A tree-based intelligence ensemble approach for spatial prediction of potential groundwater

ABSTRACT The objective of this research is to propose and confirm a new machine learning approach of Best-First tree (BFtree), AdaBoost (AB), MultiBoosting (MB), and Bagging (Bag) ensembles for potential groundwater mapping and assessing role of influencing factors. The Yasuj-Dena area (Iran) is selected as a case study. For this regard, a Yasuj-Dena database was established with 362 springs locations and 12 groundwater-influencing factors (slope, aspect, elevation, stream power index (SPI), length of slope (LS), topographic wetness index (TWI), topographic position index (TPI), land use, lithology, distance from fault, distance from river, and rainfall). The database was employed to train and validate the proposed groundwater models. The area under the curve (AUC) and statistical metrics were employed to check and confirm the quality of the models. The result shows that the BFTree-Bag model (AUC = 0.810, kappa = 0.495) has the highest prediction performance, followed by the BFTree-MB model (AUC = 0.785, kappa = 0.477), and the BFTree-MB model (AUC = 0.745, kappa = 0.422). Compared to the benchmark of Random Forests, the BFTree-Bag model performs better; therefore, we conclude that the BFtree-Bag is a new tool should be used for modeling of groundwater potential.

[1]  Jan Adamowski,et al.  Delimitation of groundwater zones under contamination risk using a bagged ensemble of optimized DRASTIC frameworks , 2019, Environmental Science and Pollution Research.

[2]  S. Mandal,et al.  Identification of groundwater potential zones of the Kumari river basin, India: an RS & GIS based semi-quantitative approach , 2019, Environment, Development and Sustainability.

[3]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[4]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[5]  Ayele Almaw Fenta,et al.  Spatial analysis of groundwater potential using remote sensing and GIS-based multi-criteria evaluation in Raya Valley, northern Ethiopia , 2015, Hydrogeology Journal.

[6]  Lidia Morawska,et al.  New insights into the spatial distribution of particle number concentrations by applying non-parametric land use regression modelling. , 2019, The Science of the total environment.

[7]  Biswajeet Pradhan,et al.  Groundwater aquifer potential modeling using an ensemble multi-adoptive boosting logistic regression technique , 2019 .

[8]  M Vadiati,et al.  A brief overview of trends in groundwater research: Progress towards sustainability? , 2018, Journal of environmental management.

[9]  Mohammad Reza Ahmadzadeh,et al.  SOM-DRASTIC: using self-organizing map for evaluating groundwater potential to pollution , 2017, Stochastic Environmental Research and Risk Assessment.

[10]  Giorgos Mountrakis,et al.  A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research , 2016 .

[11]  Saumitra Mukherjee,et al.  Delineation of Groundwater Potential Zones in Arid Region of India—A Remote Sensing and GIS Approach , 2012, Water Resources Management.

[12]  Yanjun Shang,et al.  Geophysical Assessment of Groundwater Potential: A Case Study from Mian Channu Area, Pakistan , 2018, Ground water.

[13]  Bahareh Kalantar,et al.  Groundwater potential mapping using C5.0, random forest, and multivariate adaptive regression spline models in GIS , 2018, Environmental Monitoring and Assessment.

[14]  R. Reedy,et al.  Impact of land use and land cover change on groundwater recharge and quality in the southwestern US , 2005 .

[15]  D. Bui,et al.  Spatial prediction of groundwater spring potential mapping based on an adaptive neuro-fuzzy inference system and metaheuristic optimization , 2018, Hydrology and Earth System Sciences.

[16]  Zong-Liang Yang,et al.  Improving land‐surface model hydrology: Is an explicit aquifer model better than a deeper soil profile? , 2007 .

[17]  D. M. Bachmanov,et al.  Active faults in the Zagros and central Iran , 2004 .

[18]  Dieu Tien Bui,et al.  The effect of sample size on different machine learning models for groundwater potential mapping in mountain bedrock aquifers , 2020, CATENA.

[19]  H. Pourghasemi,et al.  Groundwater potential mapping at Kurdistan region of Iran using analytic hierarchy process and GIS , 2015, Arabian Journal of Geosciences.

[20]  Wei Chen,et al.  GIS-based groundwater potential analysis using novel ensemble weights-of-evidence with logistic regression and functional tree models. , 2018, The Science of the total environment.

[21]  Omid Rahmati,et al.  Spatial analysis of groundwater potential using weights-of-evidence and evidential belief function models and remote sensing , 2015, Arabian Journal of Geosciences.

[22]  V. Sharma,et al.  Automated Classification of Fatty and Normal Liver Ultrasound Images Based on Mutual Information Feature Selection , 2018 .

[23]  H. Pourghasemi,et al.  Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms , 2019, Geoderma.

[24]  Pijush Samui,et al.  A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping , 2019, CATENA.

[25]  M. Bierkens,et al.  Environmental flow limits to global groundwater pumping , 2019, Nature.

[26]  Francisco Martínez-Álvarez,et al.  Determining the best set of seismicity indicators to predict earthquakes. Two case studies: Chile and the Iberian Peninsula , 2013, Knowl. Based Syst..

[27]  Biswajeet Pradhan,et al.  Novel Hybrid Integration Approach of Bagging-Based Fisher’s Linear Discriminant Function for Groundwater Potential Analysis , 2019, Natural Resources Research.

[28]  Marcos Aurélio Vasconcelos de Freitas,et al.  Sustainable Groundwater Exploitation Aiming at the Reduction of Water Vulnerability in the Brazilian Semi-Arid Region , 2019, Energies.

[29]  Biswajeet Pradhan,et al.  Groundwater spring potential modelling: Comprising the capability and robustness of three different modeling approaches , 2018, Journal of Hydrology.

[30]  Yih-Chi Tan,et al.  A Two-Stage Approach Integrating SOM- and MOGA-SVM-Based Algorithms to Forecast Spatial-temporal Groundwater Level with Meteorological Factors , 2018, Water Resources Management.

[31]  B. Pradhan,et al.  GIS-based modeling of rainfall-induced landslides using data mining-based functional trees classifier with AdaBoost, Bagging, and MultiBoost ensemble frameworks , 2016, Environmental Earth Sciences.

[32]  Yuan-Chien Lin,et al.  Analysis of space-time non-stationary patterns of rainfall-groundwater interactions by integrating empirical orthogonal function and cross wavelet transform methods , 2015 .

[33]  T. Kavzoglu,et al.  Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression , 2014, Landslides.

[34]  Akira Kawamura,et al.  Social sustainability assessment of groundwater resources: A case study of Hanoi, Vietnam , 2018, Ecological Indicators.

[35]  Biswajeet Pradhan,et al.  Self-Learning Random Forests Model for Mapping Groundwater Yield in Data-Scarce Areas , 2018, Natural Resources Research.

[36]  K. Sreelash,et al.  GIS and AHP Techniques Based Delineation of Groundwater Potential Zones: a case study from Southern Western Ghats, India , 2019, Scientific Reports.

[37]  Geoffrey I. Webb,et al.  MultiBoosting: A Technique for Combining Boosting and Wagging , 2000, Machine Learning.

[38]  Alfian Abdul Halin,et al.  Optimized Conditioning Factors Using Machine Learning Techniques for Groundwater Potential Mapping , 2019, Water.

[39]  Vazeer Mahammood,et al.  Groundwater-level assessment and prediction using realistic pumping and recharge rates for semi-arid coastal regions: a case study of Visakhapatnam city, India , 2018, Hydrogeology Journal.

[40]  B. Pham,et al.  Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan. , 2019, The Science of the total environment.

[41]  V. Singh,et al.  Mapping Groundwater Potential Using a Novel Hybrid Intelligence Approach , 2018, Water Resources Management.

[42]  Alireza Arabameri,et al.  GIS-based groundwater potential mapping in Shahroud plain, Iran. A comparison among statistical (bivariate and multivariate), data mining and MCDM approaches. , 2019, The Science of the total environment.

[43]  Halil Ibrahim Erdal,et al.  Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms , 2013 .

[44]  Bahareh Kalantar,et al.  Groundwater potential mapping using a novel data-mining ensemble model , 2018, Hydrogeology Journal.

[45]  Dionissios T. Hristopulos,et al.  Improving kriging of groundwater level data using nonlinear normalizing transformations—a field application , 2012 .

[46]  Rim Trabelsi,et al.  Groundwater quality assessment in semi-arid regions using integrated approaches: the case of Grombalia aquifer (NE Tunisia) , 2018, Environmental Monitoring and Assessment.

[47]  James S. Famiglietti,et al.  A framework for quantifying sustainable yield under California’s Sustainable Groundwater Management Act (SGMA) , 2018, Sustainable Water Resources Management.

[48]  Wei Chen,et al.  Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. , 2018, The Science of the total environment.

[49]  Kristine Walraevens,et al.  Groundwater Overexploitation and Seawater Intrusion in Coastal Areas of Arid and Semi-Arid Regions , 2018 .

[50]  Seyed Amir Naghibi,et al.  GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran , 2015, Environmental Monitoring and Assessment.

[51]  Michelle Kooy,et al.  Inclusive development of urban water services in Jakarta: The role of groundwater , 2016 .

[52]  Biswajeet Pradhan,et al.  Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree , 2016, Landslides.

[53]  H. Bouwer.  Artificial recharge of groundwater: hydrogeology and engineering , 2002 .

[54]  Paul F. Worthington,et al.  Geophysical investigations of groundwater resources in the Kalahari Basin , 1977 .

[55]  Saro Lee,et al.  Application of a weights-of-evidence method and GIS to regional groundwater productivity potential mapping. , 2012, Journal of environmental management.

[56]  Dieu Tien Bui,et al.  Hybrid computational intelligence models for groundwater potential mapping , 2019, CATENA.

[57]  H. Pourghasemi,et al.  Application of GIS-based data driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran , 2016 .

[58]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[59]  Hamid Reza Pourghasemi,et al.  A comparison between ten advanced and soft computing models for groundwater qanat potential assessment in Iran using R and GIS , 2018, Theoretical and Applied Climatology.

[60]  C. Gokceoglu,et al.  GIS-based landslide susceptibility mapping with probabilistic likelihood ratio and spatial multi-criteria evaluation models (North of Tehran, Iran) , 2014, Arabian Journal of Geosciences.

[61]  Hazem M. Gheith,et al.  Construction of a hydrologic model for estimating Wadi runoff and groundwater recharge in the Eastern Desert, Egypt , 2002 .

[62]  Lei Shi,et al.  Potential hazards to a tunnel caused by adjacent reservoir impoundment , 2019, Bulletin of Engineering Geology and the Environment.

[63]  P. J. Chilton,et al.  Hydrogeological Characterisation And Water-Supply Potential Of Basement Aquifers In Tropical Africa , 1995 .

[64]  A. Ozdemir.  Using a binary logistic regression method and GIS for evaluating and mapping the groundwater spring potential in the Sultan Mountains (Aksehir, Turkey) , 2011 .

[65]  Matthew Rodell,et al.  GRACE‐Based Estimates of Global Groundwater Depletion , 2016 .

[66]  J. H. Rudd,et al.  Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants , 2019, PloS one.

[67]  A. Edet,et al.  Determination of potential groundwater sites using geological and geophysical techniques in the Cross River State, southeastern Nigeria , 1998 .

[68]  P. Arp,et al.  Evaluating digital terrain indices for soil wetness mapping – a Swedish case study , 2014 .

[69]  J. Cosgrove,et al.  Role of the Kazerun Fault Zone in the formation and deformation of the Zagros Fold‐Thrust Belt, Iran , 2005 .

[70]  Reuben Reyes,et al.  Groundwater Level Changes Due to Extreme Weather—An Evaluation Tool for Sustainable Water Management , 2017 .

[71]  Seyed Amir Naghibi,et al.  Application of Support Vector Machine, Random Forest, and Genetic Algorithm Optimized Random Forest Models in Groundwater Potential Mapping , 2017, Water Resources Management.

[72]  Wei Chen,et al.  Spatial prediction of groundwater potentiality using ANFIS ensembled with teaching-learning-based and biogeography-based optimization , 2019, Journal of Hydrology.

[73]  Zhenxing Zhang,et al.  Posterior assessment of reference gages for water resources management using instantaneous flow measurements. , 2018, The Science of the total environment.

[74]  Paraskevas Tsangaratos,et al.  Groundwater spring potential mapping using population-based evolutionary algorithms and data mining methods. , 2019, The Science of the total environment.

[75]  Mohamed A. Meguid,et al.  Robust ensemble learning framework for day-ahead forecasting of household based energy consumption , 2018 .

[76]  Seyed Amir Naghibi,et al.  A Comparative Assessment Between Three Machine Learning Models and Their Performance Comparison by Bivariate and Multivariate Statistical Methods in Groundwater Potential Mapping , 2015, Water Resources Management.

[77]  J. P. King,et al.  Application and evaluation of universal kriging for optimal contouring of groundwater levels , 2011 .

[78]  Matthew J. Cracknell,et al.  Lithological mapping in the Central African Copper Belt using Random Forests and clustering: Strategies for optimised results , 2019, Ore Geology Reviews.

[79]  F. Quiel,et al.  Groundwater study using remote sensing and geographic information systems (GIS) in the central highlands of Eritrea , 2006 .

[80]  Xuejiao Lv,et al.  Drivers of spatio-temporal ecological vulnerability in an arid, coal mining region in Western China , 2019, Ecological Indicators.

[81]  A. Corsini,et al.  Weight of evidence and artificial neural networks for potential groundwater spring mapping: an application to the Mt. Modino area (Northern Apennines, Italy) , 2009 .

[82]  Chenghu Zhou,et al.  Spatial prediction based on Third Law of Geography , 2018, Ann. GIS.

[83]  Sotiris B. Kotsiantis,et al.  Combining bagging, boosting, rotation forest and random subspace methods , 2011, Artificial Intelligence Review.

[84]  Qi Zhang,et al.  Development and application of an integrated surface runoff and groundwater flow model for a catchment of Lake Taihu watershed, China , 2009 .

[85]  Tien-Dat Pham,et al.  Soil Salinity Mapping Using SAR Sentinel-1 Data and Advanced Machine Learning Algorithms: A Case Study at Ben Tre Province of the Mekong River Delta (Vietnam) , 2019, Remote. Sens..

[86]  Jie Guo,et al.  Assessment of Water Sources and Mixing of Groundwater in a Coastal Mine: The Sanshandao Gold Mine, China , 2018, Mine Water and the Environment.

[87]  Frank T.-C. Tsai,et al.  A comparison study of DRASTIC methods with various objective methods for groundwater vulnerability assessment. , 2018, The Science of the total environment.

[88]  Iqbal Javed,et al.  Can the informal groundwater markets improve water use efficiency and equity? Evidence from a semi-arid region of Pakistan. , 2019, The Science of the total environment.

[89]  Saro Lee,et al.  GIS mapping of regional probabilistic groundwater potential in the area of Pohang City, Korea , 2011 .

[90]  Manabu Watanabe,et al.  ALOS PALSAR: A Pathfinder Mission for Global-Scale Monitoring of the Environment , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[91]  Se-Yeong Hamm,et al.  Assessment of the potential for groundwater contamination using the DRASTIC/EGIS technique, Cheongju area, South Korea , 1999 .

[92]  Saro Lee,et al.  An Automated Python Language-Based Tool for Creating Absence Samples in Groundwater Potential Mapping , 2019, Remote. Sens..

[93]  Rahim Barzegar,et al.  Mapping groundwater contamination risk of multiple aquifers using multi-model ensemble of machine learning algorithms. , 2018, The Science of the total environment.

[94]  K. Beven,et al.  Testing a physically-based flood forecasting model (TOPMODEL) for three U.K. catchments , 1984 .

[95]  John P. Bloomfield,et al.  Changes in groundwater drought associated with anthropogenic warming , 2019, Hydrology and Earth System Sciences.

[96]  W. Tobler.  On the First Law of Geography: A Reply , 2004 .

[97]  Hugo A. Loáiciga,et al.  Groundwater fluxes in the global hydrologic cycle: past, present and future , 1993 .

[98]  F. D. Whisler,et al.  Steady state water flow in a saturated inclined soil slab , 1965 .

[99]  V. Sugumaran,et al.  Comparative study of decision tree classifier and best first tree classifier for fault diagnosis of automobile hydraulic brake system using statistical features , 2013 .

[100]  Omid Rahmati,et al.  Applicability of generalized additive model in groundwater potential modelling and comparison its performance by bivariate statistical methods , 2017 .

[101]  Diana M. Allen,et al.  Groundwater sustainability strategies , 2010 .

[102]  K. Adjei,et al.  Hydrogeological delineation of groundwater potential zones in the Nabogo basin, Ghana , 2018, Journal of African Earth Sciences.

[103]  E. Carranza,et al.  Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of Random Forests algorithm , 2015 .

[104]  Omid Rahmati,et al.  Delineation of groundwater potential zones using remote sensing and GIS-based data-driven models , 2016 .

[105]  Bahareh Kalantar,et al.  Application of rotation forest with decision trees as base classifier and a novel ensemble model in spatial modeling of groundwater potential , 2019, Environmental Monitoring and Assessment.

[106]  N. Lambrakis,et al.  Optimization of the DRASTIC method for groundwater vulnerability assessment via the use of simple statistical methods and GIS , 2006 .