No abstract

In an effort to improve tools for effective flood risk assessment, we applied machine learning algorithms to predict flood-prone areas in Amol city (Iran), a site with recent floods (2017–2018). An ensemble approach was then implemented to predict hazard probabilities using the best machine learning algorithms (boosted regression tree, multivariate adaptive regression spline, generalized linear model, and generalized additive model) based on a receiver operator characteristic-area under the curve (ROC-AUC) assessment. The algorithms were all trained and tested on 92 randomly selected points, information from a flood inundation survey, and geospatial predictor variables (precipitation, land use, elevation, slope percent, curve number, distance to river, distance to channel, and depth to groundwater). The ensemble model had 0.925 and 0.892 accuracy for training and testing data, respectively. We then created a vulnerability map from data on building density, building age, population density, and socio-economic conditions and assessed risk as a product of hazard and vulnerability. The results indicated that distance to channel, land use, and runoff generation were the most important factors associated with flood hazard, while population density and building density were the most important factors determining vulnerability. Areas of highest and lowest flood risks were identified, leading to recommendations on where to implement flood risk reduction measures to guide flood governance in Amol city.

Wood‐based mulches are a preferred erosion control material for rehabilitation of degraded lands because they can be made from native wood materials; however, research is needed to verify the effectiveness of new products prior to application. The present study aims to assess the effectiveness of two types of native wood strand mulches from Iran (waste byproducts of Alnus glutinosa and Fagus orientalis working) in reducing runoff, soil loss, and sediment concentration under laboratory conditions. Toward this goal, rainfall simulations were conducted 27 times using a 50 mm hr−1 rainfall during 20‐min experiments on erosion plots with treatments of different cover percentages (bare, 30 and 70%) and strand dimensions (16 and 4 cm in length; 1.5 cm wide). The results showed that all strand applications reduced runoff (>12%), soil loss (>47%), and sediment concentration (>44%) compared to the bare plots. The most effective application treatment was a 70% coverage of the 4‐cm strands of either material (p value < .002). The shorter strands were most effective for all hydrological and erosion variables reductions because they maintained more contact with the soil surface during simulated rainfall and then increased the soil retention potential, whereas the longer strands realigned in the direction of flow, thereby limiting their ability to retard flowing water. The small strands also facilitated the creation of microdams that blocked flow and promoted infiltration. Both materials were deemed effective native erosion control products in degraded sites in the Hyrcanian forests of Iran, particularly when small strands were applied at high cover rates.