Floods in urban environments often result in loss of life and destruction of property, with many negative socio-economic effects. However, the application of most flood prediction models still remains challenging due to data scarcity. This creates a need to develop novel hybridized models based on historical urban flood events, using, e.g., metaheuristic optimization algorithms and wavelet analysis. The hybridized models examined in this study (Wavelet-SVR-Bat and Wavelet-SVR-GWO), designed as intelligent systems, consist of a support vector regression (SVR), integrated with a combination of wavelet transform and metaheuristic optimization algorithms, including the grey wolf optimizer (GWO), and the bat optimizer (Bat). The efficiency of the novel hybridized and standalone SVR models for spatial modeling of urban flood inundation was evaluated using different cutoff-dependent and cutoff-independent evaluation criteria, including area under the receiver operating characteristic curve (AUC), Accuracy (A), Matthews Correlation Coefficient (MCC), Misclassification Rate (MR), and F-score. The results demonstrated that both hybridized models had very high performance (Wavelet-SVR-GWO: AUC = 0.981, A = 0.92, MCC = 0.86, MR = 0.07; Wavelet-SVR-Bat: AUC = 0.972, A = 0.88, MCC = 0.76, MR = 0.11) compared with the standalone SVR (AUC = 0.917, A = 0.85, MCC = 0.7, MR = 0.15). Therefore, these hybridized models are a promising, cost-effective method for spatial modeling of urban flood susceptibility and for providing in-depth insights to guide flood preparedness and emergency response services.

Floods are the most common natural disaster globally and lead to severe damage, especially in urban environments. This study evaluated the efficiency of a self-organizing map neural network (SOMN) algorithm for urban flood hazard mapping in the case of Amol city, Iran. First, a flood inventory database was prepared using field survey data covering 118 flooded points. A 70:30 data ratio was applied for training and validation purposes. Six factors (elevation, slope percent, distance from river, distance from channel, curve number, and precipitation) were selected as predictor variables. After building the model, the odds ratio skill score (ORSS), efficiency (E), true skill statistic (TSS), and the area under the receiver operating characteristic curve (AUC-ROC) were used as evaluation metrics to scrutinize the goodness-of-fit and predictive performance of the model. The results indicated that the SOMN model performed excellently in modeling flood hazard in both the training (AUC = 0.946, E = 0.849, TSS = 0.716, ORSS = 0.954) and validation (AUC = 0.924, E = 0.857, TSS = 0.714, ORSS = 0.945) steps. The model identified around 23% of the Amol city area as being in high or very high flood risk classes that need to be carefully managed. Overall, the results demonstrate that the SOMN model can be used for flood hazard mapping in urban environments and can provide valuable insights about flood risk management.

Water erosion is a major threat to biodiversity, according to the European Commission’s Soil Thematic Strategy, as it negatively affects soil structure, soil fertility and water availability for plants. The island of Crete (Southern Greece) has been characterized as a biodiversity hotspot including several Natura 2000 (N2K)-protected areas. The aim of this study was to model the soil loss rate in Crete regarding species richness, habitat types and their conservation status, as well as the MAES (Mapping and Assessment of Ecosystem and their Services) ecosystem types. To this end, the RUSLE soil erosion prediction model was implemented, using freely available geospatial data and cloud-computing processes. The estimated average soil loss in the study area was 6.15 t ha⁻¹ y⁻¹, while there was no significant difference between the terrestrial N2K (6.06 t ha⁻¹ y⁻¹) and non-N2K (6.19 t ha⁻¹ y⁻¹) areas. Notably, the natural habitats of principal importance for the conservation of biodiversity (referred to as “priority” areas), according to Annex I to Directive 92/43/EEC, are threatened by soil erosion with an estimated mean annual soil loss equal to 8.58 t ha⁻¹ y⁻¹. It is also notable that grasslands, heathland and shrubs and sparsely vegetated areas experienced the highest erosion rates among the identified MAES ecosystem types. The results showed that soil erosion is a serious threat to biodiversity in N2K-protected areas. Therefore, there is a need for systematic spatiotemporal monitoring and the implementation of erosion mitigation measures.

This paper examines the impacts of three different potential evapotranspiration (PET) models on drought severity and frequencies indicated by the standardized precipitation index (SPEI). The standardized precipitation-evapotranspiration index is a recent approach to operational monitoring and analysis of drought severity. The standardized precipitation-evapotranspiration index combines precipitation and temperature data, quantifying the severity of a drought as the difference in a timestep as the difference between precipitation and PET. The standardized precipitation-evapotranspiration index thus represents the hydrological processes that drive drought events more realistically than the standardized precipitation index at the expense of additional computational complexity and increased data demands. The additional computational complexity is principally due to the need to estimate PET within each time step. The standardized precipitation-evapotranspiration index was originally defined using the Thornthwaite PET model. However, numerous researchers have demonstrated the standardized precipitation-evapotranspiration index is sensitive to the PET model adopted. PET models requiring sparse meteorological inputs, such as the Thornthwaite model, have particular utility for drought monitoring in data scarce environments. The aridity index (AI) investigates the spatiotemporal changes in the hydroclimatic system. It is defined as the ratio between potential evapotranspiration and precipitation. It is used to characterize wet (humid) and dry (arid) regions. In this study, a sensitivity analysis for the standardized precipitation-evapotranspiration and aridity indexes was carried out using three different PET models; namely, the Penman–Monteith model, a temperature-based parametric model and the Thornthwaite model. The analysis was undertaken in six gauge stations in California region where long-term drought events have occurred. Having used the Penman–Monteith model as the PET model for estimating the standardized precipitation-evapotranspiration index, our findings highlight the presence of uncertainty in defining the severity of drought, especially for large timescales (12 months to 48 months), and that the PET parametric model is a preferable model to the Thornthwaite model for both the standardized precipitation-evapotranspiration index and the aridity indexes. The latter outcome is worth further consideration for when climatic studies are under development in data scarce areas where full required meteorological variables for Penman–Monteith assessment are not available.