Floods are some of the most destructive and catastrophic disasters worldwide. Development of management plans needs a deep understanding of the likelihood and magnitude of future flood events. The purpose of this research was to estimate flash flood susceptibility in the Tafresh watershed, Iran, using five machine learning methods, i.e., alternating decision tree (ADT), functional tree (FT), kernel logistic regression (KLR), multilayer perceptron (MLP), and quadratic discriminant analysis (QDA). A geospatial database including 320 historical flood events was constructed and eight geo-environmental variables—elevation, slope, slope aspect, distance from rivers, average annual rainfall, land use, soil type, and lithology—were used as flood influencing factors. Based on a variety of performance metrics, it is revealed that the ADT method was dominant over the other methods. The FT method was ranked as the second-best method, followed by the KLR, MLP, and QDA. Given a few differences between the goodness-of-fit and prediction success of the methods, we concluded that all these five machine-learning-based models are applicable for flood susceptibility mapping in other areas to protect societies from devastating floods.

Watershed models are widely used in total maximum daily load (TMDL) studies to predict the impacts of pollutant discharges on the biochemical functioning and assimilative capacity of water bodies. The reliability of a TMDL is therefore tightly linked with the predictive capability of these models. While there has been an increasing availability and application of watershed models for TMDL studies, guidelines for model evaluation, including recommendations for an appropriate selection and implementation of calibration, validation, and uncertainty analysis strategies, remain at present limited. The ASCE Environmental and Water Resources Institute (EWRI) TMDL Analysis and Modeling Task Committee was established in part to identify existing and emerging challenges encountered by water resources professionals during any phase of a TMDL development and to produce documentation to address these challenges. This paper reviews existing approaches for model calibration, validation, and uncertainty analysis, including recommendations to establish baseline modeling practices to obtain a satisfactory watershed model.

This study presents an innovative approach for the integration of flood hazard into the site selection of detention basins. The site selection process is conducted by taking into account multiple criteria and disciplines. Hydraulic modeling results derived from stormwater management model are employed by Technique for the Order of Prioritization by Similarity to Ideal Solution (TOPSIS) to determine flood hazard score. The score generated by TOPSIS is used in a spatial multi-criteria decision-making site selection framework. Applying the framework, a suitability map is generated in which primary locations for detention basin placement are determined. The method is demonstrated through the case study of Darakeh River Catchment, which is located in northern Tehran, Iran. The presented framework can be easily utilized for site selection of other stormwater management techniques, such as low impact development and best management practices, due to its versatility.