saeid janizadeh

Flood is one of the most devastating natural disasters that annually causes financial and life losses. Therefore, developing a susceptibility map for flood management and reducing its harmful effects is essential. The present study was conducted to prepare a flood susceptibility map using data mining models including Random Forest (RF) and Gradient Boosting Machine (GBM). At first, 275 flooding locations flood and 275 non-flood locations were identified in the Komijan watershed of Markazi province. Spatial locations were randomly divided to 70% (190 location) and 30% (82 location) for modeling and validation, respectively. Then, 12 factors affecting the occurrence of flood including slope, aspect, altitude, rainfall, land use, distance from river, drainage density, plan curvature, profile curvature, lithology, soil and stream power index were determined. The ROC curve was used to evaluate the models used. The results showed that in the validation stage, the under curve for RF and GBM models was 0.83 and 0.75%, respectively, which indicates that the RF model is more accurate in producing a flood susceptibility map. The most important factors affecting the flood are rainfall, distance from river and altitude.

Soil erosion is a problem for agriculture in arid and semi-arid regions and is of great importance due to its long-term effects on soil fertility and sustainable agriculture. Among the types of water erosion, gully erosion is one of the most important events in soil erosion and land reclamation. Given that the Markazi province is located in a region with arid and semi-arid climate, the intensity of rainfall is high in some months of the year. Also because of the abandoned agricultural land in the study area, there is much vegetation exposed to severe erosion which is conducive to erosion such as gutter erosion, so serious attention is needed for this area. The data mining method extracts useful information from a large volume of data and has shown good performance based on the literature review. Therefore, the aim of the present study was to prioritize environmental factors affecting the occurrence of gully erosion with data mining and statistical methods.

In order to conduct the present study and to map the distribution of gully erosion zones in the Robat Turk watershed, 242 gully data were identified in the study area and used. A total of 242 points were identified as non-flooded areas. In order to model the data, it was divided into two categories of training and validation, with 70% of data used as training and 30% of data used as validation. Based on the research background, hydrological, geological and physiographic factors including elevation, slope, aspect, curvature, slope shape, distance from river, distance from road, lithology, land use, annual precipitation and NDVI, variables were selected for modeling. In order to model the gully erosion, artificial neural network (ANN) and generalize linear model (GLM) models were used, and the ROC and Kappa, TSS coefficient were used to determine the accuracy of the gully erosion susceptibility map.

The results of gully erosion susceptibility showed that the central areas of the watershed are highly sensitive to erosion. Considering that most of the lands in the central part of the watershed are bare land and agricultural, the study of the gully erosion susceptibility map showed that the most sensitive and highly sensitive erosion susceptibility area was formed in the bare land. In relation to the influence of different elevation and slope classes in the study area on susceptibility to erosion, it should be stated that altitude class of 1800-2000 meters and slope class of 0-12% had the highest contribution to erosion susceptibility in the study area. This may be due to the higher soil compactness of these classes than other classes, which increases the likelihood of water infiltration into the soil and the possibility of material dissolution and piping. Validation results showed that GLM and ANN with ROC of 0.89 and 0.88 have very good performance regarding gully erosion susceptibility in the study area.

Gully erosion is one of the erosion processes that widely affects the appearance of the earth. In this study, GLM and ANN were used to evaluate the impact of environmental variables on gully erosion as well as to identify potential areas for gully erosion. For this purpose, 12 variables and 242 gully erosion points were used. ROC, TSS and KAPPA statistics were used to evaluate the models. The results of evaluation and validation of the models used showed that both models have good performance in zoning susceptibility to gully erosion. Identification and prediction of gully erosion susceptible areas can reduce the damaging effects of this type of erosion and prevent its further development and can be of considerable help to the people of the study area. Given that most of the gutters were created in the central part of the study area near the village of Robat Turk, protective measures should be increased in these areas to prevent the spread of agriculture and residential areas to erosive areas.

The ecological, economic, and social potential of an area for large and large uses is influenced by the quantity and quality of the waters. Therefore, appropriate methods of surface water and groundwater have been investigated qualitatively and quantitatively in order to use its results in assessing the power of the land. One of the important factors for sustainable development is the availability water resources for different uses, which imposed its quality is very important. Nowadays, groundwater resource management plays the main role in arid and semiarid regions. Investigations on the spatial variations of Water Quality Index (WQI) are very important to determine the best management program. Geo-statistical methods and ArcGIS software can be useful for this purpose. The aim of this study is WQI zoning for various uses (drinking, agriculture and industry) in the Silveh watershed (West Azerbaijan province).

In this research, water quality zoning based on WQI method for different drinking uses (pH, TDS, HCO3, Cl, Ca, Mg, K, Na and SO4), agriculture (EC, SSP and Cl) and industry (pH, TDS, Cl, TH and SO4) were sampled from 145 points (springs) from the basin level representing the studied area, which was carried out in July 2012. Then, to measure the parameters, the samples were transferred to the laboratory of the Faculty of Natural Resources of Tehran University and tested and the parameters were measured. In this research, we try to compare different methods of interpolation and select the best method to base the groundwater quality zonation map using the WQI index. Initially, the WQI index was calculated for all sampling points. After calculating the water quality index, the zoning water quality in the area was used Inverse Distance Weighting, Global Polynomial Interpolation, Local Polynomial Interpolation, Radial Basis Function and Kriging methods. Geostatistical methods to evaluate and select the best method of ArcGIS is the ability to perform cross-validation techniques and statistical criteria Root Mean Square Error (RMSE) is used.

Water Quality Index (WQI) zoning in the Silveh watershed for various uses showed that this area has no limitations in terms of groundwater quality and the use of groundwater for drinking, agricultural and industrial uses. The lowest and highest water quality index for drinking water in the area was 33.08 and 38.67, respectively, which is in the high-class of water quality index (less than 50). The lowest and the highest water quality index for agricultural consumption in the area was 36.27 and 72.77, respectively, which is in the high and good class of water quality index (less than 50 and 100-100), and There is no limit to agricultural consumption. Also, the lowest and the highest water quality index for industry consumption in the area was 34.32 and 64.96, respectively, which is in the excellent and good water quality index (less than 50 and 100-100) respectively and for the unlimited use of the industry.
 

Based on mountainous conditions and limited human activities (except for the southern and eastern areas of agricultural activities), the quality of water in the area is good. Although it is growing from the southeastern part of the city of Piranshahr, measures should be taken to prevent degradation of groundwater quality in the area due to various activities. Land use surveys show that agricultural use is about 19.97%, good rangelands are about 50.66%, good poor rangelands, 6.33% of the basin, and county of Birland and residential land cover 23.27% and 34% of the area respectively. The results also clearly illustrate the distinction of land use in the catchment area, because the water quality index in the agricultural and vegetation areas is in a good class (100-150). Given that 50% of the area is covered with good pastures (these rangelands do well to clean up underground water). The results of this study confirm the field performance in terms of high performance and water quality indexes, and recommends that similar research be used. Of course, the lithology of the area should not be ignored. Because water quality has a high correlation with the region's mineralogy. The existence of calcareous and dolomitic stones in the studied area is also a reason for the good water quality of the area.

Introduction Today, a significant portion of the water consumption in Iran, especially in the drinking sector, is provided by water resources. Exploitation of groundwater resources requires knowledge of the quantitative and qualitative status of aquifers. By determining the chemical quality of groundwater, an estimate of the health status of these water resources can be obtained and, depending on its state, the type of use is determined. In this regard, direct and indirect methods can be used to understand the qualitative characteristics of water. Direct methods, despite their high precision, require a high size of observational data, involves substantial time and cost. Hence, numerous indirect methods have been developed for simulating natural systems and estimating their parameters using a computer based on complex calculations. The main advantage of these methods is the ability to learn time series and prediction. One of these methods is modeling or hydrological simulation. The modeling of groundwater quality is an important tool for planning and decision-making in the management of water resources. The goal of this research is to identify the ability of intelligent model of Support Vector Machines (SVM), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS) for modeling groundwater quality variables (EC, SAR, TDS, and TH) in Gero plain and zoning these variables. Therefore, it can provide an appropriate management tool for controlling quality parameters for drinking and farming.
Material and methods In this study, data from 14 wells over the 2008-2016 period was used in order to model the variations in quality variables of Gero plain groundwater. The observed values for Na, Mg, Ca, SO4, Cl, and HCO3 are considered as independent variables and values of EC, SAR, TDS, and TH are considered as dependent variables. An SVM, an ANN, and an ANFIS design were used to model groundwater quality. Input data are randomly divided into two sets such that 80% of data are assigned to the training set and the remaining data (20%) form the test set.
Results Results showed that the ANFIS system had the best performance in the estimation of EC (R2 = 0.99, RMSE=109.13, CE=0.99), SAR (R2 = 0.98, RMSE=0.28, CE=0.98), and TH (R2 = 0.99, RMSE=0.49, CE=0.99) among considered methods for the modeling of groundwater quality. Results also indicated that the ANN had the best performance in estimating TDS (R2 = 0.99, RMSE=109.13, CE=0.99). Furthermore, Schoeller and Wilcox water quality classifications, for drinking and agricultural water, were respectively employed to perform groundwater quality zoning based on outcomes of the considered methods. According to Schoeller classification, TDS has three classes: inappropriate (21.1%), bad (74.59%), and non-dirking (4.31%) and TH variable has four class: good (0.84%), acceptable (23.48%), inappropriate (67.55%), and bad (8.16%). According to Wilcox classification, EC has three classes: excellent (9.41%), good (89.79%), middle (0.8%) and SAR has two classes: excellent (19%) and good (81%).
Discussion and Conclusion ANFIS for a better estimation of EC, SAR, and TH variables outperforms two models of ANN and SVM. The ANFIS system, using the if-then rules, describes that these rules are implemented in a network structure that can be used for learning algorithms used in ANN. Due to this structure, the fuzzy-comparative neural network model has more transparency for analysis and interpretation. The zoning of qualitative variables (TDS and TH) based on the classification of Schoeller drinking water showed that in the TDS variable, the groundwater quality has three classes: bad, inappropriate, and non-drinkable, with the most inadequate plain, southeastern plain bad status and the west of the plain has a terrible situation. The TH zoning map presents that the plain is in good, acceptable, inappropriate, and bad classes. The most part of the plain is in the inappropriate class, the west of the plain in the bad class, and the southeast plain is in an acceptable class. The results of zoning the variables EC and SAR based on the Wilcox agricultural classification showed that groundwater quality is acceptable four agricultural purposes. Therefore, it is essential to take measures to improve the quality of drinking water in the region.

In this study, several data-driven techniques including system identification, adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN) and wavelet-artificial neural network (Wavelet-ANN) models were applied to model rainfall-runoff (RR) relationship. For this purpose, the daily stream flow time series of hydrometric station of Hajighoshan on Gorgan River and the daily rainfall time series belonging to five meteorological stations (Houtan, Maravehtapeh, Tamar, Cheshmehkhan and Tangrah climatologic stations) were used for period of 1983-2007. Root mean square error (RMSE) and correlation coefficient (r) statistics were employed to evaluate the performance of the ANN, ANFIS, ARX and ARMAX models for rainfall-runoff modeling. The results showed that ANFIS models outperformed the system identification, ANN and Wavelet-ANN models. ANFIS model in which preprocessed data using fuzzy interface system was used as input for ANN which could cope with non-linear nature of time series and performed better than others.

Soil organic carbon has favorable effects on the chemical, physical and thermal properties of the soil as well as on the biological activities in the soil. Particulate organic matter-carbon (POM-C) is one of the important unstable elements in the soil organic matter has a considerable role in soil quality and rangeland management. In this research, in order to exact estimate of POM-C using ANN, ANFIS, Regression models were developed. Towards this attempt, 60 soil samples were taken from the depth of 0-30 cm of the soil within 60 quadrates of 1m2 of located along 6 transects of 100m in the rangelands Kharabeh Sangi of Urmia. Soil properties (Nitrogen, clay, silt, organic carbon, pH, EC, apparent specific weight of soil) were measured. Statistic indicators RMSE, CE were used for performance evaluation of the models. The results showed RMSE and CE were calculated 0.16 and 0.41(in Regression Model), 0.11 and 0.65(in Artificial Neural Network Model), 0.06 and 0.79 (in Adative Neuro-Fuzzy Inference System Model), respectively. Also Adative Neuro-Fuzzy Inference System Model is considered as a strong tool in prediction of POM-C compared with Multivariate Linear Regression and Artificial Neural Network Models in the rangelands Kharabeh Sanji of Urmia.