecologically sensitive Kabul River Basin from 2020 to 2100 under different future scenarios. They used an eXtreme Gradient Boosting (XGBoost) machine learning model with three dynamic and nine static predictors.

What worked and what didn't: The model showed strong predictive accuracy, with AUC values of 0.961–0.962, and high cross-temporal consistency across future scenarios, with correlations of 0.75–0.85. Bootstrap uncertainty analysis also supported robustness, with mean AUCs of 0.9817–0.9834, very low standard errors of 0.0003, and narrow confidence intervals of 0.9719–0.9887. In the projections, “Very Highly” susceptible areas increased from 11.78% in 2020 to 12.17% in 2040, 14.44% in 2060, 13.32% in 2080, and 13.51% by 2100, while “Very Low” susceptibility declined from 66.17% in 2020 to 56.43% by 2100.

What to keep in mind: The abstract does not describe detailed study limitations beyond noting limited understanding of future flood risk in this region before this study. The reported findings are specific to the Kabul River Basin and the scenarios and predictors used here.

Key points

• Flood susceptibility in the Kabul River Basin is projected to increase through 2100.
• The share of “Very Highly” susceptible areas rises in the projections, while “Very Low” areas decline.
• XGBoost produced strong predictive accuracy, with AUC values of 0.961–0.962.
• Bootstrap analysis reported mean AUCs of 0.9817–0.9834 and very low standard errors.
• The authors say population growth is a key driver of future flood risk.