GIS-based spatial prediction of debris flows using logistic regression and frequency ratio models for Zêzere River basin and its surrounding area,Northwest Covilhã, Portugal

Landslide susceptibility mapping (LSM) is important for catastrophe management in the mountainous regions. They focus on generating susceptibility maps beginning from landslide inventories and considering the main predisposing parameters. The aim of this study was to assess the susceptibility of the occurrence of debris flows in the Zêzere River basin and its surrounding area using logistic regression (LR) and frequency ratio (FR) models. To achieve this, a landslide inventory map was created using historical information, satellite imagery, and extensive field works. One hundred landslides were mapped, of which 75% were randomly selected as training data, while the remaining 25% were used for validating the models. The landslide influence factors considered for this study were lithology, elevation, slope gradient, slope aspect, plan curvature, profile curvature, normalized difference vegetation index (NDVI), distance to roads, topographic wetness index (TWI), and stream power index (SPI). The relationships between landslide occurrence and these factors were established, and the results were then evaluated and validated. Validation results show that both methods give acceptable results [the area under curve (AUC) of success rates is 83.71 and 76.38 for LR and FR, respectively]. Furthermore, the AUC results for prediction accuracy revealed that LR model has the highest predictive performance (AUC of predicted rate?=?80.26). Hence, it is concluded that the two models showed reasonably good accuracy in predicting the landslide susceptibility in the study area. These two models have the potential to aid planners in development and land-use planning and to offer tools for hazard mitigation measures.     

A comparative assessment between linear and quadratic discriminant analyses (LDA-QDA) with frequency ratio and weights-of-evidence models for forest fire susceptibility mapping in China

Forest fire is known as an important natural hazard in many countries which causes financial damages and human losses; thus, it is necessary to investigate different aspects of this phenomenon. In this study, performance of four models of linear and quadratic discriminant analysis (LDA and QDA), frequency ratio (FR), and weights-of-evidence (WofE) was investigated to model forest fire susceptibility in the Yihuang area, China. For this purpose, firstly, a forest fire locations map was prepared implementing MODIS satellite images and field surveys. Then, it was classified into two groups including training (70%) and validation (30%) by a random algorithm. In addition, 13 forest fire effective factors were prepared and used such as slope degree, slope aspect, altitude, Topographic Wetness Index (TWI), plan curvature, land use, Normalized Difference Vegetation Index (NDVI), annual rainfall, distance from roads and rivers, wind effect, annual temperature, and soil texture. Using the training dataset and effective factors, LDA, QDA, FR, and WofE models were applied and forest fire susceptibility maps were prepared. Finally, area under the curve (AUC) of receiver operating characteristics (ROC) was implemented for investigating the performance of the models. The results depicted that WofE had the best performance (AUC = 82.2%), followed by FR (AUC = 80.9%), QDA (AUC = 78.3%), and LDA (AUC = 78%), respectively. The results of this study showed the high contribution of altitude, slope degree, and temperature. On the other hand, it was seen that slope aspect and soil had the lowest importance in forest fire susceptibility mapping. From the AUC results, it can be concluded that FR, WofE, LDA, and QDA had acceptable performance and could be used for forest fire susceptibility mapping at the regional scale.     

Groundwater qanat potential mapping using frequency ratio and Shannon’s entropy models in the Moghan watershed,Iran

The purpose of current study is to produce groundwater qanat potential map using frequency ratio (FR) and Shannon's entropy (SE) models in the Moghan watershed, Khorasan Razavi Province, Iran. The qanat is basically a horizontal, interconnected series of underground tunnels that accumulate and deliver groundwater from a mountainous source district, along a water- bearing formation (aquifer), and to a settlement. A qanat locations map was prepared for study area in 2013 based on a topographical map at a 1:50,000-scale and extensive field surveys. 53 qanat locations were detected in the field surveys. 70 % (38 locations) of the qanat locations were used for groundwater potential mapping and 30 % (15 locations) were used for validation. Fourteen effective factors were considered in this investigation such as slope degree, slope aspect, altitude, topographic wetness index (TWI), stream power index (SPI), slope length (LS), plan curvature, profile curvature, distance to rivers, distance to faults, lithology, land use, drainage density, and fault density. Using the above conditioning factors, groundwater qanat potential map was generated implementing FR and SE models, and the results were plotted in ArcGIS. The predictive capability of frequency ratio and Shannon's entropy models were determined by the area under the relative operating characteristic curve. The area under the curve (AUC) for frequency ratio model was calculated as 0.8848. Also AUC for Shannon's entropy model was 0.9121, which depicts the excellence of this model in qanat occurrence potential estimation in the study area. So the Shannon's entropy model has higher AUC than the frequency ratio model. The produced groundwater qanat potential maps can assist planners and engineers in groundwater development plans and land use planning.     

Mapping landslide susceptibility with frequency ratio,statistical index,and weights of evidence models: a case study in northern Iran

The main objective of this study is to investigate potential application of frequency ratio (FR), weights of evidence (WoE), and statistical index (SI) models for landslide susceptibility mapping in a part of Mazandaran Province, Iran. First, a landslide inventory map was constructed from various sources. The landslide inventory map was then randomly divided in a ratio of 70/30 for training and validation of the models, respectively. Second, 13 landslide conditioning factors including slope degree, slope aspect, altitude, plan curvature, stream power index, topographic wetness index, sediment transport index, topographic roughness index, lithology, distance from streams, faults, roads, and land use type were prepared, and the relationships between these factors and the landslide inventory map were extracted by using the mentioned models. Subsequently, the multi-class weighted factors were used to generate landslide susceptibility maps. Finally, the susceptibility maps were verified and compared using several methods including receiver operating characteristic curve with the areas under the curve (AUC), landslide density, and spatially agreed area analyses. The success rate curve showed that the AUC for FR, WoE, and SI models was 81.51, 79.43, and 81.27, respectively. The prediction rate curve demonstrated that the AUC achieved by the three models was 80.44, 77.94, and 79.55, respectively. Although the sensitivity analysis using the FR model revealed that the modeling process was sensitive to input factors, the accuracy results suggest that the three models used in this study can be effective approaches for landslide susceptibility mapping in Mazandaran Province, and the resultant susceptibility maps are trustworthy for hazard mitigation strategies.     

GIS-based gully erosion susceptibility mapping: a comparison among three data-driven models and AHP knowledge-based technique

Toroud Watershed in Semnan Province, Iran is a prone area to gully erosion that causes to soil loss and land degradation. To consider the gully erosion, a comprehensive map of gully erosion susceptibility is required as useful tool for decreasing losses of soil. The purpose of this research is to generate a reliable gully erosion susceptibility map (GESM) using GIS-based models including frequency ratio (FR), weights-of-evidence (WofE), index of entropy (IOE), and their comparison to an expert knowledge-based technique, namely, Analytic Hierarchy Process (AHP). At first, 80 gully locations were identified by extensive field surveys and Google Earth images. Then, 56 (70%) gully locations were randomly selected for modeling process, and the remaining 26 (30%) gully locations were used for validation of four models. For considering geo-environmental factors, VIF and tolerance indices are used and among 18 factors, 13 factors including elevation, slope degree, slope aspect, plan curvature, distance from river, drainage density, distance from road, lithology, land use/land cover, topography wetness index (TWI), stream power index (SPI), normalized difference vegetation index (NDVI), and slope–length (LS) were selected for modeling aims. After preparing GESMs through the mentioned models, final maps divided into five classes including very low, low, moderate, high, and very high susceptibility. The receiver operating characteristic (ROC) curve and the seed cell area index (SCAI) as two validation techniques applied for assessment of the built models. The results showed that the AUC (area under the curve) in training data are 0.973 (97.3%), 0.912 (91.2%), 0.939 (93.9%), and 0.926 (92.6%) for AHP, FR, IOE, and WofE models, respectively. In contrast, the prediction rates (validating data) were 0.954 (95.4%), 0.917 (91.7), 0.925 (92.5%), and 0.921 (92.1%) for above models, respectively. Results of AUC indicated that four model have excellent accuracy in prediction of prone areas to gully erosion. In addition, the SCAI values showed that the produced maps are generally reasonable, because the high and very high susceptibility classes had very low SCAI values. The results of this research can be used in soil conservation plans in the study area.     

Landslide susceptibility zonation using statistical and machine learning approaches in Northern Lecco,Italy

This study deals with landslide susceptibility mapping in the northern part of Lecco Province, Lombardy Region, Italy. In so doing, a valid landslide inventory map and thirteen predisposing factors (including elevation, slope aspect, slope degree, plan curvature, profile curvature, distance to waterway, distance to road, distance to fault, soil type, land use, lithology, stream power index, and topographic wetness index) form the spatial database within geographic information system. The used predictive models comprise a bivariate statistical approach called frequency ratio (FR) and two machine learning tools, namely multilayer perceptron neural network (MLPNN) and adaptive neuro-fuzzy inference system (ANFIS). These models first use landslide and non-landslide records for comprehending the relationship between the landslide occurrence and predisposing factors. Then, landslide susceptibility values are predicted for the whole area. The accuracy of the produced susceptibility maps is measured using area under the curve (AUC) index, according to which, the MLPNN (AUC?=?0.916) presented the most accurate map, followed by the ANFIS (AUC?=?0.889) and FR (AUC?=?0.888). Visual interpretation of the susceptibility maps, FR-based correlation analysis, as well as the importance assessment of predisposing factors, all indicated the significant contribution of the road networks to the crucial susceptibility of landslide. Lastly, an explicit predictive formula is extracted from the implemented MLPNN model for a convenient approximation of landslide susceptibility value.

     

基于不同耦合模型的县域滑坡易发性评价对比分析

为有效预测县域滑坡发生的空间概率,探索不同统计学耦合模型滑坡易发性定量评价结果的合理性和精度,以四川省普格县为研究对象。选取坡度、坡向、高程、工程地质岩组、断层和斜坡结构等6项孕灾因子作为评价指标体系,基于信息量模型（I）、确定性系数模型（CF）、证据权模型（WF）、频率比模型（FR）分别与逻辑回归模型（LR）耦合开展滑坡易发性评价。结果表明:各耦合模型评价结果和易发程度区划均是合理的,极高易发区主要分布于则木河、黑水河河谷两侧斜坡带,面积介于129.04～183.43 km2（占比6.77%～9.62%）,各模型评价精度依次为WF-LR模型（AUC=0.869）>I-LR模型（AUC=0.868）>CF-LR模型（AUC=0.866）>NFR-LR模型（AUC=0.858）。研究成果可为川西南山区县域滑坡易发性定量评估提供重要参考。     

Combining landslide susceptibility maps obtained from frequency ratio,logistic regression,and artificial neural network models using ASTER images and GIS

Landslide-related factors were extracted from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images, and integrated techniques were developed, applied, and verified for the analysis of landslide susceptibility in Boun, Korea, using a geographic information system (GIS). Digital elevation model (DEM), lineament, normalized difference vegetation index (NDVI), and land-cover factors were extracted from the ASTER images for analysis. Slope, aspect, and curvature were calculated from a DEM topographic database. Using the constructed spatial database, the relationships between the detected landslide locations and six related factors were identified and quantified using frequency ratio (FR), logistic regression (LR), and artificial neural network (ANN) models. These relationships were used as factor ratings in an overlay analysis to create landslide susceptibility indices and maps. Three landslide susceptibility maps were then combined and applied as new input factors in the FR, LR, and ANN models to make improved susceptibility maps. All of the susceptibility maps were verified by comparison with known landslide locations not used for training the models. The combined landslide susceptibility maps created using three landslide-related input factors showed improved accuracy (87.00% in FR, 88.21% in LR, and 86.51% in ANN models) compared to the individual landslide susceptibility maps (84.34% in FR, 85.40% in LR, and 74.29% in ANN models) generated using the six factors from the ASTER images.     

Landslide susceptibility mapping using frequency ratio, analytic hierarchy process, logistic regression, and artificial neural network methods at the Inje area, Korea

Every year, the Republic of Korea experiences numerous landslides, resulting in property damage and casualties. This study compared the abilities of frequency ratio (FR), analytic hierarchy process (AHP), logistic regression (LR), and artificial neural network (ANN) models to produce landslide susceptibility index (LSI) maps for use in predicting possible landslide occurrence and limiting damage. The areas under the relative operating characteristic (ROC) curves for the FR, AHP, LR, and ANN LSI maps were 0.794, 0.789, 0.794, and 0.806, respectively. Thus, the LSI maps developed by all the models had similar accuracy. A cross-tabulation analysis of landslide occurrence against non-occurrence areas showed generally similar overall accuracies of 65.27, 64.35, 65.51, and 68.47 % for the FR, AHP, LR, and ANN models, respectively. A correlation analysis between the models demonstrated that the LR and ANN models had the highest correlation (0.829), whereas the FR and AHP models had the lowest correlation (0.619).     

Application of frequency ratio,statistical index,and weights-of-evidence models and their comparison in landslide susceptibility mapping in Central Nepal Himalaya

The Mugling–Narayanghat road section falls within the Lesser Himalaya and Siwalik zones of Central Nepal Himalaya and is highly deformed by the presence of numerous faults and folds. Over the years, this road section and its surrounding area have experienced repeated landslide activities. For that reason, landslide susceptibility zonation is essential for roadside slope disaster management and for planning further development activities. The main goal of this study was to investigate the application of the frequency ratio (FR), statistical index (SI), and weights-of-evidence (WoE) approaches for landslide susceptibility mapping of this road section and its surrounding area. For this purpose, the input layers of the landslide conditioning factors were prepared in the first stage. A landslide inventory map was prepared using earlier reports, aerial photographs interpretation, and multiple field surveys. A total of 438 landslide locations were detected. Out these, 295 (67 %) landslides were randomly selected as training data for the modeling using FR, SI, and WoE models and the remaining 143 (33 %) were used for the validation purposes. The landslide conditioning factors considered for the study area are slope gradient, slope aspect, plan curvature, altitude, stream power index, topographic wetness index, lithology, land use, distance from faults, distance from rivers, and distance from highway. The results were validated using area under the curve (AUC) analysis. From the analysis, it is seen that the FR model with a success rate of 76.8 % and predictive accuracy of 75.4 % performs better than WoE (success rate, 75.6 %; predictive accuracy, 74.9 %) and SI (success rate, 75.5 %; predictive accuracy, 74.6 %) models. Overall, all the models showed almost similar results. The resultant susceptibility maps can be useful for general land use planning.     

A GIS-based approach for gully erosion susceptibility modelling using bivariate statistics methods in the Ourika watershed,Morocco

Gully erosion is an important environmental issue with severe impacts. This study aimed to characterize gully erosion susceptibility and assess the capability of information value (InfVal) and frequency ratio (FR) models for its spatial prediction in Ourika watershed of the High Atlas region of Morocco. These two bivariate statistical methods have been used for gully erosion susceptibility mapping by comparing each data layer of causative factor to the existing gully distribution. Weights to the gully causative factors are assigned based on gully density. Gullies have been mapped through field surveys and Google earth high-resolution images. Lithofacies, land use, slope gradient, length-slope, aspect, stream power index, topographical wetness index and plan curvature were considered predisposing factors to gullying. The digitized gullies were randomly split into two parts. Sixty-five percent (65%) of the mapped gullies were randomly selected as training set to build gully susceptibility models, while the remaining 35% cases were used as validation set for the models’ validation. The results showed that barren and sparse vegetation lands and slope gradient above 50% were very susceptible to gully erosion. The ROC curve was used for testing the accuracy of the mentioned models. The analysis confirms that the FR model (AUC 80.61%) shows a better accuracy than InfVal model (AUC 52.07%). The performance of the gully erosion susceptibility map constructed by FR model is greater than that of the map produced by InfVal model. The findings proved that GIS-based bivariate statistical methods such as frequency ratio model could be successfully applied in gully susceptibility mapping in Morocco mountainous regions and in other similar environments. The produced susceptibility map represents a useful tool for sustainable planning, conservation and protection of land from gully processes.     

Extracting of prospective groundwater potential zones using remote sensing data,GIS, and a probabilistic approach in Bojnourd basin,NE of Iran

Various groundwater potential zones for the assessment of groundwater availability in the Bojnourd basin have been investigated using remote sensing, GIS, and a probabilistic approach. Five independent groundwater factors, including topography, ground slope, stream density, geology units, lineament density, and a groundwater productivity factor, i.e., springs’ discharge, were applied. Discharge rates of 226 springs over the area were collected, and the probabilistic model was designed by the discharge rates of springs as the dependent variable. For training the probabilistic model, a ratio of 70/30% of springs’ discharge was applied and discharge rates of 151 springs were selected to randomly train the model. The frequency ratio for each factor was calculated, and the groundwater potential zones were extracted by summation of frequency ratio maps. The groundwater potential map was also classified into four classes, viz., “very good” (with a frequency ratio of >6.75), “good” (5.5FR6.75), “moderate” (4.75FR5.5), and “poor” (FR4.75). Then, the model was verified based on a success-rate curve method which resulted in obtaining an accuracy ratio of 75.77%. Finally, sensitivity analysis was applied by a factor removal method in five steps. Results reveal that topography factor has the biggest effect on the groundwater potential map and removing this factor eventuates in the lowest accuracy of the final map (AUC = 63. 73%). The groundwater potential map is fairly affected by removing the lineament density factor with an accuracy of 68.80%. Removing the lineament density factor has the lowest effect on the final map with accuracy of 68.80%.     

Landslide hazard mapping in the Constantine city,Northeast Algeria using frequency ratio,weighting factor,logistic regression,weights of evidence,and analytical hierarchy process methods

Landslides constitute the most widespread and damaging natural hazards in the Constantine city. They represent a significant constraint to development and urban planning. In order to reduce the risk related to potential landslide, there is a need to develop a comprehensive landslide hazard map (LHM) of the area for an efficient disaster management and for planning development activities. The purpose of this research is to prepare and compare the LHMs of the Constantine city, by applying frequency ratio (FR), weighting factor (Wf), logistic regression (LR), weights of evidence (WOE), and analytical hierarchy process (AHP) methods used in a framework of the geographical information system (GIS). Firstly, a landslide inventory map has been prepared based on the interpretation of aerial photographs, high resolution satellite images, fieldwork, and available literature. Secondly, eight landslide-conditioning factors such as lithology, slope, exposure, rainfall, land use, distance to drainage, distance to road, and distance to fault have been considered to establish LHMs using the FR, Wf, LR, WOE, and AHP models in GIS. For verification, the obtained LHMs have been validated comparing the LHMs with the known landslide locations using the receiver operating characteristics curves (ROC). The validated results indicate that the FR method provides more accurate prediction (86.59 %) of LHMs than the WOE (82.38 %), AHP (77.86 %), Wf (77.58 %), and LR (70.45 %) models. On the other hand, the obtained results showed that all the used models in this study provided a good accuracy in predicting landslide hazard in Constantine city. The established maps can be used as useful tools for risk prevention and land use planning in the Constantine region.     

Assessing LNRF,FR, and AHP models in landslide susceptibility mapping index: a comparative study of Nojian watershed in Lorestan province,Iran

Landslides and slope instabilities are major risks for human activities which often lead to economic losses and human fatalities all over the world. The main purpose of this study is to evaluate and compare the results of Landslide Nominal Risk Factor (LNRF), Frequency Ratio (FR), and Analytical Hierarchy Process (AHP) models in mapping Landslide Susceptibility Index (LSI). The study case, Nojian watershed with an area of 344.91 km², is located in Lorestan province of Iran. The procedure was as follows: first, the effective factors of the landslide basin were prepared for each layer in the GIS software. Then, the layers and the landslides of the basin were also prepared using aerial photographs, satellite images, and fieldwork. Next, the effective factors of the layers were overlapped with the map of landslide distribution to specify the role of units in such distribution. Finally, nine factors including lithology, slope, aspect, altitude, distance from the fault, distance from river, fault land use, rainfall, and altitude were found to be effective elements in landslide occurrence of the basin. The final maps of LSI were prepared based on seven factors using LNRF, FR, and AHP models in GIS. The index of the quality sum (Qs) was also used to assess the accuracy of the LSI maps. The results of the three models with LNRF (40%), FR (39%), and AHP (44%) indicated that the whole study area was located in the classes of high to very high hazard. The Qs values for the three models above were also found to be 0.51, 0.70 and 0.70, respectively. In comparison, according to the amount of Qs, the results of AHP and FR models have slightly better performed than the LNRF model in determining the LSI maps in the study area. Finally, the study watershed was classified into five classes based on LSI as very low, low, moderate, high, and very high. The landslide susceptibility maps can be helpful to select sites and mitigate landslide hazards in the study area and the regions with similar conditions.     

Comparison of landslide susceptibility mapping methodologies for Koyulhisar,Turkey: conditional probability,logistic regression,artificial neural networks,and support vector machine

This case study presented herein compares the GIS-based landslide susceptibility mapping methods such as conditional probability (CP), logistic regression (LR), artificial neural networks (ANNs) and support vector machine (SVM) applied in Koyulhisar (Sivas, Turkey). Digital elevation model was first constructed using GIS software. Landslide-related factors such as geology, faults, drainage system, topographical elevation, slope angle, slope aspect, topographic wetness index, stream power index, normalized difference vegetation index, distance from settlements and roads were used in the landslide susceptibility analyses. In the last stage of the analyses, landslide susceptibility maps were produced from ANN, CP, LR, SVM models, and they were then compared by means of their validations. However, area under curve values obtained from all four methodologies showed that the map obtained from ANN model looks like more accurate than the other models, accuracies of all models can be evaluated relatively similar. The results also showed that the CP is a simple method in landslide susceptibility mapping and highly compatible with GIS operating features. Susceptibility maps can be easily produced using CP, because input process, calculation and output processes are very simple in CP model when compared with the other methods considered in this study.     

Landslide susceptibility mapping by binary logistic regression, analytical hierarchy process, and statistical index models and assessment of their performances

The current research presents a detailed landslide susceptibility mapping study by binary logistic regression, analytical hierarchy process, and statistical index models and an assessment of their performances. The study area covers the north of Tehran metropolitan, Iran. When conducting the study, in the first stage, a landslide inventory map with a total of 528 landslide locations was compiled from various sources such as aerial photographs, satellite images, and field surveys. Then, the landslide inventory was randomly split into a testing dataset 70 % (370 landslide locations) for training the models, and the remaining 30 % (158 landslides locations) was used for validation purpose. Twelve landslide conditioning factors such as slope degree, slope aspect, altitude, plan curvature, normalized difference vegetation index, land use, lithology, distance from rivers, distance from roads, distance from faults, stream power index, and slope-length were considered during the present study. Subsequently, landslide susceptibility maps were produced using binary logistic regression (BLR), analytical hierarchy process (AHP), and statistical index (SI) models in ArcGIS. The validation dataset, which was not used in the modeling process, was considered to validate the landslide susceptibility maps using the receiver operating characteristic curves and frequency ratio plot. The validation results showed that the area under the curve (AUC) for three mentioned models vary from 0.7570 to 0.8520 $ ({\text{AUC}}_{\text{AHP}} = 75.70\;\% ,\;{\text{AUC}}_{\text{SI}} = 80.37\;\% ,\;{\text{and}}\;{\text{AUC}}_{\text{BLR}} = 85.20\;\% ) $ ( AUC AHP = 75.70 % , AUC SI = 80.37 % , and AUC BLR = 85.20 % ) . Also, plot of the frequency ratio for the four landslide susceptibility classes of the three landslide susceptibility models was validated our results. Hence, it is concluded that the binary logistic regression model employed in this study showed reasonably good accuracy in predicting the landslide susceptibility of study area. Meanwhile, the results obtained in this study also showed that the statistical index model can be used as a simple tool in the assessment of landslide susceptibility when a sufficient number of data are obtained.     

Landslide susceptibility mapping at Zonouz Plain,Iran using genetic programming and comparison with frequency ratio,logistic regression,and artificial neural network models

Without a doubt, landslide is one of the most disastrous natural hazards and landslide susceptibility maps (LSMs) in regional scale are the useful guide to future development planning. Therefore, the importance of generating LSMs through different methods is popular in the international literature. The goal of this study was to evaluate the susceptibility of the occurrence of landslides in Zonouz Plain, located in North-West of Iran. For this purpose, a landslide inventory map was constructed using field survey, air photo/satellite image interpretation, and literature search for historical landslide records. Then, seven landslide-conditioning factors such as lithology, slope, aspect, elevation, land cover, distance to stream, and distance to road were utilized for generation LSMs by various models: frequency ratio (FR), logistic regression (LR), artificial neural network (ANN), and genetic programming (GP) methods in geographic information system (GIS). Finally, total four LSMs were obtained by using these four methods. For verification, the results of LSM analyses were confirmed using the landslide inventory map containing 190 active landslide zones. The validation process showed that the prediction accuracy of LSMs, produced by the FR, LR, ANN, and GP, was 87.57, 89.42, 92.37, and 93.27 %, respectively. The obtained results indicated that the use of GP for generating LSMs provides more accurate prediction in comparison with FR, LR, and ANN. Furthermore; GP model is superior to the ANN model because it can present an explicit formulation instead of weights and biases matrices.     

Ensemble of ground subsidence hazard maps using fuzzy logic

Hazard maps of ground subsidence around abandoned underground coal mines (AUCMs) in Samcheok, Korea, were constructed using fuzzy ensemble techniques and a geographical information system (GIS). To evaluate the factors related to ground subsidence, a spatial database was constructed from topographic, geologic, mine tunnel, land use, groundwater, and ground subsidence maps. Spatial data, topography, geology, and various ground-engineering data for the subsidence area were collected and compiled in a database for mapping ground-subsidence hazard (GSH). The subsidence area was randomly split 70/30 for training and validation of the models. The relationships between the detected ground-subsidence area and the factors were identified and quantified by frequency ratio (FR), logistic regression (LR) and artificial neural network (ANN) models. The relationships were used as factor ratings in the overlay analysis to create ground-subsidence hazard indexes and maps. The three GSH maps were then used as new input factors and integrated using fuzzy-ensemble methods to make better hazard maps. All of the hazard maps were validated by comparison with known subsidence areas that were not used directly in the analysis. As the result, the ensemble model was found to be more effective in terms of prediction accuracy than the individual model.     

Locally weighted learning based hybrid intelligence models for groundwater potential mapping and modeling: A case study at Gia Lai province,Vietnam

The groundwater potential map is an important tool for a sustainable water management and land use planning,particularly for agricultural countries like Vietnam. In this article, we proposed new machine learning ensemble techniques namely Ada Boost ensemble(ABLWL), Bagging ensemble(BLWL), Multi Boost ensemble(MBLWL),Rotation Forest ensemble(RFLWL) with Locally Weighted Learning(LWL) algorithm as a base classifier to build the groundwater potential map of Gia Lai province in Vietnam. For this study, eleven conditioning factors(aspect, altitude, curvature, slope, Stream Transport Index(STI), Topographic Wetness Index(TWI), soil, geology,river density, rainfall, land-use) and 134 wells yield data was used to create training(70%) and testing(30%)datasets for the development and validation of the models. Several statistical indices were used namely Positive Predictive Value(PPV), Negative Predictive Value(NPV), Sensitivity(SST), Specificity(SPF), Accuracy(ACC),Kappa, and Receiver Operating Characteristics(ROC) curve to validate and compare performance of models. Results show that performance of all the models is good to very good(AUC: 0.75 to 0.829) but the ABLWL model with AUC = 0.89 is the best. All the models applied in this study can support decision-makers to streamline the management of the groundwater and to develop economy not only of specific territories but also in other regions across the world with minor changes of the input parameters.     

Evaluation of four supervised learning methods for groundwater spring potential mapping in Khalkhal region (Iran) using GIS-based features

One important tool for water resources management in arid and semi-arid areas is groundwater potential mapping. In this study, four data-mining models including K-nearest neighbor (KNN), linear discriminant analysis (LDA), multivariate adaptive regression splines (MARS), and quadric discriminant analysis (QDA) were used for groundwater potential mapping to get better and more accurate groundwater potential maps (GPMs). For this purpose, 14 groundwater influence factors were considered, such as altitude, slope angle, slope aspect, plan curvature, profile curvature, slope length, topographic wetness index (TWI), stream power index, distance from rivers, river density, distance from faults, fault density, land use, and lithology. From 842 springs in the study area, in the Khalkhal region of Iran, 70 % (589 springs) were considered for training and 30 % (253 springs) were used as a validation dataset. Then, KNN, LDA, MARS, and QDA models were applied in the R statistical software and the results were mapped as GPMs. Finally, the receiver operating characteristics (ROC) curve was implemented to evaluate the performance of the models. According to the results, the area under the curve of ROCs were calculated as 81.4, 80.5, 79.6, and 79.2 % for MARS, QDA, KNN, and LDA, respectively. So, it can be concluded that the performances of KNN and LDA were acceptable and the performances of MARS and QDA were excellent. Also, the results depicted high contribution of altitude, TWI, slope angle, and fault density, while plan curvature and land use were seen to be the least important factors.