Application of Probabilistic and Machine Learning Models for Groundwater Potentiality Mapping in Damghan Sedimentary Plain, Iran

Groundwater is one of the most important natural resources, as it regulates the earth’s hydrological system. The Damghan sedimentary plain area, located in the region of a semi-arid climate of Iran, has very critical conditions of groundwater due to massive pressure on it and is in need of robust models for identifying the groundwater potential zones (GWPZ). The main goal of the current research is to prepare a groundwater potentiality map (GWPM) considering the probabilistic, machine learning, data mining, and multi-criteria decision analysis (MCDA) approaches. For this purpose, 80 wells collected from the Iranian groundwater resource department and field investigation with global positioning system (GPS), have been selected randomly and considered as the groundwater inventory datasets. Out of 80 wells, 56 (70%) wells have been brought into play for modeling and 24 (30%) for validation purposes. Elevation, slope, aspect, convergence index (CI), rainfall, drainage density (Dd), distance to river, distance to fault, distance to road, lithology, soil type, land use/land cover (LU/LC), normalized difference vegetation index (NDVI), topographic wetness index (TWI), topographic position index (TPI), and stream power index (SPI) have been used for modeling purpose. The area under the receiver operating characteristic (AUROC), sensitivity (SE), specificity (SP), accuracy (AC), mean absolute error (MAE), and root mean square error (RMSE) are used for checking the goodness-of-fit and prediction accuracy of approaches to compare their performance. In addition, the influence of groundwater determining factors (GWDFs) on groundwater occurrence was evaluated by performing a sensitivity analysis model. The GWPMs, produced by technique for order preference by similarity to ideal solution (TOPSIS), random forest (RF), binary logistic regression (BLR), weight of evidence (WoE) and support vector machine (SVM) have been classified into four categories, i.e., low, medium, high and very high groundwater potentiality with the help of the natural break classification methods in the GIS environment. The very high groundwater potentiality class is covered 15.09% for TOPSIS, 15.46% for WoE, 25.26% for RF, 15.47% for BLR, and 18.74% for SVM of the entire plain area. Based on sensitivity analysis, distance from river, and drainage density represent significantly effects on the groundwater occurrence. validation results show that the BLR model with best prediction accuracy and goodness-of-fit outperforms the other five models. Although, all models have very good performance in modeling of groundwater potential. Results of seed cell area index model that used for checking accuracy classification of models show that all models have suitable performance. Therefore, these are promising models that can be applied for the GWPZs identification, which will help for some needful action of these areas.

Download Full-text

Spatial Prediction of Groundwater Potentiality Mapping Using Machine Learning Algorithms

10.21203/rs.3.rs-303246/v1 ◽

2021 ◽

Author(s):

Sunil Saha ◽

Amiya Gayen ◽

Kaustuv Mukherjee ◽

Hamid Reza Pourghasemi ◽

M. Santosh

Keyword(s):

Machine Learning ◽

Influencing Factors ◽

Groundwater Resources ◽

Learning Algorithms ◽

Drainage Density ◽

Groundwater Potential ◽

Machine Learning Algorithms ◽

Lineament Density ◽

Dug Wells ◽

Groundwater Potentiality

Abstract Machine learning techniques offer powerful tools for the assessment and management of groundwater resources. Here, we evaluated the groundwater potential maps (GWPMs) in Md. Bazar Block of Birbhum District, India using four GIS-based machine-learning algorithms (MLA) such as predictive neural network (PNN), decision tree (DT), Naïve Bayes classifier (NBC), and random forest (RF). We used a database of 85 dug wells and one piezometer location identified using extensive field study, and employed 12 influencing factors (elevation, slope, drainage density (DD), topographical wetness index, geomorphology, lineament density, rainfall, geology, pond density, land use/land cover (LULC), geology, and soil texture) for evaluation through GIS. The 85 dug wells and 1 piezometer locations were sub-divided into two classes: 70:30 for training and model validation. The DT, RF, PNN, and NBC MLAs were implemented to analyse the relationship between the dug well locations and groundwater influencing factors to generate GWPMs. The results predict excellent groundwater potential areas (GPA) DT RF of 17.38%, 14.69%, 20.43%, and 13.97% of the study area, respectively. The prediction accuracy of each GWPM was determined using a receiver operating characteristic (ROC) curve. Using the 30% data sets (validation data), accuracies of 80.1%, 78.30%, 75.20%, and 69.2% were obtained for the PNN, RF, DT, and NBC models, respectively. The ROC values show that the four implemented models provide satisfactory and suitable results for GWP mapping in this region. In addition, the well-known mean decrease Gini (MDG) from the RF MLA was implemented to determine the relative importance of the variables for groundwater potentiality assessment. The MDG revealed that drainage density, lineament density, geomorphology, pond density, elevation, and stream junction frequency were the most useful determinants of GWPM. Our approach to delineate the GWPM can aid in the effective planning and management of groundwater resources in this region.

Download Full-text

Mapping Groundwater Potential for Irrigation, by Geographical Information System and Remote Sensing Techniques: A Case Study of District Lower Dir, Pakistan

Atmosphere ◽

10.3390/atmos12060669 ◽

2021 ◽

Vol 12 (6) ◽

pp. 669

Author(s):

Abid Sarwar ◽

Sajid Rashid Ahmad ◽

Muhammad Ishaq Asif Rehmani ◽

Muhammad Asif Javid ◽

Shazia Gulzar ◽

...

Keyword(s):

Remote Sensing ◽

Water Table ◽

Groundwater Potential ◽

Geographical Information ◽

Groundwater Potential Zone ◽

Potential Zone ◽

Relative Significance ◽

High Good ◽

Groundwater Potentiality ◽

Very High

The changing climate and global warming have rendered existing surface water insufficient, which is projected to adversely influence the irrigated farming systems globally. Consequently, groundwater demand has increased significantly owing to increasing population and demand for plant-based foods especially in South Asia and Pakistan. This study aimed to determine the potential areas for groundwater use for agriculture sector development in the study area Lower Dir District. ArcGIS 10.4 was utilized for geospatial analysis, which is referred to as Multi Influencing Factor (MIF) methodology. Seven parameters including land cover, geology, soil, rainfall, underground faults (liniment) density, drainage density, and slope, were utilized for delineation purpose. Considering relative significance and influence of each parameter in the groundwater recharge rating and weightage was given and potential groundwater areas were classified into very high, high, good, and poor. The result of classification disclosed that the areas of 113.10, 659.38, 674.68, and 124.17 km2 had very high, high, good, and poor potential for groundwater agricultural uses, respectively. Field surveys for water table indicated groundwater potentiality, which was high for Kotkay and Lalqila union councils having shallow water table. However, groundwater potentiality was poor in Zimdara, Khal, and Talash, characterized with a very deep water table. Moreover, the study effectively revealed that remote sensing and GIS could be developed as potent tools for mapping potential sites for groundwater utilization. Furthermore, MIF technique could be a suitable approach for delineation of groundwater potential zone, which can be applied for further research in different areas.

Download Full-text

Identification of Groundwater Potential Zones Using GIS and Multi-Criteria Decision-Making Techniques: A Case Study Upper Coruh River Basin (NE Turkey)

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10060396 ◽

2021 ◽

Vol 10 (6) ◽

pp. 396

Author(s):

Ümit Yıldırım

Keyword(s):

Drainage Density ◽

Groundwater Potential ◽

High Potential ◽

Groundwater Potential Zones ◽

Topographic Wetness Index ◽

Analytic Hierarchy ◽

Soil Thickness ◽

Çoruh River Basin ◽

Basin Area ◽

Very High

In this study, geographic information system (GIS)-based, analytic hierarchy process (AHP) techniques were used to identify groundwater potential zones to provide insight to decisionmakers and local authorities for present and future planning. Ten different geo-environmental factors, such as slope, topographic wetness index, geomorphology, drainage density, lithology, lineament density, rainfall, soil type, soil thickness, and land-use classes were selected as the decision criteria, and related GIS tools were used for creating, analysing and standardising the layers. The final groundwater potential zones map was delineated, using the weighted linear combination (WLC) aggregation method. The map was spatially classified into very high potential, high potential, moderate potential, low potential, and very low potential. The results showed that 21.5% of the basin area is characterised by high to very high groundwater potential. In comparison, the very low to low groundwater potential occupies 57.15%, and the moderate groundwater potential covers 21.4% of the basin area. Finally, the GWPZs map was investigated to validate the model, using discharges and depth to groundwater data related to 22 wells scattered over the basin. The validation results showed that GWPZs classes strongly overlap with the well discharges and groundwater depth located in the given area.

Download Full-text

Modeling of Groundwater Potential Using Cloud Computing Platform: A Case Study from Nineveh Plain, Northern Iraq

Water ◽

10.3390/w13233330 ◽

2021 ◽

Vol 13 (23) ◽

pp. 3330

Author(s):

Ali ZA. Al-Ozeer ◽

Alaa M. Al-Abadi ◽

Tariq Abed Hussain ◽

Alan E. Fryar ◽

Biswajeet Pradhan ◽

...

Keyword(s):

Cloud Computing ◽

Drainage Density ◽

Groundwater Potential ◽

Specific Yield ◽

Support Vector ◽

Northern Iraq ◽

Computing Platform ◽

Cloud Computing Platform ◽

Very High

Knowledge of the groundwater potential, especially in an arid region, can play a major role in planning the sustainable management of groundwater resources. In this study, nine machine learning (ML) algorithms—namely, Artificial Neural Network (ANN), Decision Jungle (DJ), Averaged Perceptron (AP), Bayes Point Machine (BPM), Decision Forest (DF), Locally-Deep Support Vector Machine (LD-SVM), Boosted Decision Tree (BDT), Logistic Regression (LG), and Support Vector Machine (SVM)—were run on the Microsoft Azure cloud computing platform to model the groundwater potential. We investigated the relationship between 512 operating boreholes with a specified specific capacity and 14 groundwater-influencing occurrence factors. The unconfined aquifer in the Nineveh plain, Mosul Governorate, northern Iraq, was used as a case study. The groundwater-influencing factors used included elevation, slope, curvature, topographic wetness index, stream power index, soil, land use/land cover (LULC), geology, drainage density, aquifer saturated thickness, aquifer hydraulic conductivity, aquifer specific yield, depth to groundwater, distance to faults, and fault density. Analysis of the contribution of these factors in groundwater potential using information gain ratio indicated that aquifer saturated thickness, rainfall, hydraulic conductivity, depth to groundwater, specific yield, and elevation were the most important factors (average merit > 0.1), followed by geology, fault density, drainage density, soil, LULC, and distance to faults (average merit < 0.1). The average merits for the remaining factors were zero, and thus, these factors were removed from the analysis. When the selected ML classifiers were used to estimate groundwater potential in the Azure cloud computing environment, the DJ and BDT models performed the best in terms of all statistical error measures used (accuracy, precision, recall, F-score, and area under the receiver operating characteristics curve), followed by DF and LD-SVM. The probability of groundwater potential from these algorithms was mapped and visualized into five groundwater potential zones: very low, low, moderate, high, and very high, which correspond to the northern (very low to low), southern (moderate), and middle (high to very high) portions of the study area. Using a cloud computing service provides an improved platform for quickly and cheaply running and testing different algorithms for predicting groundwater potential.

Download Full-text

Novel GIS Based Machine Learning Algorithms for Shallow Landslide Susceptibility Mapping

Sensors ◽

10.3390/s18113777 ◽

2018 ◽

Vol 18 (11) ◽

pp. 3777 ◽

Cited By ~ 61

Author(s):

Ataollah Shirzadi ◽

Karim Soliamani ◽

Mahmood Habibnejhad ◽

Ataollah Kavian ◽

Kamran Chapi ◽

...

Keyword(s):

Machine Learning ◽

Sample Size ◽

Prediction Accuracy ◽

Goodness Of Fit ◽

Learning Algorithm ◽

Machine Learning Algorithms ◽

Landslide Susceptibility Mapping ◽

Sample Sizes ◽

Promising Alternative ◽

Statistical Measures

The main objective of this research was to introduce a novel machine learning algorithm of alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios of different sample sizes and raster resolutions for spatial prediction of shallow landslides around Bijar City, Kurdistan Province, Iran. The evaluation of modeling process was checked by some statistical measures and area under the receiver operating characteristic curve (AUROC). Results show that, for combination of sample sizes of 60%/40% and 70%/30% with a raster resolution of 10 m, the RS model, while, for 80%/20% and 90%/10% with a raster resolution of 20 m, the MB model obtained a high goodness-of-fit and prediction accuracy. The RS-ADTree and MB-ADTree ensemble models outperformed the ADTree model in two scenarios. Overall, MB-ADTree in sample size of 80%/20% with a resolution of 20 m (area under the curve (AUC) = 0.942) and sample size of 60%/40% with a resolution of 10 m (AUC = 0.845) had the highest and lowest prediction accuracy, respectively. The findings confirm that the newly proposed models are very promising alternative tools to assist planners and decision makers in the task of managing landslide prone areas.

Download Full-text

Integrated Geospatial Multi Influencing Factor Approach to Delineate and Identify Groundwater Potential Zones in Kabul Province, Afghanistan

10.21203/rs.3.rs-211720/v1 ◽

2021 ◽

Author(s):

Muhammad Jamal Nasir ◽

Sajjad Khan ◽

Tehreem Ayaz ◽

Amir Zeb Khan ◽

Waqas Ahmad ◽

...

Keyword(s):

Groundwater Resources ◽

Influencing Factor ◽

Relative Weight ◽

Drainage Density ◽

Groundwater Potential ◽

Land Use Land Cover ◽

Groundwater Potential Zones ◽

Lineament Density ◽

Study Results ◽

Groundwater Potentiality

Abstract This study was an attempt to evaluate the groundwater potentiality in Kabul province, Afghanistan using geospatial multi influencing factor (MIF) approach. The influencing parameters employed for the assessment of groundwater potential zones (GWPZ) includes slope, geology, soil, land use/land cover, lineament density, rainfall and drainage density. The sub-classes within each influencing parameter were sub-divided, based on their effectiveness in groundwater potentiality as major, minor and no effect, and subsequently assigned a score value. The combined score value of these parameters was used for calculating the relative weight. The delineated GWPZ were classified in four groups, i.e. poor, moderate, good and very good GWPZ. The study results revealed that very good GWPZ covered an area of 354.87km2 (2% of the total area), good 1523.86 km2 (20%), moderate 2250.99 km2 (73%) and poor 477.19 km2 (5%). The study concluded that geospatial assisted MIF approach was very useful and efficient techniques for the assessment of GWPZ and can be effectively employed to enhance the conceptual understanding of groundwater resources of Kabul Basin, Afghanistan.

Download Full-text

Assessment of groundwater potentiality using geospatial techniques in Purba Bardhaman district, West Bengal

Applied Water Science ◽

10.1007/s13201-020-01302-3 ◽

2020 ◽

Vol 10 (10) ◽

Author(s):

Subodh Chandra Pal ◽

Chiranjit Ghosh ◽

Indrajit Chowdhuri

Keyword(s):

Groundwater Potential ◽

Human Society ◽

Groundwater Potential Zones ◽

Groundwater Availability ◽

Tube Wells ◽

Potential Map ◽

Groundwater Potential Map ◽

Groundwater Potentiality ◽

Gis Software ◽

Very High

Abstract The word water is life, so life on this planet cannot be possible without water. Water is an essential natural resource that is a surface and groundwater device for human society. The purpose of this research is to assess the groundwater potentiality of the Purba Bardhaman district. All data (primary and secondary) are collected from different sources and analyzed in geographic information system (GIS) software to prepare thematic maps. Different geo-environmental factors like as land use and land cover, soil, lithology, rainfall and distance from the river, etc., can impact on groundwater availability directly or indirectly in Purba Bardhaman area. To identify groundwater potential zones, all these factors are composed into GIS software using multi-criteria decision analysis (MCDA) method. The groundwater potential map has been divided into five classes based on their magnitude as very high, high, medium, low and very low groundwater potential zones. It shows that the areas of very low, low, medium, high and very high groundwater potential zones are 21.54%, 35.80%, 26.47%, 10.13%, 6.06%, respectively, of the total area. Finally, validation is carried out using groundwater depth data collected from 44 drilled tube wells which are located in a scattered manner for whole Purba Bardhaman district which indicates a higher similarity with an area under curve value of 86.8%.

Download Full-text

Evaluation of the groundwater recharge potential using GIS multi-criteria data analysis: a case study from district of Itabira, Minas Gerais, southeastern Brazil

Ciência e Natura ◽

10.5902/2179460x40433 ◽

2020 ◽

Vol 42 ◽

pp. e84

Author(s):

José Augusto Costa Gonçalves ◽

Pedro Henrique Rodrigues Pereira ◽

Eliane Maria Vieira

Keyword(s):

Multicriteria Analysis ◽

Drainage Density ◽

Groundwater Potential ◽

Minas Gerais ◽

Water Infiltration ◽

Southeastern Brazil ◽

Aquifer Recharge ◽

Thematic Maps ◽

Groundwater Exploitation ◽

Very High

Knowledge about the groundwater potential is an important tool to sustainably manage groundwater exploitation. In this context, based on the Geographic Information Systems (GIS) and multicriteria analysis by the Analytic Hierarchy Process (AHP), this study had the objective of mapping the groundwater potential of the district of Itabira, Minas Gerais, which is one of the largest mining regions in Brazil. The evaluation of the regional groundwater potential was based on thematic maps of land use and cover, soil, geology, slope, lineament density, and drainage density. From the evaluation of these parameters and their classes, weights were assigned by the AHP method, according to the influence of each one with regard to favoring water infiltration and aquifer recharge. The thematic maps were integrated in a GIS environment, generating a groundwater map of the district divided into five classes of groundwater potential (very low, low, moderate, high, and very high). In about 64% of the territory the potential for groundwater occurrence was very low to low and from moderate to very high in about 36%. The groundwater potential map showed that 64.42% of the district of Itabira has very low to low potential indices, mainly due to a number of regional characteristics that make aquifer infiltration and recharge difficult and occur in large areas of the territory.

Download Full-text

Groundwater Prospect Zonation Using Frequency Ratio Model For Banganga River Basin, India

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.f8019.088619 ◽

2019 ◽

Vol 8 (6) ◽

pp. 806-814

Keyword(s):

River Basin ◽

Drainage Density ◽

Groundwater Potential ◽

Groundwater Prospect ◽

Land Use Land Cover ◽

Well Location ◽

High Zone ◽

Gis Methods ◽

The Right ◽

Very High

Groundwater prospective Zonation mapping and its reasonable improvement are a significant perspective in Banganga River Basin. In the present investigation, the groundwater imminent zones were depicted by receiving a recurrence proportion (FR) model Land use land cover, Geomorphology, Geology, Drainage Density, Lineament Density Aquifer, Slope, well location and water level were the Thematic layers considered for groundwater prospective Zonation mapping. There are 157 spring wells situated in the investigation Study area, of which all wells were considered for evolution rate and staying absolute wells considered for predict rate in the FR model. The last groundwater prospective map was characterized into five zones as Very Low, Low, Medium, High and Very high. Finally, appropriate destinations for Groundwater revitalize for practical groundwater the board were distinguished. The locales were chosen based on profundity of groundwater level, wellspring of spring great areas and inclination from regular spring to select invigorate wells.Groundwater Prospective zone ranging from 2.8068 to 12.3712. It classified into five prospective classes Very low classes cover 904.62 sq km, low zone covers 1220.76 sq km, medium zone covers 1821.46 sq km, High zone covers 2145.55sq km and very High zone covers 2687.57 sqkm.Areas with steeply inclined limestone terrains and younger tough rocks had moderate to weak groundwater potential. The groundwater is mostly not appropriate in the research region for consumption but may be used for irrigation under unique circumstances, on the basis of the chemical analysis. The general findings show that using remote sensing and GIS methods provides strong method for developing groundwater and developing the right exploration scheme.

Download Full-text

Evaluation of Groundwater Potential Zone Using Remote Sensing and Geographical Information System: in Kaffa Zone, South Western Ethiopia

Sriwijaya Journal of Environment ◽

10.22135/sje.2021.6.2.36-52 ◽

2021 ◽

Vol 6 (2) ◽

pp. 36-52

Author(s):

Azarias Woldegebriel ◽

◽

Temesgen Amibo ◽

Abreham Bayu ◽

◽

...

Keyword(s):

Remote Sensing ◽

Prediction Accuracy ◽

Drainage Density ◽

Groundwater Potential ◽

Geographical Information ◽

Groundwater Potential Zone ◽

Potential Zone ◽

Software Analysis ◽

Potential Resource ◽

Western Ethiopia

This study focused on delineating the groundwater potential and recharge area for Kaffa Zone by the method of remote sensing and ArcGIS 10.4 software analysis techniques. There are six main influencing factors (rainfall, slope, land use/cover, lineaments, drainage density, and Lithology) selected for groundwater recharge zone mapping. The thematic maps were scanned, geo-referenced, and classified as suitable for groundwater using ArcGIS 10.4. The methods to assess the potential zone were using weight overlay analysis and hierarchy of analytical process algorithm. The result obtained the potential of ground water were discussed recharge zones into four major categories: very good, good, and moderate and low. This can help for better planning and management the potential resource of groundwater. The results analyzed the groundwater potential that were subdivided in to low, moderate, high, and very high groundwater potentials areas that cover 1664.1,7682.9, 958.27, and 192.78 km2 respectively. The prediction accuracy was checked based on the borehole yield observed and predicted data of respective locations within the selected area. The prediction accuracy obtained (68.42%) reflects that the present study's method was produced significantly reliable and precise results.

Download Full-text