Multilevel flood susceptibility mapping by fuzzy sets, analytical hierarchy process, weighted linear combination and random forest

This study investigates multilevel flood susceptibility mapping at the national scale in North Macedonia, utilizing 328 historical flood events, 14 conditioning factors derived from a digital elevation model, simplified lithology, and computed direct runoff. The methodology integrates fuzzy set theory (Fuzzy), analytic hierarchy process (AHP), weighted linear combination (WLC), and random forest (RF) approaches. The two-stage process employs distinct sets of conditioning factors in sequential flood susceptibility mapping: first, generating Fuzzy/AHP/WLC predictions and pseudo-absence data, and second, producing five RF predictions by varying pseudo-absences and binary cutoffs. Validation results indicate that the very high susceptibility class (0.8–1.0) of the Fuzzy/AHP/WLC model predicted 46.6% of flood pixels within 31.6% of the total area. In comparison, the very high susceptibility class of the RF models predicted 88.5%, 78.3%, 60.6%, 48.5%, and 28.3% of flood pixels within 54.7%, 42.2%, 30.5%, 27.0%, and 25.1% of the total area, respectively. The RF models achieved area under the curve (AUC) values exceeding 0.850, with a maximum of 0.966. Furthermore, a standard deviation map derived from the RF models identified regions of high and low uncertainty, highlighting areas for potential methodological improvement and targeted sampling. The results also show the promise of the multilevel approach for mapping flood susceptibility and call for more research into its potential for future studies and real-world applications.