Search

Although fractal mathematics has been commonly used to quantify particle size distribution (PSD), limited attention has been paid to the fractal dimension of the infiltration curve (DI). Therefore, it is necessary to determine whether the DI and fractal dimensions of PSD (Dm, Dclay, Dsilt and Dsand) can reflect the infiltration process, and soil erodibility and degradation. Accordingly, this study aimed to provide new information on the quantification of infiltration processes, and soil erodibility and degradation, using DI and Dm in the Soorak basin in the northern part of Iran. The soil and infiltration properties were calculated by field and laboratory practices on 46 topsoil samples and 34 infiltrometer double‐ring tests. Correlation, regression and redundancy analysis (RDA) were used to identify relationships between the infiltration curve and PSD coordinates with soil and infiltration properties. Results indicated that the DI was significantly linearly correlated with other infiltration curve characteristics, with the correlation coefficient ranging from −0.737 to −0.403 (sig. = 0.000–0.037). However, there was no significant correlation between DI and Dm, Dclay, Dsilt and Dsand. Different erodibility factors, especially KUSLE, had significant relations with Dm, Dclay, Dsilt, Dsand and DI (p <.01), suggesting that these fractal dimensions are indicators of soil degradation. Other findings indicated that the land use had no significant effect on DI and infiltration properties, whereas KUSLE, Dm, Dclay, DSilt and DSand were significantly affected by land‐use patterns (p <.01). These findings demonstrate that fractal dimensions of PSD and infiltration can be practicable indices to analyse soil degradation under different land‐use types. Highlights: How fractal geometry adds to understanding of the infiltration process and soil degradation.Fractal dimensions of infiltration (DI) can describe the infiltration process.Fractal dimensions of soil (Dm) and DI can be used as indicators of the soil erodibility.Erodibility and fractal properties of soil were significantly affected by land use. [ABSTRACT FROM AUTHOR]

Snow avalanches cause economic losses in many parts of the world, especially in mountainous areas. Due to its changing climates and the complex topography of mountainous regions in Iran, avalanches are significant problems. Therefore, modeling snow avalanches to predict them is essential for sustainable and safe development, appropriate infrastructure, planning for residential development, and loss prevention. This study assesses the performances of multi-criteria decision-making models and machine-learning hybrid models for snow avalanche susceptibility mapping in northwestern Iran's Sirvan watershed based on the weight of analytic network process, weighted linear combination, and frequency ratio. Using multicollinearity analysis and Pearson correlation, eleven snow avalanche conditioning factors were deemed appropriate for use. The areas under the curve (AUC), root mean square error (RMSE), seed cell area index, and snow avalanche relative index were used to validate snow avalanche susceptibility maps. The results showed that all hybrid models performed very well for the determination of the susceptibility of locations to avalanching. Based on the results of the validation analyses, the analytic network process-frequency ratio hybrid model was best among the models (AUC = 0.941, RMSE = 0.3). The resulting maps provide strong evidence to guide efforts to prevent the exposure to snow avalanches in the Sirvan watershed, and these hybrid models can be tested in other regions affected by snow avalanches. • Variables importance of topographic, meteorological and earth by the MCDA technique. • Snow avalanche susceptibility mapping (SASM) using ANP-WLC, ANP-FR, FR-CTA and FR-SOM novel ensemble algorithms. • Models were validated based on ROC, MSE, RMSE, SCAI and SARI methods. • The results showed that the ANP-FR hybrid model has better predictive performance • Nearly 7% of the study area has high susceptibility to snow avalanche. [ABSTRACT FROM AUTHOR]

Snow Water Equivalent (SWE) is one of the most critical variables in mountainous watersheds and needs to be considered in water resources management plans. As direct measurement of SWE is difficult and empirical equations are highly uncertain, the present study aimed to obtain accurate predictions of SWE using machine learning methods. Five standalone algorithms of tree-based [M5P and random tree (RT)], rule-based [M5Rules (M5R)] and lazy-based learner (IBK and Kstar) and five novel hybrid bagging-based algorithms (BA) with standalone models (i.e., BA-M5P, BA-RT, BA-IBK, BA-Kstar and BA-M5R) were developed. A total of 2550 snow measurements were collected from 62 snow and rain-gauge stations located in 13 mountainous provinces in Iran. Data including ice beneath the snow (IBS), fresh snow depth (FSD), length of snow sample (LSS), snow density (SDN), snow depth (SD) and time of falling (TS) were measured. Based on the Pearson correlation between inputs (IBS, FSD, LSS, SDN, SD and TS) and output (SWE), six different input combinations were constructed. The dataset was separated into two groups (70% and 30% of the data) by a cross-validation technique for model construction (training dataset) and model evaluation (testing dataset), respectively. Different visual and quantitative metrics (e.g., Nash–Sutcliffe efficiency (NSE)) were used for evaluating model accuracy. It was found that SD had the highest correlation with SWE in Iran (r = 0.73). In general, the bootstrap aggregation (i.e., bagging) hybrid machine learning methods (BA-M5P, BA-RT, BA-IBK, BA-Kstar and BA-M5R) increased prediction accuracy when compared to each standalone method. While BA-M5R had the highest prediction accuracy (NSE = 0.83) (considering all six input variables), BA-IBK could predict SWE with high accuracy (NSE = 0.71) using only two input variables (SD and LSS). Our findings demonstrate that SWE can be accurately predicted through a variety of machine learning methods using easily measurable variables and may be useful for applications in other mountainous regions across the globe. [ABSTRACT FROM AUTHOR]

Determining areas of high groundwater potential is important for exploitation, management, and protection of water resources. This study assesses the spatial distribution of groundwater potential in the Zarrinehroud watershed of Kurdistan Province, Iran using combinations of five statistical and machine learning algorithms – frequency ratio (FR), radial basis function (RBF), index of entropy (IOE), evidential belief function (EBF) and fuzzy art map (FAM). To accomplish this, 1448 well locations in the study area were randomly divided into two data sets for training (70%= 1013 locations) and validation (30%= 435 locations) based on the holdout method. Fourteen factors that can affect the presence or absence of groundwater were identified, measured, and mapped using ArcGIS and SAGA-GIS software. The models were used to predict the locations of groundwater based on suitable combinations of the conditioning factors to produce groundwater potential maps. The probability of groundwater at any location was classified as low, moderate, high, or very high based on natural breaks in the data spectrum. The model predictions were tested for validity and their success was determined using receiver operating characteristic (ROC) curves, standard errors (SE), positive predictive value (PPV), negative predictive value (NPV), sensitivity (SST), specificity (SPF) and accuracy (ACC), and the Friedman test. The performance assessments of groundwater potential predictions using the area under the curve (AUC) and accuracy (ACC) showed that the FR-RBF model had very good performance (AUC= 0.889, ACC= 87.51). FR-FAM (AUC= 0.869, ACC= 84.67), EBF-FAM (AUC= 0.864, ACC= 84.42), EBF-RBF (AUC= 0.854, ACC= 83.94), FR-IOE (AUC= 0.836, ACC= 83.62), and EBF-IOE (AUC= 0.833, ACC= 80.42) also had acceptable performance. The results of the Friedman test also show that there are significant differences between the models and the highest mean rank was generated by the FR-FAM model (3.642). Therefore, the hybrid models can be used to increase the accuracy of groundwater-prediction models in the study region and perhaps in similar settings. The groundwater potential was studied in the area of Zarrinehroud watershed A combination of methods including FR, RBF, IOE, EBF and FAM Very high and high groundwater potential areas were located in the northern half The development of hybrid models can increase the accuracy of the results [ABSTRACT FROM AUTHOR]

• Runoff and sediment production in rock fragment plots was lower than straw plots. • Runoff and sediment production decreased with the increase of soil coverage. • As the coverage ratio increased flow velocity decreased and roughness increased. Soil loss is a major global challenge threatening the future of soil and water resources. The significant implications of soil loss necessitate the adoption of appropriate soil conservation practices and soil management solutions according to the regional climate. Investigation of the effects of soil cover on soil erosion process can provide the information necessary for the success of soil and water conservation practices. In this study, the effect of rock fragment and wheat straw covers on the hydraulic properties, runoff, and sediment yield were investigated in plot scale laboratory experiments using artificial rainfall. Experiments were carried out on the plots prepared based on two types of soil cover (rock fragment, wheat straw) and three coverage ratios (35%, 65%, and 90%) in addition to a control (bare soil) plot, each with three replications. In these experiments, 2 m long, 0.55 m wide, and 0.30 m deep plots with a 15% slope were subjected to artificial rainfall with a duration of 70 min and an intensity of 90 mm h−1. The results showed a significant difference at the 5% level between the mean runoff rate of rock fragment cover (0.38 mm min−1) and that of wheat straw cover (0.42 mm min−1), but no such difference was found in terms of sediment production (Sig. = 0.73). The Wheat straw cover was more effective than rock fragment cover in increasing the Manning roughness (n) and Darcy-Weisbach friction (F) coefficients, and flow depth (h) and reducing the velocity (V), Reynolds (Re) and Froude (Fr) numbers. It was also found that, for both covers, increasing the coverage ratio increased the h , F , and n and decreased the runoff and sediment production, V , Re , and Fr. After investigating the relationship between hydraulic properties and sediment concentration in different plots, a direct linear regression relationship with a relatively high coefficient of determination (R2 > 0.614) and a significant relationship at the 1% level (P < 0.01) were found between sediment concentration and discharge per unit width (q), V , h , and Re. In general, it can be concluded that rock fragment cover and wheat straw cover both have a satisfactory effect on the hydraulic properties and runoff and sediment production. [ABSTRACT FROM AUTHOR]

Floods are a common natural disaster that can endanger urban and rural infrastructure. The purpose of this study was to prepare and analyze the flood risk map of Khancheh and Baronagh villages along a part of Suk Cham river. First, the topographic map was created using Google Earth and Global mapper. Then, using a topographic map made in AutoCAD Civil 3D software, the surface was created for the study interval. In the next step, using the constructed surface of cross sections, longitudinal profiles, river channel, right, and left flood banks of Suk Cham river were constructed in AutoCAD Civil 3D software environment. To simulate floods at return periods of 25, 50, 100, and 200 years, the cross sections were transferred to HEC RAS software. The Phil-Steiner method was used to convert the maximum daily flow rate to the maximum instantaneous flow rate according to the P-value of the Kolmogorov-Smirnov test (0.9). The results of flood frequency analysis showed that Pearson type 3 log distribution is the most suitable distribution. Based on the results, the flooding level for the return periods of 25, 50, 100, 200 years was 0.77, 0.9, 1.15, 1.47 km2, respectively. According to the flood risk map in the 100-year return period (high risk area), about 41.5% and 4.5% of the two villages of Khancheh and Baronagh had at moderate to very high risk of flood, respectively. Establishing coastal walls and organizing the river along the river route through these two villages is essential, which can mitigate the risks of floods. The use of prepared plans for flood control measures, flood forecasting and warning systems, flood insurance and in general for structural and non-structural flood control measures in the region is recommended. [ABSTRACT FROM AUTHOR]

Over the years, a number of prediction methods have been proposed for the evaluation of probability of hydrological–meteorological variables or drought indices. In this study, the precipitation data recorded in four stations of northwestern Iran over the period 1960–2014 were used to develop the time-series and genetic programming (GP) models. Comparison of the observed and predicted data showed that although both models have acceptable accuracy in predicting precipitation, the time-series models had lower errors than the GP models. So, the autoregressive and periodic autoregressive moving average models were chosen as the superior models for annual and monthly series, respectively. Therefore, the Standard Precipitation Index (SPI) and Z-Score Index (ZSI) were used to assess the drought conditions. According to the results, the SPI recognised a higher percentage of historical and prediction periods as drought conditions than ZSI. The validation of indices showed that the ZSI was more capable for detecting the drought and wetness conditions. The trend analysis of SPI and ZSI showed significant decreasing trends in different stations at all-time scales, except yearly in Urmia and all-time scales in Zanjan, which statically had no significant trend. In conclusion, given the current precipitation trends, the droughts are increasing in both severity and numbers. [ABSTRACT FROM AUTHOR]

Land subsidence (LS), which mainly results from poor watershed management, is a complex and nonlinear phenomenon. In the present study, LS at a country-wide assessment of Iran was mapped by using several geo-environmental conditioning factors (namely, altitude, slope degree and aspect, plan and profile curvature, distance from a river, road or fault, rainfall, geology and land use) into a machine learning algorithm-based artificial neural network (ANN), and a powerful group method of data handling (GMDH). The total dataset includes historical LS and non-LS locations, identified by the interferometric synthetic aperture radar (InSAR). The whole dataset was divided into two subsets at a ratio of 70:30 for training and validating the model, respectively. ANNand GMDH-based LS maps were evaluated using receiver-operator characteristic (ROC) curves. The information gain ratio (IGR) was calculated to determine the relative importance of the conditioning factors. The results showed that all of the considered factors contributed significantly to the LS mapping in Iran, with geology having the strongest impact. According to the ROC curve analysis, both ANN and GMDH-based LS maps were accurate, but the map obtained by the GMDH approach had a higher accuracy than that of ANN. Southwestern, northeastern and some parts of the central region of Iran were shown to be susceptible to LS in the future. According to the GMDH susceptibility map, 10% of Iran exhibits high or very high susceptibility to LS in the future. The provinces of Hamedan and Khouzestan had the highest percentage of areas at risk of LS. According to the InSAR deformation map, 39%, 20%, 25%, 13% and 3% of the investigated areas are subject to a yearly LS of -1 to -2.5, -2.5 to -5, -5 to -7.5, -7.5 to -10 and -10 to -20 cm, respectively. The province of Razavi Khorasan in the northeast of Iran had the largest area (about 3500 km² ) vulnerable to LS occurrence. Based on the LS susceptibility map, the provinces of Ardebil, Kurdistan, West and East Azerbaijan, Sistan and Baluchistan and Kermanshah, although not currently undergoing a high rate of LS, will be at high risk of severe LS in the future. [ABSTRACT FROM AUTHOR]

We used a novel hybrid functional machine learning algorithm to predict the spatial distribution of landslides in the Sarkhoon watershed, Iran. We developed a new ensemble model which is a combination of a functional algorithm, stochastic gradient descent (SGD) and an AdaBoost (AB) Meta classifier namely ABSGD model to predict the landslides. The model incorporates 20 landslide conditioning factors, which we ranked using the least-square support vector machine (LSSVM) technique. For the modeling, we considered 98 landslide locations, of which 70% (79) were used for training and 30% (19) for validation processes. Model validation was performed using sensitivity, specificity, accuracy, the root mean square error (RMSE) and the area under the receiver operatic characteristic (AUC) curve. We also used soft computing benchmark models, including SGD, logistic regression (LR), logistic model tree (LMT) and functional tree (FT) algorithms for model validation and comparison. The selected conditioning factors were significant in landslide occurrence but distance to road was found to be the most important factor. The ABSGD model (AUC= 0.860) outperformed the LR (0.797), SGD (0.776), LMT (0.740) and FT (0.734) models. Our results confirm that the combined use of a functional algorithm and a Meta classifier prevents over-fitting, reduces noise and enhances the power prediction of the individual SGD algorithm for the spatial prediction of landslides. [ABSTRACT FROM AUTHOR]

Mapping flood-prone areas is a key activity in flood disaster management. In this paper, we propose a new flood susceptibility mapping technique. We employ new ensemble models based on bagging as a meta-classifier and K-Nearest Neighbor (KNN) coarse, cosine, cubic, and weighted base classifiers to spatially forecast flooding in the Haraz watershed in northern Iran. We identified flood-prone areas using data from Sentinel-1 sensor. We then selected 10 conditioning factors to spatially predict floods and assess their predictive power using the Relief Attribute Evaluation (RFAE) method. Model validation was performed using two statistical error indices and the area under the curve (AUC). Our results show that the Bagging–Cubic–KNN ensemble model outperformed other ensemble models. It decreased the overfitting and variance problems in the training dataset and enhanced the prediction accuracy of the Cubic–KNN model (AUC=0.660). We therefore recommend that the Bagging–Cubic–KNN model be more widely applied for the sustainable management of flood-prone areas. [ABSTRACT FROM AUTHOR]