Advertisement

Hydrogeology Journal

, Volume 27, Issue 7, pp 2511–2534 | Cite as

Optimization of an adaptive neuro-fuzzy inference system for groundwater potential mapping

  • Seyed Vahid Razavi Termeh
  • Khabat Khosravi
  • Majid SartajEmail author
  • Saskia Deborah Keesstra
  • Frank T.-C. Tsai
  • Roel Dijksma
  • Binh Thai PhamEmail author
Paper

Abstract

The main goal of this study was to optimize an adaptive neuro-fuzzy inference system (ANFIS) using three meta-heuristic optimization algorithms—genetic algorithm (GA), biogeography-based optimization (BBO) and simulated annealing (SA)—to prepare groundwater potential maps. The methodology was applied to the Booshehr plain, Iran. The results of optimized models were compared with ANFIS individually and three bivariate models: frequency ratio (FR), evidential belief function (EBF), and the entropy model. First, 339 wells with groundwater yield higher than 11 m3/h were selected and randomly divided into two groups. In all, 238 wells (70%) were used for training the models and 101 wells (30%) were used for testing and validating the models. Fifteen conditioning factors were selected as input parameters for the modeling. The accuracy of the groundwater potential maps for the study area was determined using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation of error (SD), as well as the area under the receiver operating characteristic (ROC) curve (AUC). Overall, the results demonstrated that ANFIS-GA had the highest prediction capability (AUC = 0.915) for groundwater potential mapping followed by ANFIS-BBO (0.903), entropy (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) and EBF (0.80). According to the entropy model, land-use, soil order and rainfall factors had the highest impact on groundwater potential in the study area. The results of this research show that the ANFIS models combined with meta-heuristic optimization algorithms can be a useful decision-making tool for assessment and management of groundwater resources.

Keywords

Groundwater management Groundwater potential mapping Bivariate models Optimization Iran 

Optimisation d’un système d’inférence de type neurone et logique floue pour cartographier le potentiel des eaux souterraines

Résumé

L’objectif principal de cette étude et d’optimiser un système d’inférence de type neurone et logique floue adaptif (ANFIS) utilisant des algorithmes d’optimisation méta-heuristiques—algorithme génétique (GA), optimisation basée sur la biogéographie (BBO) et recuit simulé (SA)—pour préparer des cartes de potentiel en eau souterraine. La méthode a été appliquée sur la plaine de Booshehr en Iran. Les résultats de modèles optimisés ont été comparés à l’ANFIS de manière individuelle et à trois modèles bivariés: le rapport de fréquence (FR), la fonction de preuve évidente (EBF) et un modèle d’entropie. D’abord, 339 puits avec des rendements de plus de 11 m3/h ont été sélectionnés et divisés de manière aléatoire en deux groupes. 238 puits ont été utilisés pour la phase d’apprentissage du modèle et 101 puits (30%) pour les phases de test et de validation. Quinze facteurs de conditions ont été sélectionnés comme paramètres d’entrée pour la modélisation. La précision des cartes de potentialité en eau souterraine pour le site d’étude a été déterminée par la racine de l’erreur quadratique moyenne (RMSE), l’erreur absolue moyenne (MAE), l’erreur sur la moyenne absolue du pourcentage (MAPE) et l’erreur de la déviation standard (SD), ainsi que sur l’aire sous la fonction d’efficacité du récepteur (ROC) ou courbe (AUC). Dans l’ensemble, les résultats montrent que le ANFIS-GA a la meilleure capacité de prédiction (AUC = 0.915) pour cartographier le potentiel en eau souterraine suivi par le ANFIS-BBO (0.903), l’entropie (0.862), le FR (0.86), le ANFIS-le SA (0.83), l’ANFIS (0.82) et l’EBF (0.80). Selon le modèle d’entropie, l’utilisation des sols, les facteurs d’ordre des sols et précipitations ont les plus forts impacts sur le potentiel en eau souterraine pour le site étudié. Les résultats de cette recherche montrent que le modèle ANFIS combiné avec des algorithmes d’optimisation méta-heuristiques peuvent être des outils de prise de décisions utiles pour l’évaluation et la gestion des ressources en eaux souterraines.

Optimización de un sistema de inferencia neuro-fuzzy adaptable para el mapeo del potencial de aguas subterráneas

Resumen

El objetivo principal de este estudio es optimizar un sistema de inferencia neuro-fuzzy adaptativo (ANFIS) usando tres algoritmos de optimización meta-heurística (algoritmo genético (GA), optimización basada en biogeografía (BBO) y recocido simulado (SA)) para preparar mapas de potencial de aguas subterráneas. La metodología se aplicó en la llanura de Booshehr, Irán. Los resultados de los modelos optimizados se compararon con ANFIS individualmente y con tres modelos bivariados: el cociente de frecuencias (FR), la función de creencia probatoria (EBF) y el modelo de entropía. En primer lugar, se seleccionaron 339 pozos con un rendimiento de agua subterránea superior a 11 m3/h y se dividieron aleatoriamente en dos grupos. Se utilizaron 238 pozos (70%) para la capacitación de los modelos y 101 pozos (30%) para probar y validar los modelos. Se seleccionaron quince factores condicionantes como parámetros de entrada para el modelado. La exactitud de los mapas de potencial de agua subterránea para el área de estudio se determinó usando el error cuadrado medio de la raíz (RMSE), el error absoluto medio (MAE), el error porcentual absoluto medio (MAPE) y la desviación estándar del error (SD), así como el área bajo la curva de la característica (AUC) de operación del receptor (ROC). En general, los resultados demostraron que ANFIS-GA tenía la mayor capacidad de predicción (AUC = 0.915) para el mapeo del potencial de aguas subterráneas, seguido por ANFIS-BBO (0.903), entropía (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) y EBF (0.80). De acuerdo con el modelo de entropía, el uso de la tierra, el orden del suelo y los factores de precipitación tuvieron el mayor impacto en el potencial del agua subterránea en el área de estudio. Los resultados de esta investigación muestran que los modelos ANFIS combinados con algoritmos de optimización meta-heurística pueden ser una herramienta útil para la toma de decisiones en la evaluación y gestión de los recursos hídricos subterráneos.

地下水潜力图绘制的自适应神经模糊推理系统优化

摘要

本研究的主要目的是使用三种元启发式优化算法(遗传算法(GA),基于生物地理学的优化(BBO)和模拟退火(SA))来优化自适应神经模糊推理系统(ANFIS)以绘制地下水潜力区。该方法应用于伊朗的Booshehr平原。优化模型的结果与单独的ANFIS和三个双变量模型(频率比(FR),证据信念函数(EBF)和熵模型)进行了比较。首先,选择了地下水出水量高于11 m3/h的339口井,将其随机分为两组。 238孔(70%)用于模型训练,101孔(30%)用于模型测试和验证。选择15个调节因子作为建模的输入参数。使用均方根误差(RMSE),平均绝对误差(MAE),平均绝对百分误差(MAPE)和误差的标准偏差(SD),以及接收器操作特性(ROC)曲线的面积(AUC),来量化研究区地下水潜力图的准确度。总体而言,结果表明ANFIS-GA具有最高的地下水潜力预测能力(AUC = 0.915),其次是ANFIS-BBO(0.903),熵(0.862),FR(0.86),ANFIS-SA(0.83),ANFIS (0.82)和EBF(0.80)。根据熵模型,土地利用,土壤顺序和降雨因子对研究区地下水潜力制图的影响最大。研究结果表明,ANFIS模型结合元启发式优化算法可以成为评估和管理地下水资源的有用决策工具。

Otimização de um sistema de inferência adaptativo neuro-fuzzy para o mapeamento do potencial das águas subterrâneas

Resumo

O principal objetivo deste estudo foi otimizar um sistema de inferência adaptativa neuro-fuzzy (SIANF) usando três algoritmos de otimização meta-heurística (algoritmo genético (AG), otimização baseada em biogeografia (OBB) e simulação annealing (SA)) para mapear o potencial da águas subterrâneas. A metodologia foi aplicada na planície de Booshehr, no Irã. Os resultados dos modelos otimizados foram comparados com o SIANF individualmente e três modelos bivariados: razão de frequência (RF), função de crença evidencial (FCE) e o modelo de entropia. Primeiramente, 339 poços com produção de água subterrânea superior a 11 m3/h foram selecionados e divididos aleatoriamente em dois grupos. Foram utilizados 238 poços (70%) para treinamento dos modelos e 101 poços (30%) para testar e validar os modelos. Quinze fatores condicionantes foram selecionados como parâmetros de entrada para a modelagem. A precisão dos mapas de potencial das águas subterrâneas para a área de estudo foi determinada usando o erro médio quadrático (EMQ), erro absoluto médio (EAM), erro percentual absoluto médio (EPAM) e desvio-padrão do erro (DPE), bem como a área sob a curva característica de operação do receptor (CCOR). No geral, os resultados demonstraram que SIANF-AG teve a maior capacidade de predição (CCOR = 0.915) para mapeamento do potencial das águas subterrâneas seguido por SIANF-OBB (0.903), entropia (0.862), RF (0.86), SIANF-SA (0.83), SIANF (0.82) e FCE (0.80). De acordo com o modelo de entropia, o uso da terra, a ordem do solo e os fatores de precipitação tiveram o maior impacto no potencial das águas subterrâneas na área de estudo. Os resultados desta pesquisa mostram que os modelos SIANF combinados com algoritmos de otimização meta-heurística podem ser uma ferramenta útil de tomada de decisão para avaliação e gerenciamento de recursos hídricos subterrâneos.

References

  1. Adiat K, Nawawi M, Abdullah K (2012) Assessing the accuracy of GIS-based elementary multi criteria decision analysis as a spatial prediction tool: a case of predicting potential zones of sustainable groundwater resources. J Hydrol 440:75–89Google Scholar
  2. Aghdam IN, Varzandeh MHM, Pradhan B (2016) Landslide susceptibility mapping using an ensemble statistical index (Wi) and adaptive neuro-fuzzy inference system (ANFIS) model at Alborz Mountains (Iran). Environ Earth Sci 75:553Google Scholar
  3. Akgun A (2012) A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at İzmir, Turkey. Landslides 9:93–106Google Scholar
  4. Al-Abadi AM, Al-Temmeme AA, Al-Ghanimy MA (2016) A GIS-based combining of frequency ratio and index of entropy approaches for mapping groundwater availability zones at Badra-Al Al-Gharbi-Teeb areas, Iraq. Sustain Water Resour Manag 2:265–283Google Scholar
  5. Althuwaynee OF, Pradhan B, Park H-J, Lee JH (2014) A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping. Catena 114:21–36Google Scholar
  6. Arabgol R, Sartaj M, Asghari K (2016) Predicting nitrate concentration and its spatial distribution in groundwater resources using support vector machines (SVMs) model. Environ Model Assess 21:71–82Google Scholar
  7. Ayalew L, Yamagishi H (2005) The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, central Japan. Geomorphology 65:15–31Google Scholar
  8. Ayazi MH, Pirasteh S, Arvin A, Pradhan B, Nikouravan B, Mansor S (2010) Disasters and risk reduction in groundwater: Zagros Mountain Southwest Iran using geoinformatics techniques. Disaster Adv 3:51–57Google Scholar
  9. Brown EC, Sumichrast RT (2005) Evaluating performance advantages of grouping genetic algorithms. Eng Appl Artif Intell 18:1–12Google Scholar
  10. Bui DT, Pradhan B, Lofman O, Revhaug I, Dick OB (2012) Landslide susceptibility mapping at Hoa Binh Province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS. Comput Geosci 45:199–211Google Scholar
  11. Bui DT, Tuan TA, Klempe H, Pradhan B, Revhaug I (2016a) 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. Landslides 13:361–378Google Scholar
  12. Bui DT, Pradhan B, Nampak H, Bui Q-T, Tran Q-A, Nguyen Q-P (2016b) Hybrid artificial intelligence approach based on neural fuzzy inference model and metaheuristic optimization for flood susceptibility modeling in a high-frequency tropical cyclone area using GIS. J Hydrol 540:317–330Google Scholar
  13. Chang F-J, Tsai M-J (2016) A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques. J Hydrol 535:256–269Google Scholar
  14. Chen W, Panahi M, Pourghasemi HR (2017) Performance evaluation of GIS-based new ensemble data mining techniques of adaptive neuro-fuzzy inference system (ANFIS) with genetic algorithm (GA), differential evolution (DE), and particle swarm optimization (PSO) for landslide spatial modelling. CATENA 157:310–324Google Scholar
  15. Chen W, Panahi M, Khosravi K, Pourghasemi HR, Rezaie F, Parvinnezhad D (2019) Spatial prediction of groundwater potentiality using ANFIS ensembled with teaching-learning-based and biogeography-based optimization. J Hydrol 572:435–448Google Scholar
  16. Chenini I, Mammou AB, El May M (2010) Groundwater recharge zone mapping using GIS-based multi-criteria analysis: a case study in central Tunisia (Maknassy Basin). Water Resour Manag 24:921–939Google Scholar
  17. Czech ZJ (2001) Three parallel algorithms for simulated annealing. PPAM 2003, Lecture Notes in Computer Science, vol 3019, Springer, Heidelberg, Germany, pp 210–217Google Scholar
  18. Dempster AP (1968) A generalization of Bayesian inference. J R Stat Soc Ser B Methodol 30:205–232Google Scholar
  19. Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30Google Scholar
  20. Dinesh Kumar P, Gopinath G, Seralathan P (2007) Application of remote sensing and GIS for the demarcation of groundwater potential zones of a river basin in Kerala, southwest coast of India. Int J Remote Sens 28:5583–5601Google Scholar
  21. Du D, Simon D, Ergezer M (2009) Biogeography-based optimization combined with evolutionary strategy and immigration refusal. SMC’09 Proceedings of the 2009 IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, October 2009, pp 997–1002Google Scholar
  22. Ganapuram S, Kumar GV, Krishna IM, Kahya E, Demirel MC (2009) Mapping of groundwater potential zones in the Musi basin using remote sensing data and GIS. Adv Eng Softw 40:506–518Google Scholar
  23. Gao J, Gen M, Sun L, Zhao X (2007) A hybrid of genetic algorithm and bottleneck shifting for multiobjective flexible job shop scheduling problems. Comput Ind Eng 53:149–162Google Scholar
  24. Ghajar I, Najafi A, Ali Torabi S, Khamehchiyan M, Boston K (2012) An adaptive network-based fuzzy inference system for rock share estimation in forest road construction. Croatian J Forest Eng 33:313–328Google Scholar
  25. Goldberg D (1989) Genetic algorithms in optimization, search and machine learning. Addison-Wesley, Reading, UKGoogle Scholar
  26. GSI (Geology Survey of Iran) (1997) Website. http://gsi.ir/en. Accessed July 2019
  27. Güçlü YS, Şen Z (2016) Hydrograph estimation with fuzzy chain model. J Hydrol 538:587–597Google Scholar
  28. Haznedar B, Kalinli A (2018) Training ANFIS structure using simulated annealing algorithm for dynamic systems identification. Neurocomputing 302:66–74Google Scholar
  29. Hong H, Panahi M, Shirzadi A, Ma T, Liu J, Zhu A-X, Chen W, Kougias I, Kazakis N (2018) Flood susceptibility assessment in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution. Sci Total Environ 621:1124–1141Google Scholar
  30. Jaafari A, Panahi M, Pham BT, Shahabi H, Bui DT, Rezaie F, Lee S (2019) Meta optimization of an adaptive neuro-fuzzy inference system with grey wolf optimizer and biogeography-based optimization algorithms for spatial prediction of landslide susceptibility. Catena 175:430–445Google Scholar
  31. Jang J-S (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybernet 23:665–685Google Scholar
  32. Kalai AT, Vempala S (2006) Simulated annealing for convex optimization. Math Oper Res 31:253–266Google Scholar
  33. Kennison RF, Cox J (2013) Health and functional limitations predict depression scores in the health and retirement study: results straight from MARS. Cal J Health Promotion 11(1):97Google Scholar
  34. Khosravi K, Nohani E, Maroufinia E, Pourghasemi HR (2016a) A GIS-based flood susceptibility assessment and its mapping in Iran: a comparison between frequency ratio and weights-of-evidence bivariate statistical models with multi-criteria decision-making technique. Nat Hazards 83:947–987Google Scholar
  35. Khosravi K, Pourghasemi HR, Chapi K, Bahri M (2016b) Flash flood susceptibility analysis and its mapping using different bivariate models in Iran: a comparison between Shannon’s entropy, statistical index, and weighting factor models. Environ Monit Assess 188:656Google Scholar
  36. Khosravi K, Panahi M, Tien Bui D (2018a) Spatial prediction of groundwater spring potential mapping based on adaptive neuro-fuzzy inference system and metaheuristic optimization. Hydrol Earth Syst Sci 22:4771–4792Google Scholar
  37. Khosravi K, Sartaj M, Tsai FT-C, Singh VP, Kazakis N, Melesse AM, Prakash I, Bui DT, Pham BT (2018b) A comparison study of DRASTIC methods with various objective methods for groundwater vulnerability assessment. Sci Total Environ 642:1032–1049Google Scholar
  38. Khosravi K, Shahabi H, Pham BT, Adamawoski J, Shirzadi A, Pradhan B, Dou J, Ly H-B, Gróf G, Ho HL (2019) A comparative assessment of flood susceptibility modeling using multi-criteria decision-making analysis and machine learning methods. J Hydrol 573:311–323Google Scholar
  39. Kia MB, Pirasteh S, Pradhan B, Mahmud AR, Sulaiman WNA, Moradi A (2012) An artificial neural network model for flood simulation using GIS: Johor River basin, Malaysia. Environ Earth Sci 67:251–264Google Scholar
  40. Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220:671-680Google Scholar
  41. Kordestani MD, Naghibi SA, Hashemi H, Ahmadi K, Kalantar B, Pradhan B (2019) Groundwater potential mapping using a novel data-mining ensemble model. Hydrogeol J 27:211–224Google Scholar
  42. Leardi R (2003) Nature-inspired methods in chemometrics: genetic algorithms and artificial neural networks. Elsevier, AmsterdamGoogle Scholar
  43. Lee S, Song K, Kim Y, Park I (2012) Regional groundwater productivity potential mapping using a geographic information system (GIS) based artificial neural network model. Hydrogeol J 20(8):1511–1527Google Scholar
  44. Lohani A, Kumar R, Singh R (2012) Hydrological time series modeling: a comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. J Hydrol 442:23–35Google Scholar
  45. Mahalingam B, Vinay M (2015) Identification of ground water potential zones using GIS and remote sensing techniques: a case study of Mysore Taluk-Karnataka. Int J Geomat Geosci 5:393Google Scholar
  46. Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing machines. J Chem Phys 21:1087–1092Google Scholar
  47. Moore I, Burch G (1986) Sediment transport capacity of sheet and rill flow: application of unit stream power theory. Water Resour Res 22:1350–1360Google Scholar
  48. Moore ID, Grayson R, Ladson A (1991) Digital terrain modelling: a review of hydrological, geomorphological, and biological applications. Hydrol Process 5:3–30Google Scholar
  49. Naghibi SA, Dashtpagerdi MM (2017) Evaluation of four supervised learning methods for groundwater spring potential mapping in Khalkhal region (Iran) using GIS-based features. Hydrogeol J 25:169–189Google Scholar
  50. Naghibi SA, Pourghasemi HR, Pourtaghi ZS, Rezaei A (2015) Groundwater qanat potential mapping using frequency ratio and Shannon’s entropy models in the Moghan watershed, Iran. Earth Sci Inf 8:171–186Google Scholar
  51. Naghibi SA, Pourghasemi HR, Dixon B (2016) GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran. Environ Monit Assess 188:44Google Scholar
  52. Naghibi SA, Moghaddam DD, Kalantar B, Pradhan B, Kisi O (2017) A comparative assessment of GIS-based data mining models and a novel ensemble model in groundwater well potential mapping. J Hydrol 548:471–483Google Scholar
  53. Naghibi SA, Pourghasemi HR, Abbaspour K (2018) A comparison between ten advanced and soft computing models for groundwater qanat potential assessment in Iran using R and GIS. Theor Appl Climatol 131:967–984Google Scholar
  54. Nampak H, Pradhan B, Manap MA (2014) Application of GIS based data driven evidential belief function model to predict groundwater potential zonation. J Hydrol 513:283–300Google Scholar
  55. Oh H-J, Kim Y-S, Choi J-K, Park E, Lee S (2011) GIS mapping of regional probabilistic groundwater potential in the area of Pohang City, Korea. J Hydrol 399:158–172Google Scholar
  56. Ozdemir A (2011) GIS-based groundwater spring potential mapping in the Sultan Mountains (Konya, Turkey) using frequency ratio, weights of evidence and logistic regression methods and their comparison. J Hydrol 411:290–308Google Scholar
  57. Pham BT, Bui DT, Prakash I, Dholakia M (2016) Rotation forest fuzzy rule-based classifier ensemble for spatial prediction of landslides using GIS. Nat Hazards 83:97–127Google Scholar
  58. Pham BT, Bui DT, Prakash I, Dholakia M (2017) Hybrid integration of multilayer perceptron neural networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS. Catena 149:52–63Google Scholar
  59. Pourghasemi HR, Beheshtirad M (2015) Assessment of a data-driven evidential belief function model and GIS for groundwater potential mapping in the Koohrang watershed, Iran. Geocarto Int 30:662–685Google Scholar
  60. Pourghasemi HR, Mohammady M, Pradhan B (2012) Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood Basin, Iran. Catena 97:71–84Google Scholar
  61. Pourghasemi HR, Jirandeh AG, Pradhan B, Xu C, Gokceoglu C (2013) Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province, Iran. J Earth Syst Sci 122:349–369Google Scholar
  62. Pourtaghi ZS, Pourghasemi HR (2014) GIS-based groundwater spring potential assessment and mapping in the Birjand township, southern Khorasan Province, Iran. Hydrogeol J 22:643–662Google Scholar
  63. Rahmati O, Samani AN, Mahdavi M, Pourghasemi HR, Zeinivand H (2015) Groundwater potential mapping at Kurdistan region of Iran using analytic hierarchy process and GIS. Arab J Geosci 8:7059–7071Google Scholar
  64. Rao NS, Chakradhar G, Srinivas V (2001) Identification of groundwater potential zones using remote sensing techniques in and around Guntur town, Andhra Pradesh, India. J Indian Soc Remote Sens 29:69Google Scholar
  65. Regmi AD, Devkota KC, Yoshida K, Pradhan B, Pourghasemi HR, Kumamoto T, Akgun A (2014) Application of frequency ratio, statistical index, and weights-of-evidence models and their comparison in landslide susceptibility mapping in Central Nepal Himalaya. Arab J Geosci 7:725–742Google Scholar
  66. Sangchini EK, Emami SN, Tahmasebipour N, Pourghasemi HR, Naghibi SA, Arami SA, Pradhan B (2016) Assessment and comparison of combined bivariate and AHP models with logistic regression for landslide susceptibility mapping in the Chaharmahal-e-Bakhtiari Province, Iran. Arab J Geosci 9:201Google Scholar
  67. Sheta A, Turabieh H (2006) A comparison between genetic algorithms and sequential quadratic programming in solving constrained optimization problems. ICGST Int J Artif Intell Mach Learn (AIML) 6:67–74Google Scholar
  68. Sharafati A, Khosravi K, Khosravinia P, Ahmad K, Salman S, Yaseen Z (2019) The potential of novel data mining models for global solar radiation prediction. Int J Environ Sci Tech.  https://doi.org/10.1007/s13762-019-02344-0 Google Scholar
  69. Shiklomanov I, Rodda J (2003) World water resources at the beginning of the 21st century. Cambridge and UNESCO International Hydrology Series, UNESCO, ParisGoogle Scholar
  70. Shu C, Ouarda T (2008) Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. J Hydrol 349:31–43Google Scholar
  71. Simon D (2008) Biogeography-based optimization. IEEE Trans Evol Comput 12:702–713Google Scholar
  72. Singh AK, Prakash SR (2002) An integrated approach of remote sensing, geophysics and GIS to evaluation of groundwater potentiality of Ojhala sub-watershed, Mirjapur district, UP, India. Asian conference on GIS, GPS, Aerial Photography and Remote Sensing, Bangkok, Thailand, August, 2002Google Scholar
  73. Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modelling and control, proceedings, SMC-15. IEEE Trans Syst Man Cybernet 1:116–132Google Scholar
  74. Talebi A, Uijlenhoet R, Troch P (2007) Soil moisture storage and hillslope stability. Nat Hazards Earth Syst Sci 7:523–534Google Scholar
  75. Tehrany MS, Pradhan B, Jebur MN (2015a) Flood susceptibility analysis and its verification using a novel ensemble support vector machine and frequency ratio method. Stoch Env Res Risk A 29:1149–1165Google Scholar
  76. Tehrany MS, Pradhan B, Mansor S, Ahmad N (2015b) Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. Catena 125:91–101Google Scholar
  77. Termeh SVR, Kornejady A, Pourghasemi HR, Keesstra S (2018) Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. Sci Total Environ 615:438–451Google Scholar
  78. Tien Bui D, Khosravi K, Li S, Shahabi H, Panahi M, Singh V, Chapi K, Shirzadi A, Panahi S, Chen W (2018a) New hybrids of anfis with several optimization algorithms for flood susceptibility modeling. Water 10:1210Google Scholar
  79. Tien Bui D, Panahi M, Shahabi H, Singh VP, Shirzadi A, Chapi K, Khosravi K, Chen W, Panahi S, Li S (2018b) Novel hybrid evolutionary algorithms for spatial prediction of floods. Sci Rep 8:15364Google Scholar
  80. Todd DK, Mays LW (1980) Groundwater hydrology, 3rd edn. Wiley, Chichester, UKGoogle Scholar
  81. UNWWDR (2006) Water: a shared responsibility. United Nations World Water Development report 2. UNESCO, ParisGoogle Scholar
  82. UNWWDR (2015) Water for a sustainable world. United Nations World Water Development report. UNESCO, ParisGoogle Scholar
  83. Wuest T, Weimer D, Irgens C, Thoben K-D (2016) Machine learning in manufacturing: advantages, challenges, and applications. Prod Manufact Res 4:23–45Google Scholar
  84. Xu C, Xu X, Dai F, Xiao J, Tan X, Yuan R (2012) Landslide hazard mapping using GIS and weight of evidence model in Qingshui River watershed of 2008 Wenchuan earthquake struck region. J Earth Sci 23:97–120Google Scholar
  85. Yang K, Trewn J (2004) Multivariate statistical methods in quality management McGraw-Hill, New YorkGoogle Scholar
  86. Yesilnacar E, Topal T (2005) Landslide susceptibility mapping: a comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey). Eng Geol 79:251–266Google Scholar
  87. Zandi J, Ghazvinei PT, Hashim R, Yusof KBW, Ariffin J, Motamedi S (2016) Mapping of regional potential groundwater springs using logistic regression statistical method. Water Resour 43:48–57Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Seyed Vahid Razavi Termeh
    • 1
  • Khabat Khosravi
    • 2
  • Majid Sartaj
    • 3
    Email author
  • Saskia Deborah Keesstra
    • 4
    • 5
  • Frank T.-C. Tsai
    • 6
  • Roel Dijksma
    • 7
  • Binh Thai Pham
    • 8
    Email author
  1. 1.Faculty of Geodesy & Geomatics EngineeringK.N. Toosi University of TechnologyTehranIran
  2. 2.Department of Watershed Management Engineering, Faculty of Natural ResourcesSari Agricultural Science and Natural Resources University (SANRU)SariIran
  3. 3.Civil Engineering DepartmentUniversity of OttawaOttawaCanada
  4. 4.Soil Physics and Land Management GroupWageningen UniversityWageningenNetherlands
  5. 5.Civil, Surveying and Environmental EngineeringThe University of NewcastleCallaghanAustralia
  6. 6.Department of Civil and Environmental EngineeringLouisiana State UniversityBaton RougeUSA
  7. 7.Department of Hydrology and Quantitative Water ManagementWageningen UniversityWageningenNetherlands
  8. 8.Institute of Research and DevelopmentDuy Tan UniversityDa NangVietnam

Personalised recommendations