Comparison of multi-criteria-analytical hierarchy process and machine learning-boosted tree models for regional flood susceptibility mapping: a case study from Slovakia

Abstract

Identification of areas susceptible to floods is an important issue which requires an increased attention due to the changing frequency and magnitude of floods, which is mainly a result of the ongoing climate change and increasing anthropic pressure on the landscape. In this study, the aim was to identify the areas susceptible to floods using and comparing two different approaches, namely the multi-criteria decision analysis-analytical hierarchy process (MCDA-AHP) and the machine learning-boosted classification (BCT) and boosted regression (BRT) tree. The study area was represented by the Topl 'a river basin, Slovakia. Altogether, seven relevant flood conditioning factors: elevation, slope, river network density, distance from river, flow accumulation, curve numbers and lithology as well as flood inventory database consisting of 107 flood locations were used. Based on the results, almost 40% of the study area is characterized by high to very high flood susceptibility using the MCDA-AHP. In case of the BCT and BRT models, the share of high and very high flood susceptibility class on the basin area is 45% and 38%, respectively. Validation of the performed flood susceptibility models confirmed generally higher accuracy of the machine learning models. The accuracy of the MCDA-AHP model was 81.33% while the accuracy of the boosted tree models was 87.70% and 91.42%, respectively, for classification and regression. The results of this study can enhance more effective preliminary flood risk assessment according to the EU Floods Directive.

GIS-Based Multi-Criteria Analytical Hierarchy Process Modelling for Urban Flood Risk Analysis and Assessment, Accra Metropolis

“…This result indicates an excellent correlation between the predicted ood risk map and the ground truth data. Similar ndings of the present study dovetail with ndings of previous studies carried by Bouamrane et al, (2020); Khosravi et al, (2016); Saha and Agrawal, (2020) and Vojtek et al, (2021).…”

Designing grazing susceptibility to land degradation index (GSLDI) in hilly areas

“…Based on the recent approach by Costacheetal. 59 , 60 and Vojtek et al 61 , we developed a new advanced GSLDI and the SRs grazing pressure using ML algorithms. The proposed modeling framework consists of: (1) land erosion inventory (manually identifying erosion and no-erosion sampling points based on aerial imagery); (2) developing geographical characteristics (17 parameters, e.g., lithological structure, altitude) for each sampling point, (3) standardizing the dataset (55 subsequent attributes e.g., classes/features), and (4) ML model training process.…”

“…Currently, management of natural environmental hazards (e.g., floods, landslides, gully can be assessed, mapped and predicted using machine learning (ML, a branch of artificial intelligence, algorithms and tools. More devoted literature using ML combined with diverse statistical methods (e.g., random forest—RF; boosted regression tree—BRT can be found in valuable scientific works focused on vulnerable territories (e.g., Himalayan regions, for example by Roy et al 55 , Chowdhuri et al 56 , 57 Pal et al 58 , Costache et al 59 , 60 and Vojtek et al 61 .…”

School Location Analysis by Integrating the Accessibility, Natural and Biological Hazards to Support Equal Access to Education

“…The weighting mechanism employed the SAW method, giving equal weights to each analysis result. Mechanism development could be used in the Analytic Hierarchy Process (AHP) method based on expert-based assessments or weights derived through a community-based method that has been empirically tested [63,64].…”