Evidential Belief Function Model Research Articles

Non-path dependent urban growth potential mapping using a data-driven evidential belief function

Improper urbanization and its environmental impacts have imposed many problems to humanity. Recently, numerous studies have been conducted using different methods to understand and manage spatial and temporal changes in urbanization. In this study, the capability of the data-driven evidential belief function model as a non-path dependent urban growth potential mapping method was evaluated. Using this approach, the conventional trend-based urban growth prediction procedure is transformed into a data integration task through which the potential locations for urban sprawl in response to multiple environmental and anthropogenic variables could be determined. Therefore, true knowledge about urban growth conditioning factors and their quantitative relationships with built-up areas can be obtained. The multivariate-based logistic regression model as a well-known urban growth modelling method was employed to check the efficiency and validity of the proposed evidential belief function model. Furthermore, a hybrid approach based on the logistic regression model results coupled with the data-driven evidential belief function model was developed. The validation results using the relative operating characteristic method indicated that the evidential belief function, logistic regression, and the hybrid methods’ accuracy were 91.81, 84.72, and 92.34%, respectively. Therefore, it can be concluded that while the proposed evidential belief function and hybrid methods for non-path dependent urban growth potential mapping yielded approximately equal results, both of them outperformed the logistic regression model which is an indication of their reliability and accuracy. The proposed evidential belief function and hybrid methods are best suited for integration in different environmental and socio-economic scenarios enhancing the models for urban allocation tasks. In this way, local communities and policy-makers can make smarter decisions.

Flood Spatial Modeling in Northern Iran Using Remote Sensing and GIS: A Comparison between Evidential Belief Functions and Its Ensemble with a Multivariate Logistic Regression Model

Floods are some of the most dangerous and most frequent natural disasters occurring in the northern region of Iran. Flooding in this area frequently leads to major urban, financial, anthropogenic, and environmental impacts. Therefore, the development of flood susceptibility maps used to identify flood zones in the catchment is necessary for improved flood management and decision making. The main objective of this study was to evaluate the performance of an Evidential Belief Function (EBF) model, both as an individual model and in combination with Logistic Regression (LR) methods, in preparing flood susceptibility maps for the Haraz Catchment in the Mazandaran Province, Iran. The spatial database created consisted of a flood inventory, altitude, slope angle, plan curvature, Topographic Wetness Index (TWI), Stream Power Index (SPI), distance from river, rainfall, geology, land use, and Normalized Difference Vegetation Index (NDVI) for the region. After obtaining the required information from various sources, 151 of 211 recorded flooding points were used for model training and preparation of the flood susceptibility maps. For validation, the results of the models were compared to the 60 remaining flooding points. The Receiver Operating Characteristic (ROC) curve was drawn, and the Area Under the Curve (AUC) was calculated to obtain the accuracy of the flood susceptibility maps prepared through success rates (using training data) and prediction rates (using validation data). The AUC results indicated that the EBF, EBF from LR, EBF-LR (enter), and EBF-LR (stepwise) success rates were 94.61%, 67.94%, 86.45%, and 56.31%, respectively, and the prediction rates were 94.55%, 66.41%, 83.19%, and 52.98%, respectively. The results showed that the EBF model had the highest accuracy in predicting flood susceptibility within the catchment, in which 15% of the total areas were located in high and very high susceptibility classes, and 62% were located in low and very low susceptibility classes. These results can be used for the planning and management of areas vulnerable to floods in order to prevent flood-induced damage; the results may also be useful for natural disaster assessment.

Spatial prediction of landslide susceptibility by combining evidential belief function, logistic regression and logistic model tree

In this study, we introduced novel hybrid of evidence believe function (EBF) with logistic regression (EBF-LR) and logistic model tree (EBF-LMT) for landslide susceptibility modelling. Fourteen conditioning factors were selected, including slope aspect, elevation, slope angle, profile curvature, plan curvature, topographic wetness index (TWI), stream sediment transport index (STI), stream power index (SPI), distance to rivers, distance to faults, distance to roads, lithology, normalized difference vegetation index (NDVI), and land use. The importance of factors was assessed using correlation attribute evaluation method. Finally, the performance of three models was evaluated using the area under the curve (AUC). The validation process indicated that the EBF-LMT model acquired the highest AUC for the training (84.7%) and validation (76.5%) datasets, followed by EBF-LR and EBF models. Our result also confirmed that combination of a decision tree-logistic regression-based algorithm with a bivariate statistical model lead to enhance the prediction power of individual landslide models.

Landslide susceptibility assessment using different slope units based on the evidential belief function model

Selecting an appropriate mapping unit is an important step for landslide susceptibility evaluation. This study compares the results of applying different slope units for landslide susceptibility maps. Landslide susceptibility maps based on the evidential belief function model were obtained using two different slope units: hydrological analysis-based and curvature watersheds-based slope units. An inventory map with 249 landslide locations was constructed from multiple sources. Landslide locations were randomly split into two datasets: 70% for building the models and 30% for validation. Nine landslide-influencing factors were prepared for landslide susceptibility mapping in the study area. Area under the curve (AUC) was used to analyse the landslide susceptibility maps by calculating the success rate and prediction rate. The verification results indicated that the AUC for the curvature watersheds and hydrological analysis models were 0.8038 and 0.7885 with prediction accuracy 0.8056 and 0.7798, respectively. The resultant maps will be useful for hazard mitigation purposes.

Wildfire Probability Mapping: Bivariate vs. Multivariate Statistics

Wildfires are one of the most common natural hazards worldwide. Here, we compared the capability of bivariate and multivariate models for the prediction of spatially explicit wildfire probability across a fire-prone landscape in the Zagros ecoregion, Iran. Dempster–Shafer-based evidential belief function (EBF) and the multivariate logistic regression (LR) were applied to a spatial dataset that represents 132 fire events from the period of 2007–2014 and twelve explanatory variables (altitude, aspect, slope degree, topographic wetness index (TWI), annual temperature, and rainfall, wind effect, land use, normalized difference vegetation index (NDVI), and distance to roads, rivers, and residential areas). While the EBF model successfully characterized each variable class by four probability mass functions in terms of wildfire probabilities, the LR model identified the variables that have a major impact on the probability of fire occurrence. Two distribution maps of wildfire probability were developed based upon the results of each model. In an ensemble modeling perspective, we combined the two probability maps. The results were verified and compared by the receiver operating characteristic (ROC) and the Wilcoxon Signed-Rank Test. The results showed that although an improved predictive accuracy (AUC = 0.864) can be achieved via an ensemble modeling of bivariate and multivariate statistics, the models fail to individually provide a satisfactory prediction of wildfire probability (EBFAUC = 0.701; LRAUC = 0.728). From these results, we recommend the employment of ensemble modeling approaches for different wildfire-prone landscapes.

Data-driven evidential belief function (EBF) model in exploring landslide susceptibility zones for the Darjeeling Himalaya, India

In the present study, data-driven evidential belief function model (belief function) was employed to generate landslides susceptibility index map of Darjeeling Himalaya considering 15 landslide causative factors, which grouped into six categories, i.e. geomorphological factors (elevation, aspect, slope, curvature), lithological factors (geology, soil, lineament density, distance to lineament), hydrologic factors (drainage density, distance to drainage, stream power index, topographic wetted index), triggering factor (rainfall), protective factor (normalized differential vegetation index) and anthropogenic factor (land use and land cover). Total 2079 landslide locations were mapped and randomly divided it into training datasets (70% landslide locations) and validation datasets (30% landslide locations). The resultant susceptibility map was divided into five different susceptibility zones i.e. very low, low, moderate, high and very high which covered 5.60%, 25.65%, 34.47%, 24.67% and 9.61% area respectively of the Darjeeling Himalaya. Receiver operating characteristics curve suggested that 80.20% prediction accuracy of the prepared map whereas frequency ratio plot indicated towards the ideal landslides susceptibility index map.

A comparison of statistical methods and multi-criteria decision making to map flood hazard susceptibility in Northern Iran

In north of Iran, flood is one of the most important natural hazards that annually inflict great economic damages on humankind infrastructures and natural ecosystems. The Kiasar watershed is known as one of the critical areas in north of Iran, due to numerous floods and waste of water and soil resources, as well as related economic and ecological losses. However, a comprehensive and systematic research to identify flood-prone areas, which may help to establish management and conservation measures, has not been carried out yet. Therefore, this study tested four methods: evidential belief function (EBF), frequency ratio (FR), Technique for Order Preference by Similarity To ideal Solution (TOPSIS) and Vlse Kriterijumsk Optimizacija Kompromisno Resenje (VIKOR) for flood hazard susceptibility mapping (FHSM) in this area. These were combined in two methodological frameworks involving statistical and multi-criteria decision making approaches. The efficiency of statistical and multi-criteria methods in FHSM were compared by using area under receiver operating characteristic (AUROC) curve, seed cell area index and frequency ratio. A database containing flood inventory maps and flood-related conditioning factors was established for this watershed. The flood inventory maps produced included 132 flood conditions, which were randomly classified into two groups, for training (70%) and validation (30%). Analytical hierarchy process (AHP) indicated that slope, distance to stream and land use/land cover are of key importance in flood occurrence in the study catchment. In validation results, the EBF model had a better prediction rate (0.987) and success rate (0.946) than FR, TOPSIS and VIKOR (prediction rate 0.917, 0.888, and 0.810; success rate 0.939, 0.904, and 0.735, respectively). Based on their frequency ratio and seed cell area index values, all models except VIKOR showed acceptable accuracy of classification.

Groundwater productivity potential mapping using frequency ratio and evidential belief function and artificial neural network models: focus on topographic factors

AbstractThis study analysed groundwater productivity potential (GPP) using three different models in a geographic information system (GIS) for Okcheon city, Korea. Specifically, we have used variety topography factors in this study. The models were based on relationships between groundwater productivity (for specific capacity (SPC) and transmissivity (T)) and hydrogeological factors. Topography, geology, lineament, land-use and soil data were first collected, processed and entered into the spatial database. T and SPC data were collected from 86 well locations. The resulting GPP map has been validated in under the curve analysis area using well data not used for model training. The GPP maps using artificial neural network (ANN), frequency ratio (FR) and evidential belief function (EBF) models for T had accuracies of 82.19%, 81.15% and 80.40%, respectively. Similarly, the ANN, FR and EBF models for SPC had accuracies of 81.67%, 81.36% and 79.89%, respectively. The results illustrate that ANN models can be useful for the development of groundwater resources.

Landslide susceptibility assessment in the Anfu County, China: comparing different statistical and probabilistic models considering the new topo-hydrological factor (HAND)

The present study is aimed at producing landslide susceptibility map of a landslide-prone area (Anfu County, China) by using evidential belief function (EBF), frequency ratio (FR) and Mahalanobis distance (MD) models. To this aim, 302 landslides were mapped based on earlier reports and aerial photographs, as well as, carrying out several field surveys. The landslide inventory was randomly split into a training dataset (70%; 212landslides) for training the models and the remaining (30%; 90 landslides) was cast off for validation purpose. A total of sixteen geo-environmental conditioning factors were considered as inputs to the models: slope degree, slope aspect, plan curvature, profile curvature, the new topo-hydrological factor termed height above the nearest drainage (HAND), average annual rainfall, altitude, distance from rivers, distance from roads, distance from faults, lithology, normalized difference vegetation index (NDVI), sediment transport index (STI), stream power index (SPI), soil texture, and land use/cover. The validation of susceptibility maps was evaluated using the area under the receiver operating characteristic curve (AUROC). As a results, the FR outperformed other models with an AUROC of 84.98%, followed by EBF (78.63%) and MD (78.50%) models. The percentage of susceptibility classes for each model revealed that MD model managed to build a compendious map focused at highly susceptible areas (high and very high classes) with an overall area of approximately 17%, followed by FR (22.76%) and EBF (31%). The premier model (FR) attested that the five factors mostly influenced the landslide occurrence in the area: NDVI, soil texture, slope degree, altitude, and HAND. Interestingly, HAND could manifest clearer pattern with regard to landslide occurrence compared to other topo-hydrological factors such as SPI, STI, and distance to rivers. Lastly, it can be conceived that the susceptibility of the area to landsliding is more subjected to a complex environmental set of factors rather than anthropological ones (residential areas and distance to roads). This upshot can make a platform for further pragmatic measures regarding hazard-planning actions.

Evaluation of landslide susceptibility mapping by evidential belief function, logistic regression and support vector machine models

The main purpose of this study was to produce landslide susceptibility maps using evidential belief function (EBF), logistic regression (LR) and support vector machine (SVM) models and to compare their results for the region surrounding Yongin, South Korea. We compiled a landslide inventory map of 82 landslides based on reports and aerial photographs and confirmed these data through extensive field surveys. All landslides were randomly separated into two data sets of 41 landslide data points each; half were selected to establish the model, and the remaining half were used for validation. We divided 18 landslide conditioning factors into the following four categories: topography factors, hydrology factors, soil map and forest map; these were considered for landslide susceptibility mapping. The relationships between landslide occurrence and landslide conditioning factors were analyzed using the EBF, LR and SVM models. The three models were then validated using the area under the curve (AUC) method. According to the validation results, the prediction accuracy of the LR model (AUC = 94.59%) was higher than those of the EBF model (AUC = 92.25%) and the SVM model (AUC = 81.78%); the LR model also had the highest training accuracy.

Landslide susceptibility assessment using evidential belief function, certainty factor and frequency ratio model at Baxie River basin, NW China

This study evaluates and compares landslide susceptibility maps of the Baxie River basin, Gansu Province, China, using three models: evidential belief function (EBF), certainty factor (CF) and frequency ratio (FR). First, a landslide inventory map is constructed from satellite image interpretation and extensive field data. Second, the study area is partitioned into 17,142 slope units, and modelled using nine landslide influence parameters: elevation, slope angle, slope aspect, relief amplitude, cutting depth, gully density, lithology, normalized difference vegetation index and distance to roads. Finally, landslide susceptibility maps are presented based on EBF, CF and FR models and validated using area under curve (AUC) analysis. The success rates of the EBF, CF and FR models are 0.8038, 0.7924 and 0.8088, respectively, while the prediction rates of the three models are 0.8056, 0.7922 and 0.7989, respectively. The result of this study can be reliably used in land use management and planning.

A comparative assessment of fuzzy logic and evidential belief function models for mapping artesian zone boundary in an arid region, Iraq

Abstract This paper discusses and compares the potential application of the evidential belief function model and fuzzy logic inference system technique for spatial delineation of a groundwater artesian zone boundary in an arid region of central Iraq. First, a flowing well inventory of a total of 93 perennial flowing wells was constructed and randomly partitioned into two data sets: 70% (65 wells) for training and 30% (28 wells) for validation. Twelve groundwater conditioning factors were considered in the geospatial analysis depending on data availability and literature review. The random forest (RF) algorithm was first applied to investigate the most important conditioning factors in groundwater potential analysis. The most important factors with training flowing wells were used to develop predictive models. The prediction accuracy of the developed models was checked using the area under the relative operating characteristic curve. Results showed that the best model with a higher prediction accuracy of 86% was a fuzzy AND model followed by the evidential model with 84%. The main conclusion of this study is that the integrated use of the adapted models with RF offer a rapid assessment tool in groundwater exploration and can be helpful in groundwater management.

Application of weights-of-evidence (WoE) and evidential belief function (EBF) models for the delineation of soil erosion vulnerable zones: a study on Pathro river basin, Jharkhand, India

Soil erosion is a natural geomorphic process and it significantly threatens agriculture, natural resources and environment. The paper seeks to produce soil erosion susceptibility map (SESM) using weights-of-evidence (WoE) and evidential belief function (EBF) models based on geographic information system (GIS) in Pathro river basin, Jharkhand, India. In doing that, the research has taken into consideration a total number of 430 soil erosion patches in highly erosion prone areas in Pathro river basin. Within 430 cases, 300 (69.8%) are randomly selected for training purpose, while the remaining 130 (30.2%) are used for validating the model. It could be mentioned here that both the models have taken into consideration 14 soil erosion conditioning factors, which are derived from the spatial geodatabases. These soil erosion conditioning factors typically include slope, slope aspect, altitude, NDVI, curvature, distance from river, land use and land cover, soil type, rainfall erosivity, stream power index, slope length, distance from road, distance from lineament and lineament density. At the same time, use of WoE and EBF models on a GIS platform would also help one to estimate the soil erosion susceptibility value (SESV) for each pixel. At the same time, by drawing on a suitable classification technique, the paper has also prepared the soil erosion susceptibility map (SESM). Finally, the receiver operating characteristic (ROC) curves have also been prepared for both the soil erosion susceptibility models, mentioned above. The paper also calculates the area under the curve (AUC) for the verification and accuracy assessment of these two models. The result seems to suggest that the SESM, thus, prepared, drawing on both the models, has a high prediction accuracy of 89.80% for the WoE model. Similarly, the AUC for the EBF model has shown 91.80% prediction accuracy. Taken together, it could be argued that both the models have performed good prediction accuracy. In terms of the immediate value, these SESMs, produced with a high success rate and accuracy, would be of some interest and use for planners and policy makers to induct remedial measures in the erosion prone areas.

Spatial prediction of wildfire probability in the Hyrcanian ecoregion using evidential belief function model and GIS

Accurate estimates of wildfire probability and production of distribution maps are the first important steps in wildfire management and risk assessment. In this study, geographical information system (GIS)-automated techniques were integrated with the quantitative data-driven evidential belief function (EBF) model to predict spatial pattern of wildfire probability in a part of the Hyrcanian ecoregion, northern Iran. The historical fire events were identified using earlier reports and MODIS hot spot product as well as by carrying out multiple field surveys. Using the GIS-based EBF model, the relationships among existing fire events and various predictor variables predisposing fire ignition were analyzed. Model results were used to produce a distribution map of wildfire probability. The derived probability map revealed that zones of moderate, high, and very high probability covered nearly 60% of the landscape. Further, the probability map clearly demonstrated that the probability of a fire was strongly dependent upon human infrastructure and associated activities. By comparing the probability map and the historical fire events, a satisfactory spatial agreement between the five probability levels and fire density was observed. The probability map was further validated by receiver operating characteristic using both success rate and prediction rate curves. The validation results confirmed the effectiveness of the GIS-based EBF model that achieved AUC values of 84.14 and 81.03% for success and prediction rates, respectively.

Identification of Critical Flood Prone Areas in Data-Scarce and Ungauged Regions: A Comparison of Three Data Mining Models

Flood is one of the most devastating natural disasters with socio-economic consequences. Thus, preparation of the flood prone areas (FPA) map is essential for flood disaster management, and for planning further development activities. The main goal of this study is to investigate new applications of the evidential belief function (EBF), random forest (RF), and boosted regression trees (BRT) models for identifying the FPA in the Galikesh region, Iran. This research was conducted in three main stages such as data preparation, flood susceptibility mapping using EBF, RF, and BRT models and validation of constructed models using receiver operating characteristic (ROC) curve. At first, a flood inventory map was prepared using documentary sources of Iranian Water Resources Department (IWRD) and extensive field surveys. In total, 63 flood locations were identified in the study area. Of these, 47 (75%) floods were randomly selected as training/model building and the remaining 16 (25%) cases were used for the validation purposes. The flood conditioning factors considered in the study area are altitude, slope aspect, slope angle, topographic wetness index, plan curvature, geology, landuse, distance from rivers, drainage density, and soil texture. Subsequently, the FPA maps were prepared using EBF, RF, and BRT models in a GIS environment. Finally, the results were validated using ROC curve and area under the curve (AUC) analysis. From the analysis, it was seen that the EBF (AUC = 78.67%) and BRT models (AUC = 78.22%) performed better than RF model (AUC = 73.33%). Therefore, the resultant FPA maps can be useful for researchers and planner in flood mitigation strategies.

Application of GIS-based data-driven models for groundwater potential mapping in Kuhdasht region of Iran

Water shortage and population growth in Iran rapidly diminish groundwater supplies. Thus, finding the techniques such as GIS that can be used as powerful tools in groundwater management, and predicting groundwater potential is required. The main objective of this study is to evaluate the efficiency of the statistical index (SI), frequency ratio (FR) weights of evidence (WoE) and evidential belief function (EBF) models for groundwater potential mapping at Kuhdasht region, Lorestan province, Iran. For this purpose, 12 groundwater influencing factors were considered in this investigation. From 171 available wells in the study area, 114 wells (67%) and 57 wells (33%) were used based on random selection in SI, FR, WoE and EBF models as training and validation data-sets, respectively. The area under the ROC curve (AUC) for SI, FR, WoE and EBF models was calculated as 91.8, 91, 93.6 and 93.3%, respectively. These curve values indicated that all four models have reasonably good accuracy in spatially predicting groundwater potential in this area.

Development of groundwater favourability map using GIS-based driven data mining models: an approach for effective groundwater resource management

The development of groundwater favourability map is an effective tool for the sustainability management of groundwater resources in typical agricultural regions, such as southern Perak Province, Malaysia. Assessing the potentiality and pollution vulnerability of groundwater is a fundamental phase of favourability mapping. A geographic information system (GIS)-based Boolean operator of a spatial analyst module was applied to combine a groundwater potentiality map (GPM) model and a groundwater vulnerability to pollution index (GVPI) map, thereby establishing the favourable zones for drinking water exploration in the investigated area. The area GPM model was evaluated by applying a GIS-based Dempster–Shafer–evidential belief function model. In the evaluation, six geoelectrically determined groundwater potential conditioning factors (i.e. overburden resistivity, overburden thickness, aquifer resistivity, aquifer thickness, aquifer transmissivity and hydraulic conductivity) were synthesized by employing the probability-based algorithms of the model. The generated thematic maps of the seven hydrogeological parameters of the DRASTIC model were considered as pollution potential conditioning factors and were analysed with the developed ordered weighted average–DRASTIC index model algorithms to construct the GVPI map. Approximately 88.8 and 85.71% prediction accuracies for the Groundwater Potentiality and GVPI maps were established using the reacting operating characteristic curve method and water quality status–vulnerability zone relationship scheme, respectively. Finally, the area groundwater favourability map (GFM) model was produced by applying a GIS-based Boolean operator on the Groundwater Potentiality and GVPI maps. The GFM model reveals three distinct zones: ‘not suitable’, ‘less suitable’ and ‘very suitable’ zones. The area analysis of the GFM model indicates that more than 50% of the study area is covered by the ‘very suitable’ zones. Results produce a suitability map that can be used by local authorities for the exploitation and management of drinking water in the area. The study findings can also be applied as a tool to help increase public awareness of groundwater issues in developing countries.

A Comparative Study of the Frequency Ratio and Evidential Belief Function Models for Landslide Susceptibility Mapping

The goal of this study was to analyze landslide susceptibility using two different models and compare the results. For this purpose, a landslide inventory map was produced from a field survey, and the inventory was divided into two groups for training and validation, respectively. Sixteen landslide conditioning factors were considered. The relationships between landslide occurrence and landslide conditioning factors were analyzed using the FR (Frequency Ratio) and EBF (Evidential Belief Function) models. The LSI (Landslide Susceptibility Index) maps that were produced were validated using the ROC (Relative Operating Characteristics) curve and the SCAI (Seed Cell Area Index). The AUC (Area under the ROC Curve) values of the FR and EBF LSI maps were 80.6% and 79.5%, with prediction accuracies of 72.7% and 71.8%, respectively. Additionally, in the low and very low susceptibility zones, the FR LSI map had higher SCAI values compared to the EBF LSI map, as high as 0.47%p. These results indicate that both models were reasonably accurate, however that the FR LSI map had a slightly higher accuracy for landslide susceptibility mapping in the study area.

Landslide susceptibility zonation using GIS and evidential belief function model

The main goal of this paper is to generate a landslide susceptibility map through evidential belief function (EBF) model by using Geographic Information System (GIS) for Qianyang County, Shaanxi Province, China. At first, a detailed landslide inventory map was prepared, and the following ten landslide-conditioning factors were collected: slope angle, slope aspect, curvature, plan curvature, profile curvature, altitude, distance to rivers, geomorphology, lithology, and rainfall. The landslides were detected from the interpretation of aerial photographs and supported by field surveys. A total of 81 landslides were randomly split into the following two parts: the training dataset 70 % (56 landslides) were used for establishing the model and the remaining 30 % (25 landslides) were used for the model validation. The ArcGIS was used to analyze landslide-conditioning factors and evaluate landslide susceptibility; as a result, a landslide susceptibility map was generated by using EBF and ArcGIS 10.0, thus divided into the following five susceptibility classes: very low, low, moderate, high, and very high. Finally, when we validated the accuracy of the landslide susceptibility map, both the success-rate and prediction-rate curve methods were applied. The results reveal that a final susceptibility map has the success rate of 83.31 % and the prediction rate of 79.41 %.

Prediction of groundwater flowing well zone at An-Najif Province, central Iraq using evidential belief functions model and GIS.

The objective of this study is to delineate groundwater flowing well zone potential in An-Najif Province of Iraq in a data-driven evidential belief function model developed in a geographical information system (GIS) environment. An inventory map of 68 groundwater flowing wells was prepared through field survey. Seventy percent or 43 wells were used for training the evidential belief functions model and the reset 30% or 19 wells were used for validation of the model. Seven groundwater conditioning factors mostly derived from RS were used, namely elevation, slope angle, curvature, topographic wetness index, stream power index, lithological units, and distance to the Euphrates River in this study. The relationship between training flowing well locations and the conditioning factors were investigated using evidential belief functions technique in a GIS environment. The integrated belief values were classified into five categories using natural break classification scheme to predict spatial zoning of groundwater flowing well, namely very low (0.17-0.34), low (0.34-0.46), moderate (0.46-0.58), high (0.58-0.80), and very high (0.80-0.99). The results show that very low and low zones cover 72% (19,282km(2)) of the study area mostly clustered in the central part, the moderate zone concentrated in the west part covers 13% (3481km(2)), and the high and very high zones extended over the northern part cover 15% (3977km(2)) of the study area. The vast spatial extension of very low and low zones indicates that groundwater flowing wells potential in the study area is low. The performance of the evidential belief functions spatial model was validated using the receiver operating characteristic curve. A success rate of 0.95 and a prediction rate of 0.94 were estimated from the area under relative operating characteristics curves, which indicate that the developed model has excellent capability to predict groundwater flowing well zones. The produced map of groundwater flowing well zones could be used to identify new wells and manage groundwater storage in a sustainable manner.