Groundwater is considered one of the most valuable fresh water resources. The main objective of this study was to produce groundwater spring potential maps in the Koohrang Watershed, Chaharmahal-e-Bakhtiari Province, Iran, using three machine learning models: boosted regression tree (BRT), classification and regression tree (CART), and random forest (RF). Thirteen hydrological-geological-physiographical (HGP) factors that influence locations of springs were considered in this research. These factors include slope degree, slope aspect, altitude, topographic wetness index (TWI), slope length (LS), plan curvature, profile curvature, distance to rivers, distance to faults, lithology, land use, drainage density, and fault density. Subsequently, groundwater spring potential was modeled and mapped using CART, RF, and BRT algorithms. The predicted results from the three models were validated using the receiver operating characteristics curve (ROC). From 864 springs identified, 605 (≈70 %) locations were used for the spring potential mapping, while the remaining 259 (≈30 %) springs were used for the model validation. The area under the curve (AUC) for the BRT model was calculated as 0.8103 and for CART and RF the AUC were 0.7870 and 0.7119, respectively. Therefore, it was concluded that the BRT model produced the best prediction results while predicting locations of springs followed by CART and RF models, respectively. Geospatially integrated BRT, CART, and RF methods proved to be useful in generating the spring potential map (SPM) with reasonable accuracy.

GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran

Multi-criteria decision analysis (MCDA) as an advantageous tool has been applied by various researchers to improve their management ability. Management of groundwater resource, especially under data-scarce and arid areas, encountered a lot of problems and issues which drives the planers to use of MCDA. In this research, a standard methodology has been applied to delineate groundwater resource potential zonation based on integrated analytical hierarchy process (AHP), geographic information system (GIS), and remote sensing (RS) techniques in Kurdistan plain, Iran. At first, the effective thematic layers on the groundwater potential such as rainfall, lithology, drainage density, lineament density, and slope percent were derived from the spatial geodatabase. Then, the assigned weights of thematic layers based on expert knowledge were normalized by eigenvector technique of AHP. To prepare the groundwater potential index, the weighted linear combination (WLC) method was applied in GIS. Finally, the receiver operating characteristic (ROC) curve was drawn for groundwater potential map, and the area under curve (AUC) was computed. Results indicated that the rainfall and slope percent factors have taken the highest and lowest weights, respectively. Validation of results showed that the AHP method (AUC = 73.66 %) performed fairly good predication accuracy. Such findings revealed that in the regions suffering from data scarcity through the MCDM methodology, the planners would be able to having accurate knowledge on groundwater resources based on geospatial data analysis. Therefore, the developing scenario for future planning of groundwater exploration can be achieved in an efficient manner.

Groundwater potential mapping at Kurdistan region of Iran using analytic hierarchy process and GIS

Landslide susceptibility mapping is essential for land use planning and decision-making especially in the mountainous areas. The main objective of this study is to produce landslide susceptibility maps at Safarood basin, Iran using two statistical models such as an index of entropy and conditional probability and to compare the obtained results. At the first stage, landslide locations were identified in the study area by interpretation of aerial photographs and from field investigations. Of the 153 landslides identified, 105 (≈70%) locations were used for the landslide susceptibility maps, while the remaining 48 (≈30%) cases were used for the model validation. The landslide conditioning factors such as slope degree, slope aspect, altitude, lithology, distance to faults, distance to rivers, distance to roads, topographic wetness index (TWI), stream power index (SPI), slope–length (LS), land use, and plan curvature were extracted from the spatial database. Using these factors, landslide susceptibility and weights of each factor were analyzed by index of entropy and conditional probability models. Finally, the ROC (receiver operating characteristic) curves for landslide susceptibility maps were drawn and the areas under the curve (AUC) were calculated. The verification results showed that the index of entropy model (AUC=86.08%) performed slightly better than conditional probability (AUC=82.75%) model. The produced susceptibility maps can be useful for general land use planning in the Safarood basin, Iran.

Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood Basin, Iran

Groundwater is considered as the most important natural resources in arid and semi-arid regions. In this study, the application of random forest (RF) and maximum entropy (ME) models for groundwater potential mapping is investigated at Mehran Region, Iran. Although the RF and ME models have been applied widely to environmental and ecological modeling, their applicability to other kinds of predictive modeling such as groundwater potential mapping has not yet been investigated. About 163 groundwater data with high potential yield values of ≥ 11 m 3 /h were obtained from Iranian Department of Water Resources Management (IDWRM). Further, these selected wells were randomly divided into a dataset 70% (114 wells) for training and the remaining 30% (49 wells) was applied for validation purposes. In total, ten groundwater conditioning factors that affect the storage of groundwater occurrences (e.g. altitude, slope percent, slope aspect, plan curvature, drainage density, distance from rivers, topographic wetness index (TWI), landuse, lithology, and soil texture) were used as input to the models. Subsequently, the RF and ME models were applied to generate the groundwater potential maps (GPMs). Moreover, a sensitivity analysis was used to identify the impact of variable uncertainties on the produced GPMs. Finally, the results of the GPMs were quantitatively validated using observed groundwater dataset and the receiver operating characteristic (ROC) method. Area under ROC curve (AUC) was used to compare the performance of RF with ME. The uncertainty on the preparation of conditioning factors was taken in account to enhance the model. The validation results showed that the AUC for success rate of RF and ME models was 86.5 and 91%, respectively. In contrast, the AUC for prediction rate of RF and ME methods was obtained 83.1 and 87.7%, respectively. Therefore, RF and ME were found to be effective models for groundwater potential mapping.

Application of GIS-based data driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran

The main goal of this study was to investigate the analytical hierarchy process (AHP), frequency ratio (FR), and certainty factor (CF) models for groundwater potential mapping using geographical information system (GIS) at Varamin Plain, Tehran province, Iran In the first step, the groundwater conditioning factors such as altitude, slope angle, slope aspect, topographic witness index, rainfall, drainage density, water table level, aquifer thickness, lithology, and distance from rivers were prepared The groundwater yield dataset was prepared using earlier reports, and extensive field surveys In total, 71 groundwater data with high potential yield values of ≥40 m3/h were collected and mapped in GIS Out these, 50 (70 %) cases were randomly selected for models training, and the remaining 21 (30 %) cases were used for the validation purposes Subsequently, groundwater potential maps were produced using AHP, FR, and CF models in ArcGIS 102 Finally, the receiver operating characteristic (ROC) curves for all the groundwater potential models were constructed and the areas under the curves (AUC) were computed From the analysis, it is seen that the FR model (AUC = 7755 %) performs better than AHP (AUC = 7347 %) and CF (AUC = 6508 %) models The results of groundwater potential map can be helpful for future planning in groundwater resource management and land use planning

Application of analytical hierarchy process, frequency ratio, and certainty factor models for groundwater potential mapping using GIS

An artificial neural network model (ANN) and a geographic information system (GIS) are applied to the mapping of regional groundwater productivity potential (GPP) for the area around Pohang City, Republic of Korea. The model is based on the relationship between groundwater productivity data, including specific capacity (SPC) and its related hydrogeological factors. The related factors, including topography, lineaments, geology, and forest and soil data, are collected and input into a spatial database. In addition, SPC data are collected from 44 well locations. The SPC data are randomly divided into a training set, to analyse the GPP using the ANN, and a test set, to validate the predicted potential map. Each factor’s relative importance and weight are determined by the back-propagation training algorithms and applied to the input factor. The GPP value is then calculated using the weights, and GPP maps are created. The map is validated using area under the curve analysis with the SPC data that have not been used for training the model. The validation shows prediction accuracies between 73.54 and 80.09 %. Such information and the maps generated from it could serve as a scientific basis for groundwater management and exploration.

Regional groundwater productivity potential mapping using a geographic information system (GIS) based artificial neural network model

Prediction of landslides using ASTER imagery and data mining models

The purpose of this study is to detect landslide locations using web-based digital aerial photographs and to map landslide susceptibility using landslide locations in Jinbu, Korea. The landslide susceptibility map was generated and validated using frequency ratio, weight of evidence, logistic regression and artificial neural network models with a geographic information system (GIS). The landslide locations were identified in the study area from interpretation of digital aerial photographs that were provided on an Internet portal (http://map.daum.net) and checked by field survey. A spatial database of the topography, soil, forest, geology and land use was constructed and landslide-related factors were extracted. Using these factors, landslide susceptibility was analysed using four models. Seventy percent of the landslides were used in landslide susceptibility mapping and the remaining 30% were used for validation. The validation result showed that the frequency ratio, weight of evidence, logistic regressio...

Kyo-Young Song

Papers

Regional groundwater productivity potential mapping using a geographic information system (GIS) based artificial neural network model

Prediction of landslides using ASTER imagery and data mining models

Detection of landslides using web-based aerial photographs and landslide susceptibility mapping using geospatial analysis