Elsevier

Journal of Hydrology

Volume 513, 26 May 2014, Pages 283-300
Journal of Hydrology

Application of GIS based data driven evidential belief function model to predict groundwater potential zonation

https://doi.org/10.1016/j.jhydrol.2014.02.053Get rights and content

Highlights

  • The EBF model was applied to explore groundwater potential productivity mapping.

  • A total of twelve groundwater conditioning parameters were used.

  • The relationships between the yield and conditioning parameters were assessed.

  • The groundwater potential map was constructed using the belief map and validated.

  • Statistical significant parameters were computed using logistic regression model.

Summary

The objective of this paper is to exploit potential application of an evidential belief function (EBF) model for spatial prediction of groundwater productivity at Langat basin area, Malaysia using geographic information system (GIS) technique. About 125 groundwater yield data were collected from well locations. Subsequently, the groundwater yield was divided into high (⩾11 m3/h) and low yields (<11 m3/h) respectively, based on the groundwater classification standard recommended by Department of Mineral and Geosciences (JMG), Malaysia. Out of all of the borehole data, only 60 wells possessed higher yield at ⩾ 11 m3/h. Further, these wells were randomly divided into a testing dataset 70% (42 wells) for training the model and the remaining 30% (18 wells) was used for validation purpose. To perform cross validation, the frequency ratio (FR) approach was applied into remaining groundwater wells with low yield to show the spatial correlation between the low potential zones of groundwater productivity. A total of twelve groundwater conditioning factors that affect the storage of groundwater occurrences were derived from various data sources such as satellite based imagery, topographic maps and associated database. Those twelve groundwater conditioning factors are elevation, slope, curvature, stream power index (SPI), topographic wetness index (TWI), drainage density, lithology, lineament density, land use, normalized difference vegetation index (NDVI), soil and rainfall. Subsequently, the Dempster–Shafer theory of evidence model was applied to prepare the groundwater potential map. Finally, the result of groundwater potential map derived from belief map was validated using testing data. Furthermore, to compare the performance of the EBF result, logistic regression model was applied. The success-rate and prediction-rate curves were computed to estimate the efficiency of the employed EBF model compared to LR method. The validation results demonstrated that the success-rate for EBF and LR methods were 83% and 82% respectively. The area under the curve for prediction-rate of EBF and LR methods were calculated 78% and 72% respectively. The outputs achieved from the current research proved the efficiency of EBF in groundwater potential mapping.

Introduction

Groundwater is one of the most important natural resources worldwide serving as a major source of water to communities, industries and agricultural purposes (Ayazi et al., 2010, Manap et al., 2012, Manap et al., 2013, Neshat et al., 2013, Pradhan, 2009). Groundwater is defined as water in saturated zone (Fitts, 2002) which fills the pore spaces among mineral grains or cracks and fractured rocks in rock mass. Groundwater is usually formed by rain or snow melts which seeps down through the soil into the underlying rocks (Banks et al., 2002, Saraf and Choudhury, 1998).

The traditional approach of groundwater exploration through drilling, geological, hydro-geological, and geophysical methods are costly and time consuming (Sander et al., 1996, Singh and Prakash, 2002). A common method used to prepare groundwater potential maps is mainly based on ground surveys (Ganapuram et al., 2009). Recently, with the popular use of geographic information systems (GISs) and remote sensing (RS) based technologies, groundwater potential mapping has become an easy procedure (Singh and Prakash, 2002). GIS is a powerful tool to handle huge amount of spatial data and can be used in the decision making process in a number of fields such as geology and environmental management. The information about surface features related to groundwater such as landforms, land use, lineaments can be extracted through RS data. Those data can be easily entered to GIS to integrate with other associated tabular data, followed by spatial analysis and visual interpretation (Jha et al., 2007).

In Malaysia, groundwater has been considered as a hot issue especially during prolonged drought periods. The Selangor state faced a long period of drought in 1998 due to El Nino effects. Groundwater, in other states of Malaysia such as Kelantan, Perlis, Terengganu, Pahang, Sarawak and Sabah has been utilized as a main source of water supply (Suratman, 2004). Moreover, it is being exploited by private sectors for commercial production of mineral water. The failure to recognize the vast potential zone is the main reason for underutilization of groundwater resources in Malaysia.

More recently, a lot of studies have been applied using index based models for assessing groundwater potential mapping (Dar et al., 2010, Madrucci et al., 2008, Nag et al., 2012, Prasad et al., 2008). In some studies probabilistic models such as multi-criteria decision analysis (Chenini et al., 2010, Gupta and Srivastava, 2010, Murthy and Mamo, 2009), weights-of-evidence (Corsini et al., 2009, Lee et al., 2012), frequency ratio (FR) (Oh et al., 2011), and analytical hierarchy process (AHP) (Chowdhury et al., 2009, Pradhan, 2009) have been used for groundwater potential mapping. In recent years, some soft computing techniques such as fuzzy logic (Shahid et al., 2002, Ghayoumian et al., 2007), numerical modelling and decision tree (DT) (Chenini and Mammou, 2010) approaches have been applied in groundwater potential mapping. Magesh et al. (2012) carried out weighted overlay analysis using a multi-influencing factors and assigned weights to various groundwater conditioning factors.

In this paper, an EBF model was applied for groundwater potential mapping (Shafer, 1976, Dempster, 2008). The EBF approach has been popularly used in mineral potential mapping (Moon, 1990). Carranza and Hale (2003) proposed a data-driven approach based on the Dempster’s rule of combination using GIS for mineral potential mapping (Carranza and Castro, 2006). Similarly multivariate based logistic regression model (LR) has been applied in groundwater potential mapping (Ozdemir, 2011). LR model is useful to describe the significance and correlation of groundwater occurence to each conditioning factor.

The main aim of the present study is to evaluate the efficiency of the EBF model for groundwater potential mapping. In order to compare the robustness of the proposed EBF model, a well-known LR model was applied to identify the significant groundwater conditioning factors and subsequently the EBF model was re-run to check its efficiency. Through this analysis, the relationships between wells and each conditioning factor will be quantitatively defined. The main difference between this research and the approaches described in the aforementioned publications is that an EBF model is applied and the result is validated for groundwater potential mapping in the Langat basin, Malaysia. The application of EBF in groundwater potential mapping provides originality to this study.

Section snippets

Study area

Langat River catchment is located in the southeast part of Selangor state. It is considered as the most urbanized river basin in Malaysia providing two thirds of the water in the Selangor state. However, with the large-scale physical and economic development in the area, water scarcity and water quality deterioration is emerging in recent years. Bringemeier (2006) reported that the number of water-intensive enterprises (e.g. steel works, pulp and paper industry, power plants) play a vital role

Groundwater occurrence characteristics

The groundwater data such as topography, number of wells, yield and depth were obtained from Department of Mineral and Geosciences (JMG), Malaysia. Groundwater yield is based on actual pumping test of groundwater well e.g. m3/h. Moreover, groundwater potential is based on prediction of the best potential for groundwater extraction in the study area. There are 125 individual groundwater borehole wells in the study area. In the year 2007, JMG had set up their own standard of groundwater potential

Methodology

The groundwater potential zonation mapping consists of four main steps: (1) data collection and spatial database construction for the groundwater related conditioning factors, (2) assessment of groundwater potential using the relationships between wells and groundwater conditioning factors, (3) validation of the results, (4) description and visual interpretation of the results. Fig. 5 illustrates the general methodological flow chart used in this study.

Application of EBF to groundwater potential mapping

Once three mass functions for all input data layers were prepared, Dempster’s rule of combination was applied to obtain four combined mass functions including the belief, disbelief, ignorance, and plausibility functions.

Eq. (12) shows the Dempster–Shafer theory direct mass function.M:2={ø,Tp,Tp¯,}={Tp,Tp}where Tp and Tp¯ express the following:

  • Tp = class pixels involved by groundwater wells.

  • Tp¯ = class pixels not involved by groundwater wells.

In this part, L Numbers of multiple spatial data layer

Conclusion

Groundwater is one of the most important natural resources which play an increasingly significant role for water supplies throughout the world. Therefore, detection and prediction of spatial distribution of potential locations for groundwater exploration have become an important topic for private, government, and research institutions worldwide. In this paper, a data driven EBF model was successfully applied to delineate the potential groundwater zones in the Langat basin in Malaysia. The

Acknowledgments

This research was supported by RUGS Grant/05-02-12-2195 RU at the University Putra Malaysia (Vote No. 9376500). The Authors would like to thank Department of Survey and Mapping Malaysia (JUPEM), Minerals and Geosciences Department Malaysia (JMG) and Department of Agriculture for providing various data sets for the research. Thanks to Mahyat Shafapour Tehrany, Mustafa Neamah Jebur and Omar Althuwaynee for their valuable contribution while preparing the manuscript. Thanks to anonymous reviewers

References (65)

  • S. Lee et al.

    Application of data-driven evidential belief functions to landslide susceptibility mapping in Jinbu, Korea

    Catena

    (2013)
  • V. Madrucci et al.

    Groundwater favourability map using GIS multi criteria data analysis on crystalline terrain, Sao Paulo State, Brazil

    J. Hydrol.

    (2008)
  • N.S. Magesh et al.

    Delineation of groundwater potential zones in Theni district, Tamil Nadu, using remote sensing

    GIS and MIF techniques. Geosci. Frontiers

    (2012)
  • M. Mohammady et al.

    Landslide susceptibility mapping at Golestan Province, Iran: a comparison between frequency ratio, Dempster–Shafer, and weights-of-evidence models

    J. Asian Earth Sci.

    (2012)
  • H.J. Oh et al.

    GIS mapping of regional probabilistic groundwater potential in the area of Pohang City, Korea

    J. Hydrol.

    (2011)
  • A. Ozdemir

    Using a binary logistic regression method and GIS for evaluating and mapping the groundwater spring potential in the Sultan Mountains (Aksehir, Turkey)

    J. Hydrol.

    (2011)
  • B. Pradhan

    A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS

    Comput. Geosci.

    (2013)
  • M.S. Tehrany et al.

    Spatial prediction of flood susceptible areas using rule based decision tree (DT) and a novel ensemble bivariate and multivariate statistical models in GIS

    J. Hydrol.

    (2013)
  • M.S. Tehrany et al.

    Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS

    J. Hydrol.

    (2014)
  • Z. Umar et al.

    Earthquake induced landslide susceptibility mapping using an integrated ensemble frequency ratio and logistic regression models in West Sumatera Province, Indonesia

    Catena

    (2014)
  • A. Akgun

    A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at İzmir, Turkey

    Landslides

    (2012)
  • M.H. Ayazi et al.

    Disasters and risk reduction in groundwater: Zagros Mountain Southwest Iran using geoinformatics techniques

    Disaster Adv.

    (2010)
  • D. Banks et al.

    An Introduction to Groundwater in Crystalline Bedrock

    (2002)
  • K.J. Beven et al.

    A physically based, variable contributing area model of basin hydrology/Un modèle à base physique de zone d’appel variable de l’hydrologie du bassin versant

    Hydrol. Sci. J.

    (1979)
  • Bringemeier, 2006. Groundwater exploration adjacent to the Kuala Lumpur International Airport/Malaysia—challenges and...
  • D.T. Bui et al.

    Spatial prediction of landslide hazards in Hoa Binh province (Vietnam): a comparative assessment of the efficacy of evidential belief functions and fuzzy logic models

    Catena

    (2012)
  • D.T. Bui et al.

    A novel hybrid evidential belief function-based fuzzy logic model in spatial prediction of rainfall-induced shallow landslides in the Lang Son city area (Vietnam)

    Geomatics, Nat. Hazard Risk

    (2013)
  • E.J.M. Carranza et al.

    Predicting lahar-inundation zones: case study in West Mount Pinatubo, Philippines

    Nat. Hazards

    (2006)
  • E.J.M. Carranza et al.

    Application of data-driven evidential belief functions to prospectivity mapping for aquamarine-bearing pegmatites, Lundazi district, Zambia

    Nat. Resour. Res.

    (2005)
  • F. Chang-Jo et al.

    Validation of spatial prediction models for landslide hazard mapping

    Nat. Hazards

    (2003)
  • Charon, J.E., 1974. Hydrogeological applications of ERTS satellite imagery. In: Proc UN/FAO Regional Seminar on Remote...
  • I. Chenini et al.

    Groundwater recharge zone mapping using GIS-based multi-criteria analysis: a case study in Central Tunisia (Maknassy Basin)

    Water Resour. Manage

    (2010)
  • Cited by (415)

    • Critical review on water quality analysis using IoT and machine learning models

      2024, International Journal of Information Management Data Insights
    View all citing articles on Scopus
    View full text