Abstract

The present research aims at applying three geographic information system (GIS)-based bivariate models, namely, weights of evidence (WOE), weighting factor (WF), and statistical index (SI), for mapping of groundwater potential for sustainable groundwater management. The locations of wells with groundwater yields more than 11 m3/h were selected for modeling. Then, these locations were grouped into two categories with 70% (52 locations) in a training dataset to build the model and 30% (22 locations) in a testing dataset to validate it. Conditioning factors, namely, altitude, slope degree, plan curvature, slope aspect, rainfall, soil, land use, geology, distance from fault, and distance from river were selected. Finally, the three achieved maps were compared using area under receiver operating characteristic (ROC) and area under the ROC curve (AUC). The ROC method result showed that the SI model better fitted the training dataset (AUC = 0.747) followed by WF (AUC = 0.742) and WOE (AUC = 0.737). Results of the testing dataset show that the WOE model (AUC = 0.798) outperforms SI (AUC = 0.795) and WF (AUC = 0.791). According to the WF model, altitude and rainfall had the highest and lowest impacts on groundwater well potential occurrence, respectively. With regard to Friedman test, the difference in performances of these three models was not statistically significant.

INTRODUCTION

Groundwater is considered to be one of the most essential natural resources worldwide, which saturates the pore space of geologic formations, and is used for drinking, agricultural, and industrial activities (Fitts 2002; Todd & Mays 2005; Pradhan 2009; Manap et al. 2013, 2014; Nampak et al. 2014). Moreover, it supplies the greatest proportion of water demand in arid and semi-arid areas. The main source of groundwater formation is rainfall or snowmelt that percolates through the soil to the underlying formation or water table (Banks & Robins 2002). The level of use of groundwater has increased due to population growth and surface water drought and limitation, as well as groundwater's constant temperature, better quality, lower vulnerability to pollution, and being widespread, which make it available to tap when required (Jha et al. 2007; Manap et al. 2013). The existence of groundwater beneath the Earth's surface is the result of interaction among some climatic, hydrological, soil, geological, and physiographical factors.

Iran is an arid country with two-thirds of its area covered by desert without any green pasture as only 10% of the country has enough rainfall; thus, groundwater is the only safe source for drinking, agricultural, and industrial purposes (Pourghasemi & Beheshtirad 2015; Khosravi et al. 2018a, 2018b). The three most common sources for the use of groundwater in Iran are wells, springs, and qanats. Thus, identification of areas with high potential for the existence of groundwater resources is the most important issue in proper groundwater resources management and long-term planning. Groundwater potential assessment and mapping is one of the most substantial aspects of groundwater studies, which helps to better exploit and manage the resources of groundwater (Naghibi et al. 2016).

Among three groundwater indicators, namely, wells, spring, and qanats, wells are best in the identification of groundwater yield. Traditional methods of groundwater identification, including drilling, geophysical, geological, and hydrogeological methods, are time-consuming and costly (Nampak et al. 2014; Khosravi et al. 2018c). Preparation for groundwater potential assessment is mainly through ground survey (Ganapuram et al. 2009). Nowadays, application of geographic information system (GIS) as a powerful tool brings insight into the water resources management field. Moreover, some GIS-based bivariate models of frequency ratio (Naghibi et al. 2015; Razandi et al. 2015; Al-Abadi et al. 2016; Balamurugan et al. 2016; Falah et al. 2017; Kim et al. 2018), Shannon entropy (Naghibi et al. 2015; Khosravi et al. 2016b), weights of evidence (Lee et al. 2012; Tahmassebipoor et al. 2016; Ghorbani Nejad et al. 2017), multivariate logistic regression (Ozdemir 2011; Zandi et al. 2016), multiple criteria decision making of analytical hierarchy process (AHP) (Chenini et al. 2010; Agarwal et al. 2013), and machine learning methods including decision tree (DT), random forest (RF), support vector machine (SVM), naïve Bayes (NB), and hybrid adaptive neuro fuzzy inference system (ANFIS) with meta-heuristic algorithms (Chenini & Mammou 2010; Naghibi et al. 2017; Naghibi & Dashtpagerdi 2017; Lee et al. 2018; Khosravi et al. 2018b, 2018d) have been used in the field of hydrology and water resources, especially for recognition of groundwater.

On the one hand, as machine learning algorithms are new, and although they have widespread uses in most of the sciences, some of them have some weaknesses; thus, researchers have combined them with other methods to solve problems (Tehrany et al. 2014, 2015; Khosravi et al. 2018b, 2018d). On the other hand, their accuracy depends on high-resolution data and, in some cases, bivariate models are more accurate than them. For example, Rahmati & Pourghasemi (2017) compared bivariate method of evidential belief function (EBF) with two machine learning methods, namely, RF and boosted regression trees (BRT), in recognition of flood-prone areas and, eventually, revealed that the EBF method had a higher prediction power than two machine learning methods. Also, they stated that bivariate methods were simple tools with high prediction power.

As shown in a literature review, researchers have applied different methods in different fields of study and, generally, there is no framework that identifies which method is better than others. The accuracy of any model is completely dependent on distribution of the used data, case study characteristics, and model structure. The present research study is mainly aimed at comparing prediction power of the three bivariate models of weights of evidence, weighting factor (WF), and statistical index (SI), which are rarely used in groundwater potential mapping, although their prediction power has been confirmed in other fields of study, such as flood susceptibility mapping (Khosravi et al. 2016a) and landslide susceptibility assessment (Yalcin 2008).

CASE STUDY

Sero Plain in the west of West Azerbaijan Province, which covers about 52 km2, is selected as the case study, where groundwater resources supply the greatest proportion of water demand for drinking and agricultural sectors (see Figure 1).

Figure 1

Case study location and well location map with DEM of Sero Plain, West Azerbaijan Province, Iran.

Figure 1

Case study location and well location map with DEM of Sero Plain, West Azerbaijan Province, Iran.

It is located between 44 37 30 to 44 43 30 E and 37 41 to 37 47 N. Altitude varies from 1,490 m to 1,697 m above the mean sea level. Slope varies between 0 and 26 degrees. According to Urmia Regional Water Authority reports, the mean annual rainfall is about 440 mm. Sero Plain is mostly covered by Inceptisol soil and agriculture land-use covers about 94% of the study area. Geologically, Quaternary and Permian cover about 58% and 18% of the study area, respectively. Average storage coefficient for the study area is about 5%, for Quaternary formation (Qt1 and Qbv) is about 6% and for Eosin and Cambrian is about 4%.

DATA USED

Well inventory mapping

Well inventory mapping is necessary for determination of the spatial relationship of the well locations with each conditioning factor in the case study. Recognition of spatial groundwater with higher potential is performed through wells with higher groundwater yield (Nampak et al. 2014). In this study, the threshold of 11 m3/h was considered according to the reports of Urmia Regional Water Authority and a literature review for groundwater yield, and the wells with groundwater yields higher than 11 m3/h were considered for modeling (Nampak et al. 2014). In the study area, only 75 well locations had groundwater yields higher than 11 m3/h. These wells were grouped into two categories randomly with 70% (53 well locations) in the training dataset and 30% (22 well locations) in the testing dataset. The training dataset was used to build the model and the testing dataset was used to evaluate and compare it with other ones (Nampak et al. 2014; Khosravi et al. 2018b). The locations of wells and their groundwater yields were obtained through Urmia Regional Water Authority.

Conditioning factors

Ten conditioning factors of ground slope, altitude, aspect, curvature, distance from river, distance from fault, lithology, land-use, rainfall, and soil media were considered for groundwater spatial modeling based on a literature review and the available data (Nampak et al. 2014; Khosravi et al. 2018b).

A digital elevation model (DEM) was obtained for the area under study from ASTER Global DEM with a spatial resolution of 30 m; then, factors of ground slope, slope aspect, altitude, and curvature were achieved directly from a DEM using ArcGIS10.2 software. Altitude factor was divided into five classes of 1,491–1,548, 1,548–1,573, 1,573–1,599, 1,599–1,633, and 1,633–1,697 m (Figure 2(a)). Ground slope of the area under study was classified into five categories including 0–3.1, 3.2–5.7, 5.8–8.7, 8.8–12.8, and 12.9–26.7 by quantile scheme classification method (Figure 2(b)). According to a literature review, quantile scheme classification method was applied in the present research to classify all the performed maps (Tehrany et al. 2014, 2015; Khosravi et al. 2018b, 2018c). The plan curvature factor was divided into three classes of less than −0.05 (or concave), −0.05 to 0.05 (or flat), and more than 0.05 (or convex) (Figure 2(c)) (Pham et al. 2017). This factor shows surface topography of the Earth. Slope aspect of Sero Plain was classified into nine categories of flat, north, northeast, east, southeast, south, southwest, west, and northwest (Figure 2(d)).

Figure 2

Groundwater occurrences conditioning factors: altitude (a), slope angle (b), curvature (c), aspect (d), rainfall (e), soil (f), land use (g), geology (h), distance from fault (i), and distance from river (j).

Figure 2

Groundwater occurrences conditioning factors: altitude (a), slope angle (b), curvature (c), aspect (d), rainfall (e), soil (f), land use (g), geology (h), distance from fault (i), and distance from river (j).

Average annual rainfall in 20 years for 4 rain-gauge stations was utilized in the production of the rainfall map. This factor is considered as one of the most substantial conditioning factors in groundwater resources occurrence, as groundwater forms by deep percolation of rainfall or snowmelt. The rainfall map was extracted by Kriging method, because of low RMSE, and divided into five rainfall groups of 400–424, 425–446, 447–467, 468–488, and 49–510 mm (Figure 2(e)). Soil characteristics have a direct effect on groundwater resources in water infiltration. 1:50,000 soil map of West Azerbaijan Province in (.shp) format, provided by Iranian Water Resources Department (IWRD), was applied in the preparation of the case study soil. Three soil types of Inceptisols, rock outcrop/Inceptisols, and rock outcrop/Entisols cover the Sero Plain (Figure 2(f)).

Land-use/land-cover map of the case study was produced by using Landsat 7 (ETM+) through supervised image classification techniques. Images were received from the US Geological Survey (USGS). Finally, the prepared land-use map was divided into three classes of irrigated land and agriculture, dry farming, and moderate rangeland (Figure 2(g)). Geology factor can affect groundwater resources due to different infiltration rates of different lithological formations (Pradhan 2009; Adiat et al. 2012). This factor was identified by GSI. Moreover, the formation of geology, including Qt1, Qbv, E2c, E2s, Pr, and Pgn (Figure 2(h)), were considered. Fault layers of Iran in (.shp) format, provided by Geological Survey of Iran (GSI) at a scale of 1:100,000, were utilized for identification of the fault layer in the area under study. Faults and rivers in the area under study were used in the identification of the two most substantial conditioning factors of distance from fault and distance from river. Finally, these factors were divided into five classes of 0–100, 100–200, 200–500, 500–1,000, and >1,000 m (Figure 2(i) and 2(j)) (Khosravi et al. 2018b).

METHODOLOGY

Three bivariate models of weights of evidence, SI, and WF were applied in spatial modeling of groundwater resources. A flowchart of the present research is presented in Figure 3.

Figure 3

Flowchart of the present research study.

Figure 3

Flowchart of the present research study.

Figure 4

Groundwater well potential mapping using: (a) WOE model, (b) SI model, and (c) WF model.

Figure 4

Groundwater well potential mapping using: (a) WOE model, (b) SI model, and (c) WF model.

Weights of evidence model

The weight of each conditioning factors class in the model is determined through its relationship with the distribution of well locations. The main advantage of the WOE method in comparison with other bivariate models is that it benefits from Bayesian probability model (Pradhan et al. 2010; Tehrany et al. 2014). Two fundamental parameter types to perform this model are positive weights (W+) and negative weights (W) (Pradhan et al. 2010; Khosravi et al. 2016a). W+ shows the presence of the respective conditioning factor in the groundwater well locations and the magnitude of the parameter shows the strength of its relationship with groundwater occurrence. W shows negative correlation and represents the absence of the respective conditioning factor in groundwater occurrence probability (Regmi et al. 2014). The weight of each conditioning factors class (A) is calculated as follows (Bonham-Carter 1994):  
formula
(1)
 
formula
(2)
where P is defined as the probability and Ln is the natural logarithm. B is presence and is absence of groundwater well conditioning factors. As well, A and are defined as the presence and absence of groundwater well, respectively (Xu et al. 2012). Weight contrast, which shows the spatial union of each conditioning factor with groundwater well occurrence, is calculated by the difference between W+ and W (Dahal et al. 2008; Tehrany et al. 2013).
Standard deviation of W is estimated as follows:  
formula
(3)
where two terms of S2W+ and S2W are defined as the variances of positive weights and negative weights, respectively. Variances of positive and negative weights are calculated as follows:  
formula
(4)
 
formula
(5)
By dividing the contract by its standard deviation, the final weight is calculated as follows:  
formula
(6)

Statistical index

SI is another bivariate model that was introduced for the first time by Van Western in 1997 for identification of landslide-prone areas (Khosravi et al. 2016b). Performance of this method can be summarized as: (1) classification of each conditioning factor; (2) overlaying of the groundwater well location and each conditioning factor; (3) calculation of density of wells in each class of factors; (4) calculation of the weight of each conditioning factors class; and, finally, (5) calculation of the algebraic sum of all conditioning factors to produce the map of groundwater well potential. The SI method, similar to other bivariate models, is on the basis of the spatial relationship of groundwater well distribution with the characteristics of each conditioning factor (Yalcin 2008).

The weight of each conditioning factor class is calculated as the natural logarithm of groundwater well density for each class divided by total groundwater well density of the case study (Van Western 1997; Yalcin 2008). Weight of the SI (WSI) model for the given class i of parameter j is calculated through the following equation:  
formula
(7)

Eij is defined as the groundwater well density of the class i of factor j, and E shows the total groundwater well density of the case study. Lij reveals the number of groundwater well locations for the class i of factor j, and LT is considered as the sum of the groundwater wells in the case study. Also, Pij shows the amount of pixels in the class i of factor j and PL is the total number of pixels in the case study.

The positive and negative values for WSI show the strong and weak relationships, respectively, between each class of factors and groundwater occurrence. It is noteworthy that the more the positive value, the greater the correlation will be; it is the opposite for negative values.

Weighting factor

WF is a hybrid model that uses the SI model to determine the weights, and it can be stated that this model is a modified version of the SI model (Cevik & Topal 2003; Yalcin 2008). This model gets the weight for each class from SI and weight for each conditioning factor from WF. The steps for performing this model are: (1) groundwater well inventory is converted to raster; (2) the raster points are crossed with all rasterized conditioning factors; (3) SI values are calculated for each class of factors; (4) values of pixels for each conditioning factor are summed; (5) the WF values for each layer (conditioning factor) are calculated in the range of 1 to 100; and, finally, (6) the values of SI are multiplied by WF values for each class to determine the final hybrid weights. The equations of the WF model are presented below (Yalcin 2008; Khosravi et al. 2016b):  
formula
(8)
 
formula
(9)
where TSI is the total value of groundwater well pixels for any class, n is the number of classes of conditioning factors, WF is the weight of each layer, and MinTSI and MaxTSI are minimum and maximum values among the weights in each layer (Khosravi et al. 2016b). Finally, all the conditioning factors are summed up to produce the map of groundwater well potential.

Model evaluation

Model evaluation is the crucial step to determine the quality of the achieved maps. In the present research, two criteria, namely, receiver operating characteristic (ROC) method and Friedman test, are investigated for model evaluation and comparison.

ROC method

ROC method is the well known and most popular method of evaluation based on visual attractiveness (Fawcett 2006; Powers 2011; Tehrany et al. 2013; Pham et al. 2017). There are two types of ROC curves, including success rate and prediction rate. Success rate is constructed by training dataset; thus, it only shows how the model fits the training data and it cannot be utilized in model validation. As a result, testing dataset, which cannot be used in model building, is applied for model validation. It shows how good the applied model predicts the groundwater well potential. Area under the ROC curve method (AUC) reveals the prediction power of the model, quantitatively.

Friedman

Friedman is a well-known, non-parametric statistical test, introduced by Friedman (1937), and used to determine the statistical significance of differences between groups (prediction power of the models) (Beasley & Zumbo 2003; Khosravi et al. 2018b). Our null hypothesis is that there are not differences in prediction power of the models in mapping of the groundwater well potential. If P-value and chi-square are less than 0.05 and more than 3.84, respectively, then the null hypothesis is rejected (Chapi et al. 2017; Khosravi et al. 2018b, 2018c).

RESULTS AND DISCUSSION

Multi-collinearity diagnosis test

One of the most substantial steps in any spatial modeling is to determine whether there is multi-collinearity between independent variables or not (Pourghasemi & Beheshtirad 2015). Multi-collinearity shows that there exists high correlation between independent variables and one of them can be predicted by another one; thus, it must be removed. Multi-collinearity diagnosis is measured by two indices that are called tolerance and variance inflation factor (VIF) (O'Brien 2007). Tolerances less than 0.2 or 0.1 and/or VIFs of 5 or 10 and/or more indicate multi-collinear problems (O'Brien 2007). According to Table 1, the smallest tolerance and the largest VIF are 0.300 and 3.331, respectively. Thus, no multi-collinearity exists between independent factors in the study area.

Table 1

Multi-collinearity diagnosis index

Conditioning factor Collinearity statistic
 
Tolerance VIF 
Altitude (m) 0.300 3.331 
Slope angle 0.353 2.833 
Plan curvature (100/m) 0.806 1.240 
Aspect 0.332 3.016 
Distance from fault (m) 0.774 1.293 
Distance from river (m) 0.377 2.656 
Rainfall (mm) 0.714 1.401 
Geology (unit) 0.876 1.142 
Land use 0.784 1.275 
Soil 0.779 1.284 
Conditioning factor Collinearity statistic
 
Tolerance VIF 
Altitude (m) 0.300 3.331 
Slope angle 0.353 2.833 
Plan curvature (100/m) 0.806 1.240 
Aspect 0.332 3.016 
Distance from fault (m) 0.774 1.293 
Distance from river (m) 0.377 2.656 
Rainfall (mm) 0.714 1.401 
Geology (unit) 0.876 1.142 
Land use 0.784 1.275 
Soil 0.779 1.284 

Groundwater well potential mapping by WOE model

The achieved weights by WOE model are presented in Table 2. In terms of altitude, the first class, i.e., 1,491–1,548 m, has the highest weight (4.14) and the greater the altitude, the lower would be the weights or the lower the groundwater well potential probability. Results show that 41.5% of the wells have been drilled at the altitude of 1,491–1,548 m. Slopes between 0 and 3.1 degrees show the highest probability of groundwater occurrence and with increase in ground slope, the probability of groundwater occurrence is reduced. The reason is that with increase in the slope, runoff generation gets higher and infiltration lower; thus, the probability of groundwater occurrence decreases. This is in accordance with the results of Khosravi et al. (2018b), Naghibi et al. (2015, 2016), and Nampak et al. (2014). Regarding plan curvature, flat curvature has the highest effect on groundwater (4.35) and the other two curvatures, namely, convex and concave, do not have significant effects on groundwater occurrence. This is because water infiltration is greater in a flat curvature than in other curvatures. North aspect has the highest effect on groundwater occurrence (2.71), followed by southwest (1.08) and east (0.13); however, other aspects do not have significant impacts. This is because north aspect gets the lowest amount of solar radiation among all aspects. Only the rainfall class of 446–467 mm has a positive effect (1.38) on groundwater potential probability and other classes are not effective. Theoretically, the more the rainfall, the higher the probability of groundwater occurrence; however, our case study does not follow this theory; this is because other factors which have significant effects on the groundwater occurrence control the condition. As most of the area under study is covered by Inceptisol soil and the other two types of soil encompass a very small proportion of the area, all the wells are located in Inceptisol soil. Also, as the case study is mostly covered by agricultural lands, all the wells have been drilled in this type of land use. Although 52% of the wells have been drilled in the Qt1 Quaternary-period formation, because large areas are covered by the formation of this period, it does not have a significant impact and the geologic period of Permian (Pcgn) has the highest impact (2.46) on groundwater occurrence; moreover, other geologic units do not have significant effects on groundwater potential. Permian-period formation (Pcgn) consists of sandstone and lime.

Table 2

Achieved weights using WOE, SI, and WF models

Altitude (m) No. of pixels in the domain Percentage of domain No. of wells Percentage of floods WOE SI WF 
1,491–1,548 13,164 18.30 22 41.51 4.14 0.82 100 
1,548–1,573 24,492 34.05 18 33.96 −0.01 0.00 
1,573–1,599 20,000 27.80 12 22.64 −0.84 −0.21 
1,599–1,633 10,080 14.01 0.00 None None 
1,633–1,697 4,196 5.83 1.89 −1.16 −1.13 
Slope degree        
0–3.1 19,992 27.79 22 41.51 2.20 0.40 35.14 
3.1–5.7 24,805 34.48 16 30.19 −0.66 −0.13 
5.7–8.6 16,459 22.88 11.32 −1.95 −0.70 
8.6–12.7 8,406 11.69 16.98 1.19 0.37 
12.7–26.6 2,270 3.16 0.00 None None 
Curvature        
Convex 31,125 43.27 17 32.08 −1.63 −0.30 51.14 
Flat 9,970 13.86 19 35.85 4.35 0.95 
Concave 30,837 42.87 17 32.08 −1.57 −0.29 
Aspect        
Flat 128 0.18 0.00 None None 43.22 
North 10,609 14.75 15 28.30 2.71 0.65 
Northeast 10,931 15.20 3.77 −2.11 −1.39 
East 10,408 14.47 15.09 0.13 0.04 
Southeast 8,901 12.37 11.32 −0.23 −0.09 
South 8,577 11.92 11.32 −0.14 −0.05 
Southwest 7,550 10.50 15.09 1.08 0.36 
West 7,166 9.96 7.55 −0.58 −0.28 
Northwest 7,662 10.65 7.55 −0.73 −0.34 
Rainfall (mm)        
400–423 5,845 8.13 7.55 −0.15 −0.07 
423–446 5,977 8.32 7.55 −0.20 −0.10 
446–467 22,188 30.87 21 39.62 1.38 0.25 
467–487 25,923 36.06 18 33.96 −0.31 −0.06 
487–509 11,948 16.62 11.32 −1.03 −0.38 
Soil        
Rock outcrops/Entisols 1,083 1.51 0.00 None None 9.41 
Outcrops/Inceptisols 2,116 2.94 0.00 None None 
Inceptisols 68,682 95.48 53 100.00 1.6 0.05 
Land use        
Dry farming 1,317 1.83 0.00 None None 15.46 
Moderate rangeland 2,906 4.04 0.00 None None 
Agriculture 67,658 94.13 53 100.00 1.7 0.06 
Geology (unit)        
Qt1 41,724 58.05 28 52.83 −0.76 −0.09 21.99 
Qbv 1,770 2.46 0.00 None None 
E2s 14,871 20.69 15.09 −1.00 −0.31 
Pr 117 0.16 0.00 None None 
Pcgn 13,399 18.64 17 32.08 2.46 0.54 
Distance from fault (m)        
0–100 4,611 6.41 11 20.75 3.96 1.17 67.1 
100–200 4,493 6.25 7.55 0.39 0.19 
200–500 12,910 17.96 13 24.53 1.24 0.31 
500–1,000 18,262 25.41 14 26.42 0.17 0.04 
>1,000 31,605 43.97 11 20.75 −3.24 −0.75 
Distance from river (m)        
0–100 7,369 10.25 13 24.53 3.28 0.87 34.21 
100–200 6,850 9.53 9.43 −0.02 −0.01 
200–500 16,216 22.56 14 26.42 0.67 0.16 
500–1,000 13,254 18.44 11.32 −1.32 −0.49 
34.21 > 1,000 28,192 39.22 15 28.30 −1.61 −0.33 
Altitude (m) No. of pixels in the domain Percentage of domain No. of wells Percentage of floods WOE SI WF 
1,491–1,548 13,164 18.30 22 41.51 4.14 0.82 100 
1,548–1,573 24,492 34.05 18 33.96 −0.01 0.00 
1,573–1,599 20,000 27.80 12 22.64 −0.84 −0.21 
1,599–1,633 10,080 14.01 0.00 None None 
1,633–1,697 4,196 5.83 1.89 −1.16 −1.13 
Slope degree        
0–3.1 19,992 27.79 22 41.51 2.20 0.40 35.14 
3.1–5.7 24,805 34.48 16 30.19 −0.66 −0.13 
5.7–8.6 16,459 22.88 11.32 −1.95 −0.70 
8.6–12.7 8,406 11.69 16.98 1.19 0.37 
12.7–26.6 2,270 3.16 0.00 None None 
Curvature        
Convex 31,125 43.27 17 32.08 −1.63 −0.30 51.14 
Flat 9,970 13.86 19 35.85 4.35 0.95 
Concave 30,837 42.87 17 32.08 −1.57 −0.29 
Aspect        
Flat 128 0.18 0.00 None None 43.22 
North 10,609 14.75 15 28.30 2.71 0.65 
Northeast 10,931 15.20 3.77 −2.11 −1.39 
East 10,408 14.47 15.09 0.13 0.04 
Southeast 8,901 12.37 11.32 −0.23 −0.09 
South 8,577 11.92 11.32 −0.14 −0.05 
Southwest 7,550 10.50 15.09 1.08 0.36 
West 7,166 9.96 7.55 −0.58 −0.28 
Northwest 7,662 10.65 7.55 −0.73 −0.34 
Rainfall (mm)        
400–423 5,845 8.13 7.55 −0.15 −0.07 
423–446 5,977 8.32 7.55 −0.20 −0.10 
446–467 22,188 30.87 21 39.62 1.38 0.25 
467–487 25,923 36.06 18 33.96 −0.31 −0.06 
487–509 11,948 16.62 11.32 −1.03 −0.38 
Soil        
Rock outcrops/Entisols 1,083 1.51 0.00 None None 9.41 
Outcrops/Inceptisols 2,116 2.94 0.00 None None 
Inceptisols 68,682 95.48 53 100.00 1.6 0.05 
Land use        
Dry farming 1,317 1.83 0.00 None None 15.46 
Moderate rangeland 2,906 4.04 0.00 None None 
Agriculture 67,658 94.13 53 100.00 1.7 0.06 
Geology (unit)        
Qt1 41,724 58.05 28 52.83 −0.76 −0.09 21.99 
Qbv 1,770 2.46 0.00 None None 
E2s 14,871 20.69 15.09 −1.00 −0.31 
Pr 117 0.16 0.00 None None 
Pcgn 13,399 18.64 17 32.08 2.46 0.54 
Distance from fault (m)        
0–100 4,611 6.41 11 20.75 3.96 1.17 67.1 
100–200 4,493 6.25 7.55 0.39 0.19 
200–500 12,910 17.96 13 24.53 1.24 0.31 
500–1,000 18,262 25.41 14 26.42 0.17 0.04 
>1,000 31,605 43.97 11 20.75 −3.24 −0.75 
Distance from river (m)        
0–100 7,369 10.25 13 24.53 3.28 0.87 34.21 
100–200 6,850 9.53 9.43 −0.02 −0.01 
200–500 16,216 22.56 14 26.42 0.67 0.16 
500–1,000 13,254 18.44 11.32 −1.32 −0.49 
34.21 > 1,000 28,192 39.22 15 28.30 −1.61 −0.33 
Results show that the greater the distance from the fault, the lower the weights and the lower the impacts on groundwater occurrence, as 0–100 m distance from the fault has the highest effect (3.96) and >1,000 m the lowest effect (−3.24) on groundwater occurrence. This is because faults are cracks and fractures on the soil and rocks, and water infiltrates easily through them. Effect of distance from the river on groundwater occurrence is similar to that of distance from fault, i.e., with increase in the distance from the river, it would be decreased. That is, rivers on the Sero Plain have interactions with each other and they may discharge the groundwater. In the final run, the groundwater well potential mapping (GWPM) was produced using WOE, through the following equation, and is shown in Figure 4(a):  
formula
(10)

The prepared map has been categorized based on quantile classification scheme into five classes of very low (VL), low (L), moderate (M), high (H), and very high (VH) groundwater potential. This method is used in the field of geosciences when data have skewness (Khosravi et al. 2018a, 2018b).

Groundwater well potential mapping by SI model

The achieved weights by the SI model are presented in Table 2. The first class of altitude in the range 1,491–1,548 m has the highest weight of SI (0.82) and the last class in the range 1,633–1,697 m has the lowest weight (−1.13); moreover, the weights decrease with increase in altitude. In terms of ground slope, the first class in the range 0–3.1 degrees has the highest effect on groundwater occurrence (0.4) and the last class has the lowest effect. Similar to the WOE model, flat curvature has the highest impact on groundwater occurrence probability (0.95), but the other two classes are not effective. Among the nine slope aspects, only the north aspect has a positive weight in groundwater occurrence (0.65). Results of the SI model show that there is no clear relationship between rainfall and groundwater occurrence; however, rainfall of 446–467 mm has the greatest influence (0.25). Inceptisol soil and agricultural land use have the highest effect on groundwater occurrence probability. Similar to the WOE model, Pcgn geologic period has the highest impact on groundwater occurrence probability (0.54). Results of the SI model show that with increase in the distances from fault and river, the SI weights are reduced; that is, the greater the distances from fault and river, the lower the groundwater occurrence probability. Finally, the groundwater well potential mapping has been produced using the SI model through the following equation, as shown in Figure 4(b):  
formula
(11)

Groundwater well potential mapping by WF model

The achieved weights by the WF model for each layer are presented in Table 2. Based on the results achieved by the WF model, altitude has the highest effect on groundwater occurrence (100), followed by distance from fault (67.1), plan curvature (51.1), aspect (43.2), ground slope (35.1), distance from river (34.2), geology (21.99), land use (15.46), soil (9.41), and rainfall (1). Finally, GWPM was produced using the WF model through the following equation, as shown in Figure 4(c):  
formula
(12)

Validation of the achieved GWPMs

Results of success rate show that the SI model has the highest AUC (0.747), that is, this model better fits the training dataset, followed by WF (AUC = 0.742) and WOE (AUC = 0.737) (Figure 5(a)).

Figure 5

Model validation by: (a) success rate and (b) prediction rate.

Figure 5

Model validation by: (a) success rate and (b) prediction rate.

Results of prediction rate reveal that, similar to success rate, the WOE model has the highest prediction power (AUC = 0.798) with accuracy of 79.8%, followed by SI (AUC = 0.795) and WF (AUC = 0.791) (Figure 5(b)).

The highest prediction power of the WOE model can be related to the fact that WOE model benefits from the Bayesian-based theorem in a log-linear form. Also, the WOE model is utilized when sufficient dataset is in hand to predict the relative significance of evidential themes by statistical tools (Bonham-Carter 1994).

According to Yesilnacar (2005), all the performed models have good prediction power. Results of Friedman test (Table 3) reveal that P-value (0.913) and chi-square (0.182) are more than 0.05 and less than 3.84, respectively; thus, the null hypothesis is accepted, i.e., the difference between performances of the models is not statistically significant.

Table 3

Friedman test

Model Rank Chi-square P-value 
WOE 0.182 0.913 
SI 2.05 
WF 1.95 
Model Rank Chi-square P-value 
WOE 0.182 0.913 
SI 2.05 
WF 1.95 

Results of the WOE model, as the best model in prediction of groundwater well potential, show that VL, L, M, H, and VH cover about 20.03, 20.05, 20, 19.95, and 19.95% of the study area, respectively (Figure 6). This result for the SI model is close to WOE but for the WF model is not similar. The WF model has an overestimate in the H class and an underestimate in the VL class.

Figure 6

Percentage of area for each class in each model.

Figure 6

Percentage of area for each class in each model.

The result of this research is not in accordance with the results of Falah et al. (2017), in which, FR had a higher prediction power in comparison to SI and WOE, and Ghorbani Nejad el al. (2017), where EBF had a higher efficiency. However, our result is in accordance with the result of Arabameri et al. (2019), that the WOE model outperforms RF and technique for order preference by similarity to ideal solution (TOPSIS) multi-criteria. There is a lot of research about groundwater potential mapping which has applied different types of models in the aforementioned literature review, but there is no universal guideline as to which model is better or has a higher prediction power (Chen et al. 2019). Khosravi et al. (2018d) suggested that as each model has advantages and disadvantages and we cannot find the model that has the highest prediction power with most of the data, some popular models should be applied and finally the best one be selected for further analysis. This is related to the mode structure and type of data (Khosravi et al. 2018c).

CONCLUSION

One of the major causes of today's water crisis is the lack of integrated water resources management and long-term planning for drought stress, especially in developing countries. A principal step towards this aim is identification of the existence of water and groundwater resources. In the present study, three GIS-based models of weights of evidence, SI, and WF were applied in spatial identification of groundwater resources. Outcomes show that all the models showed good results; however, WOE had the highest prediction capability, followed by SI and WF. According to the SI and WOE models, most of the groundwater was identified in the altitude of 1,491–1,548 m, ground slope of 0–3.1 degrees, flat curvature, north aspect, rainfall of 446–467 mm, Inceptisol soil, agricultural land use, Permian geologic period, and 0–100 m distance from fault and rivers. According to the WF model, altitude had the highest impact on groundwater occurrence and rainfall had the lowest. According to the WOE model, 39% of the area under study, located in the southeastern part, had high and very high potential for groundwater. Results of this research study are helpful for Urmia Water Regional Company to sustainably manage groundwater resources.

REFERENCES

REFERENCES
Agarwal
E.
,
Agarwal
R.
,
Garg
R. D.
&
Garg
P. K.
2013
Delineation of groundwater potential zone: an AHP/ANP approach
.
Journal of Earth System Sciences
122
(
3
),
887
898
.
Al-Abadi
A. M.
,
Al-Temmeme
A. A.
&
Al-Ghanimy
M. A.
2016
A GIS-based combining of frequency ratio and index of entropy approaches for mapping groundwater availability zones at Badra–Al Al-Gharbi–Teeb areas, Iraq
.
Sustainable Water Resources Management
2
(
3
),
265
283
.
doi: 10.1007/s40899-016-0056-5
.
Balamurugan
G.
,
Seshan
K.
&
Bera
S.
2016
Frequency ratio model for groundwater potential mapping and its sustainable management in cold desert, India
.
Journal of King Saud University – Science
29
,
333
347
. https://doi.org/10.1016/j.jksus.2016.08.003.
Banks
D.
&
Robins
N.
2002
An Introduction to Groundwater in Crystalline Bedrock
.
Norges Geologiske Undersøkelse
,
Trondheim
, p.
64
.
Beasley
T. M.
&
Zumbo
B. D.
2003
Comparison of aligned Friedman rank and parametric methods for testing interactions in split-plot designs
.
Computational Statistics & Data Analysis
42
(
4
),
569
593
.
doi: 10.1016/S0167-9473(02)00147-0
.
Bonham-Carter
G. F.
1994
Geographic Information Systems for Geoscientists: Modeling with GIS
.
Computer Methods in the Geosciences
,
Pergamon, Oxford
,
UK
.
Cevik
E.
&
Topal
T.
2003
GIS-based landslide susceptibility mapping for a problematic segment of the natural gas pipeline, Hendek (Turkey)
.
Environmental Geology
44
(
8
),
949
962
.
doi: 10.1007/s00254-003-0838-6
.
Chapi
K.
,
Singh
V. P.
,
Shirzadi
A.
,
Shahabi
H.
,
Bui
D. T.
,
Pham
B. T.
&
Khosravi
K.
2017
A novel hybrid artificial intelligence approach for flood susceptibility assessment
.
Environmental Modelling & Software
95
,
229
245
.
doi: 10.1016/j.envsoft.2017.06.012
.
Chen
W.
,
Panahi
M.
,
Khosravi
K.
,
Pourghasemi
H. R.
,
Rezaie
F.
&
Parvinnezhad
D.
2019
Spatial prediction of groundwater potentiality using ANFIS ensembled with teaching-learning-based and biogeography-based optimization
.
Journal of Hydrology
572
,
435
448
.
Chenini
I.
&
Mammou
A. B.
2010
Groundwater recharge study in arid region: an approach using GIS techniques and numerical modeling
.
Computers & Geosciences
36
(
6
),
801
817
.
doi:.1016/j.cageo.2009.06.014
.
Chenini
I.
,
Mammou
A. B.
&
El May
M.
2010
Groundwater recharge zone mapping using GIS-based multi-criteria analysis: a case study in Central Tunisia (Maknassy Basin)
.
Water Resources Management
24
(
5
),
921
939
.
doi: 10.1007/s11269-009-9479-1
.
Dahal
R. K.
,
Hasegawa
S.
,
Nonomura
A.
,
Yamanaka
M.
,
Masuda
T.
&
Nishino
K.
2008
GIS-based weights-of-evidence modelling of rainfall-induced landslides in small catchments for landslide susceptibility mapping
.
Environmental Geology
54
(
2
),
311
324
.
doi: 10.1007/s00254-007-0818-3
.
Falah
F.
,
Ghorbani Nejad
S.
,
Rahmati
O.
,
Daneshfar
M.
&
Zeinivand
H.
2017
Applicability of generalized additive model in groundwater potential modelling and comparison its performance by bivariate statistical methods
.
Geocarto International
32
(
10
),
1069
1089
.
Fawcett
T.
2006
An introduction to ROC analysis
.
Pattern Recognition Letters
27
(
8
),
861
874
.
Fitts
C. R.
2002
Groundwater Science
.
Elsevier
,
Amsterdam
,
The Netherlands
.
Friedman
M.
1937
The use of ranks to avoid the assumption of normality implicit in the analysis of variance
.
Journal of the American Statistical Association
32
(
200
),
675
701
.
doi: 10.2307/2279372
.
Ganapuram
S.
,
Kumar
G. V.
,
Krishna
I. M.
,
Kahya
E.
&
Demirel
M. C.
2009
Mapping of groundwater potential zones in the Musi basin using remote sensing data and GIS
.
Advances in Engineering Software
40
(
7
),
506
518
.
doi: 10.1016/j.advengsoft.2008.10.001
.
Ghorbani Nejad
S.
,
Falah
F.
,
Daneshfar
M.
,
Haghizadeh
A.
&
Rahmati
O.
2017
Delineation of groundwater potential zones using remote sensing and GIS-based data-driven models
.
Geocarto International
32
(
2
),
167
187
.
Jha
M. K.
,
Chowdhury
A.
,
Chowdary
V. M.
&
Peiffer
S.
2007
Groundwater management and development by integrated remote sensing and geographic information systems: prospects and constraints
.
Water Resources Management
21
(
2
),
427
467
.
doi: 10.1007/s11269-006-9024-4
.
Khosravi
K.
,
Pourghasemi
H. R.
,
Chapi
K.
&
Bahri
M.
2016b
Flash flood susceptibility analysis and its mapping using different bivariate models in Iran: a comparison between Shannon's entropy, statistical index, and weighting factor models
.
Environmental Monitoring and Assessment
188
(
12
),
656
.
doi: 10.1007/s10661-016-5665-9
.
Khosravi
K.
,
Pham
B. T.
,
Chapi
K.
,
Shirzadi
A.
,
Shahabi
H.
,
Revhaug
I.
,
Prakash
I.
&
Tien Bui
D.
2018a
A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran
.
Science of the Total Environment
627
,
744
755
.
doi: 10.1016/j.scitotenv.2018.01.266
.
Khosravi
K.
,
Sartaj
M.
,
Tsai
F.
,
Singh
V. P.
,
Nerantzis
K.
,
Melesse
A.
,
Prakhsh
I.
,
Tien Bui
D.
&
Pham
B. T.
2018b
A comparison study of DRASTIC methods with various objective methods for groundwater vulnerability assessment
.
Science of the Total Environment
642
,
1032
1049
.
doi: 10.1016/j.scitotenv.2018.06.130
.
Khosravi
K.
,
Mao
L.
,
Kisi
O.
,
Yaseen
Z.
&
Shahid
S.
2018c
Quantifying hourly suspended sediment using data mining models: case study glacierized Andes catchment, Chile
.
Journal of Hydrology
567
,
165
179
.
Khosravi
K.
,
Panahi
M.
&
Tien Bui
D.
2018d
Spatial prediction of groundwater spring potential mapping based on an adaptive neuro-fuzzy inference system and metaheuristic optimization
.
Hydrology of the Earth System Sciences
22
,
4771
4792
.
doi.org/10.5194/hess-22-4771-2018
.
Lee
S.
,
Kim
Y. S.
&
Oh
H. J.
2012
Application of a weights-of-evidence method and GIS to regional groundwater productivity potential mapping
.
Journal of Environmental Management
96
(
1
),
91
105
.
doi: 10.1016/j.jenvman.2011.09.016
.
Manap
M. A.
,
Sulaiman
W. N. A.
,
Ramli
M. F.
,
Pradhan
B.
&
Surip
N.
2013
A knowledge-driven GIS modeling technique for groundwater potential mapping at the Upper Langat Basin, Malaysia
.
Arabian Journal of Geosciences
6
(
5
),
1621
1637
.
doi: 10.1007/s12517-011-0469-2
.
Manap
M. A.
,
Nampak
H.
,
Pradhan
B.
,
Lee
S.
,
Sulaiman
W. N. A.
&
Ramli
M. F.
2014
Application of probabilistic-based frequency ratio model in groundwater potential mapping using remote sensing data and GIS
.
Arabian Journal of Geosciences
7
(
2
),
711
724
.
doi: 10.1007/s12517-012-0795-z
.
Naghibi
S. A.
&
Dashtpagerdi
M. M.
2017
Evaluation of four supervised learning methods for groundwater spring potential mapping in Khalkhal region (Iran) using GIS-based features
.
Hydrogeology Journal
25
(
1
),
169
189
.
doi: 0.1007/s10040-016-1466-z
.
Naghibi
S. A.
,
Pourghasemi
H. R.
,
Pourtaghi
Z. S.
&
Rezaei
A.
2015
Groundwater qanat potential mapping using frequency ratio and Shannon's entropy models in the Moghan watershed, Iran
.
Earth Science Informatics
8
(
1
),
171
186
.
doi:1007/s12145-014-0145-7
.
Naghibi
S. A.
,
Moghaddam
D. D.
,
Kalantar
B.
,
Pradhan
B.
&
Kisi
O.
2017
A comparative assessment of GIS-based data mining models and a novel ensemble model in groundwater well potential mapping
.
Journal of Hydrology
548
,
471
483
.
doi: 10.1016/j.jhydrol.2017.03.020
.
Nampak
H.
,
Pradhan
B.
&
Manap
M. A.
2014
Application of GIS based data driven evidential belief function model to predict groundwater potential zonation
.
Journal of Hydrology
513
,
283
300
.
doi: 10.1016/j.jhydrol.2014.02.053
.
O'Brien
R. M.
2007
A caution regarding rules of thumb for variance inflation factors
.
Quality & Quantity
41
(
5
),
673
690
.
doi: 10.1007/s11135-006-9018-6
.
Pourghasemi
H. R.
&
Beheshtirad
M.
2015
Assessment of a data-driven evidential belief function model and GIS for groundwater potential mapping in the Koohrang Watershed, Iran
.
Geocarto International
30
(
6
),
662
685
.
doi:1080/10106049.2014.966161
.
Powers
D. M.
2011
Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
.
Journal of Machine Learning Technologies
2
(
1
),
37
63
.
Pradhan
B.
,
Oh
H. J.
&
Buchroithner
M.
2010
Weights-of-evidence model applied to landslide susceptibility mapping in a tropical hilly area
.
Geomatics, Natural Hazards and Risk
1
(
3
),
199
223
.
doi: 10.1080/19475705.2010.498151
.
Rahmati
O.
&
Pourghasemi
H. R.
2017
Identification of critical flood prone areas in data-scarce and ungauged regions: a comparison of three data mining models
.
Water Resources Management
31
(
5
),
1473
1487
.
doi: 10.1007/s11269-017-1589-6
.
Razandi
Y.
,
Pourghasemi
H. R.
,
Neisani
N. S.
&
Rahmati
O.
2015
Application of analytical hierarchy process, frequency ratio, and certainty factor models for groundwater potential mapping using GIS
.
Earth Science Informatics
8
(
4
),
867
883
.
Regmi
A. D.
,
Devkota
K. C.
,
Yoshida
K.
,
Pradhan
B.
,
Pourghasemi
H. R.
,
Kumamoto
T.
&
Akgun
A.
2014
Application of frequency ratio, statistical index, and weights-of-evidence models and their comparison in landslide susceptibility mapping in Central Nepal Himalaya
.
Arabian Journal of Geosciences
7
(
2
),
725
742
.
doi: 10.1007/s12517-012-0807-z
.
Tahmassebipoor
N.
,
Rahmati
O.
,
Noormohamadi
F.
&
Lee
S.
2016
Spatial analysis of groundwater potential using weights-of-evidence and evidential belief function models and remote sensing
.
Arabian Journal of Geosciences
9
(
1
),
79
.
doi: 10.1007/s12517-015-2166-z
.
Tehrany
M. S.
,
Pradhan
B.
&
Jebur
M. N.
2014
Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS
.
Journal of Hydrology
512
,
332
343
.
doi: 10.1016/j.jhydrol.2014.03.008
.
Tehrany
M. S.
,
Pradhan
B.
,
Mansor
S.
&
Ahmad
N.
2015
Flood susceptibility assessment using GIS-based support vector machine model with different kernel types
.
Catena
125
,
91
101
.
doi: 10.1016/j.catena.2014.10.017
.
Todd
D. K.
&
Mays
L. W.
2005
Groundwater Hydrology
.
Wiley
,
New York
,
USA
.
Van Westen
C.
1997
Statistical Landslide Hazard Analysis. ILWIS 2.1 for Windows Application Guide
.
ITC Publication
,
Enschede
,
The Netherlands
, pp.
73
84
.
Yesilnacar
E. K.
2005
The Application of Computational Intelligence to Landslide Susceptibility Mapping in Turkey
.
PhD thesis
,
Department of Geomatics, University of Melbourne
,
Australia
.
Zandi
J.
,
Ghazvinei
P. T.
,
Hashim
R.
,
Yusof
K. B. W.
,
Ariffin
J.
&
Motamedi
S.
2016
Mapping of regional potential groundwater springs using Logistic Regression statistical method
.
Water Resources
43
(
1
),
48
57
.
doi: 10.1134/S0097807816010097
.