Floods are one of the most severe devastating natural hazards, which cause significant environmental and socio-economic losses. Climate and land-use change may have a strong effect on flood occurrence and severity. The frequency of major floods in many places around the world seems to be increasing. Understanding the physical processes giving rise to floods of a given probability of occurrence is among the crucial areas of catchment hydrology. These processes are complex and controlled by various variables, including rainfall regime, snowmelt, catchment characteristics, and catchment state. To avoid the catastrophic impacts of floods, accurate temporal and spatial prediction is critical to developing efficient prevention and mitigation measures. Spatially analyzing floods can provide an effective way to reduce or even prevent such disasters. In general, the most common method used to simulate and predict the spatial distribution of floods is to use hydrodynamic and hydrological models. During the last decade, satellite images have been used to capture post-flood images, but that type of information is not accessible everywhere. Despite considerable research, efforts have been made to improve the numerical accuracy and computational efficiency of 2D hydrodynamic flood models.

In many cases, the existing hydrodynamic models are still computationally limited for large-scale applications, especially in urban environments where a high-resolution representation of complex topographic features is needed. Coupling hydrodynamic models with hydrological models may overcome some of the shortcomings of either type of modeling approach. However, these models require a considerable amount of data and resources. Recently, especially in regions that lack flow data records and other resources, soft computing-based approaches are being developed and tested in different climate and geomorphological conditions for flood susceptibility modeling and mapping. The proposed models are considered novel, alternative, and appropriate tools, especially for flash flood susceptibility mapping.

The main objective of this Special Issue is to explore the potential of soft computing models for modeling and assessing different types of floods and to contribute new ideas/approaches and solutions in sustainable river management to improve water management policies and practices regarding flood risk reduction. We welcome original research and review papers that bring new insights on flood modeling using different soft computing models. Special attention will be devoted to contributions that compare or combine different approaches such as hydrodynamic modeling, hydrological modeling, soft computing modeling, and satellite-based flood observation assessment approaches. Contributions focusing solely on the social and economic implications of floods are also welcomed.

Potential topics include but are not limited to the following:

• Hydro-Meteorological characterization of floods
• Relationship between hydro-meteorological patterns and their influence on floods
• Linkage of atmospheric circulation with floods
• Circulation weather types associated with floods
• The role of atmospheric processes associated with floods
• Fluvial flood susceptibility assessment
• Long-rain and short-rain floods susceptibility assessment
• Flash and coastal floods susceptibility assessment
• Rain-on-snow floods susceptibility assessment
• Snowmelt floods susceptibility assessment
• Hydrologic modeling of floods
• Hydrodynamic modeling
• Hybrid method for 2D flood modeling
• Flash flood susceptibility mapping
• Soft computing models for floods mapping
• Application machine learning algorithms in floods modeling
• Deep learning neural network for flood susceptibility mapping
• Flood risk assessment and mitigation
• Hydrologic–hydrodynamic modeling using limited data
• Flood hazard and damage analysis
• Flood exposure and social vulnerability