Abstract
Spring discharge always illustrates the groundwater-flux and aquifer storage oscillations. Because of inherent heterogeneity in karst environments, it is essential to mimic karst spring flows to acquire a superior understanding of hydrological processes and provide sustainable management and protection of karst waters. The framework of karst media is nonlinear and complex, which can be demonstrated by data-driven models. In this study, the performance of Support Vector Regression (SVR), the Adaptive Neuro-Fuzzy Inference System (ANFIS), and Artificial Neural Networks (ANN) was assessed to predict spring discharge 1-, 3-, 7-, 10- and 14-day ahead. A hybrid Gamma Test-Genetic Algorithm was performed to establish an optimal input combination. SVR, ANFIS, and ANN performances were analyzed via four residuals: Correlation Coefficient, Mean Absolute Error, Root Mean Squared Error (RMSE), Nash–Sutcliffe Efficiency, and Developed Discrepancy Ratio. According to the RMSE values (of 0.08, 0.18, 0.64 and 0.86 using ANN; 0.19, 0.22, 0.83, and 0.61 using ANFIS; and 0.15, 0.26, 0.78 and 0.59 using SVR for Lordegan, Deime, Dehcheshmeh, and Dehghara springs, respectively), the results demonstrated that ANN was highly accurate for the discharge prediction of the Lordegan, Deime, and Dehcheshme springs whereas it had the least accuracy for the discharge prediction of the Dehghara spring up to 14-day ahead. However, SVR performed better than the other models for all prediction steps in the Dehghara spring, having a more complex and heterogeneous flow system compared to the others. For all the springs, the models’ accuracy decreased as the time ahead increased.
This is a preview of subscription content, log in via an institution to check access.
Availability of Data and Material
The data can be downloaded in Harvard Dataverse, V1. https://doi.org/10.7910/DVN/GTMRLH, UNF:6:XtSM5JzdOJKUnfH9upk/HA== [fileUNF] (Mirarabi 2020).
Code Availability
The codes used in this work are available from the corresponding author by request.
Abbreviations
- ANFIS:
-
Adaptive neuro-fuzzy inference system
- ANFIS-SC:
-
Adaptive neuro-fuzzy inference system subtractive clustering
- ANN:
-
Artificial neural networks
- DDR:
-
Developed discrepancy ratio
- FIS:
-
Fuzzy inference system
- GA:
-
Genetic algorithm
- GT:
-
Gamma test
- LM:
-
Levenberg–Marquardt
- MAE:
-
Mean absolute error
- NSE:
-
Nash–Sutcliffe efficiency
- P:
-
Precipitation
- PCA:
-
Principal components analysis
- Q:
-
Spring discharge
- R:
-
Correlation coefficient
- RBF:
-
Radial basis function
- RMSE:
-
Root mean squared error
- SVR:
-
Support vector machine regression
References
Ahmed JA, Sarma AK (2005) Genetic algorithm for optimal operating policy of a multipurpose reservoir. Water Resour Manage 19:145–161. https://doi.org/10.1007/s11269-005-2704-7
Azadi S, Amiri H, Ataei P, Javadpour S (2020) Optimal design of groundwater monitoring networks using gamma test theory. Hydrogeol J 28:1389–1402. https://doi.org/10.1007/s10040-020-02115-z
Barfield B, Felton G, Stevens E, McCann M (2004) A simple model of karst spring flow using modified NRCS procedures. J Hydrol 287:34–48. https://doi.org/10.1016/j.jhydrol.2003.09.031
Bastani M, Kholghi M, Rakhshandehroo GR (2010) Inverse modeling of variabledensity groundwater flow in a semi-arid area in Iran using a genetic algorithm. Hydrogeol J 18:1191–1203
Bonacci O (1992) Karst springs hydrographs as indicators of karst aquifers. Hydrol Sci J 38:51–62. https://doi.org/10.1080/02626669309492639
Chaharmahal Bakhtiari Water Resource Authority (2006) The report of water features of the province, the water resource basic study office
Chen L, Sun C, Wang G, Xie H, Shen Z (2017) Modeling multi-event non-point source pollution in a data-scarce catchment using ANN and entropy analysis. Entropy 19:265–283. https://doi.org/10.3390/e19060265
Cheng S, Qiao X, Shi Y, Wang D (2021) Machine learning for predicting discharge fluctuation of a karst spring in North China. Acta Geophys 69:257–270. https://doi.org/10.1007/s11600-020-00522-0
Cherkassky V, Ma Y (2004) Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw 17:113–126
Choubin B, Malekian A (2017) Combined gamma and M-test-based ANN and ARIMA models for groundwater fluctuation forecasting in semiarid regions. Environ Earth Sci 76:538. https://doi.org/10.1007/s12665-017-6870-8
Coulibaly P, Anctil F, Bobee B (2000) Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. J Hydrol 230:244–257. https://doi.org/10.1016/S0022-1694(00)00214-6
De Rooij R, Perrochet P, Graham W (2013) From rainfall to spring discharge: Coupling conduit flow, subsurface matrix flow and surface flow in karst systems using a discrete-continuum model. Adv Water Resour 61:29–41. https://doi.org/10.1016/j.advwatres.2013.08.009
Durrant PJ (2001) winGamma: a non-linear data analysis and modeling tool with applications to flood prediction. Dissertation, Cardiff University Wales UK
Evans D, Jones AJ (2002) A proof of the Gamma test. In Proceedings of the Royal Society of London 458:2759–2799. https://www.jstor.org/stable/3560031
Ford D, Williams PD (2013) Karst hydrogeology and geomorphology. John Wiley and Sons, Chichester
Gill LW, Schuler P, Duran L, Morrissey P, Johnston PM (2021) An evaluation of semi distributed-pipe-network and distributed-finite-difference models to simulate karst systems. Hydrogeol J 29:259–279. https://doi.org/10.1007/s10040-020-02241-8
Ghavidel SZZ, Montaseri M (2014) Application of different data-driven methods for the prediction of total dissolved solids in the Zarinehroud basin. Stoch Environ Res Risk Assess 28:2101–2118. https://doi.org/10.1007/s00477-014-0899-y
Gholami V, Khaleghi MR (2019) A comparative study of the performance of artificial neural network and multivariate regression in simulating springs discharge in the Caspian Southern Watersheds. Iran Appl Water Sci 9:9. https://doi.org/10.1007/s13201-018-0886-4
Ghorbani MA, Zadeh H, Isazadeh M, Terzi O (2016) A comparative study of artificial neural network (MLP RBF) and support vector machine models for river flow prediction. Environ Earth Sci 75:476. https://doi.org/10.1007/s12665-015-5096-x
Han D, Chan L, Zhu N (2007) Flood forecasting using support vector machines. J Hydroinformatics 9:267–276. https://doi.org/10.2166/hydro.2007.027
Hao Y, Yeh TCJ, Gao Z, Wang Y, Zhao Y (2006) A gray system model for studying the response to climatic change: The Liulin karst springs, China. J Hydrol 328:668–676
Hartmann A, Goldscheider N, Wagener T, Lange J, Weiler M (2014) Karst water resources in a changing world: review of hydrological modeling approaches. Rev Geophys 52:218–242. https://doi.org/10.1002/2013rg000443
Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification. http://www.csie.ntu.edu.tw/~cjlin
Huang GB (2003) Learning capability and storage capacity of two-hidden-layer feed forward networks. Last updated: 2016. IEEE Trans Neural Netw Learn Syst 14:274–281
Hu C, Hao Y, Yeh TCJ, Pang B, Wu Z (2008) Simulation of spring flows from a karst aquifer with an artificial neural network. Hydrol Process 22:596–604. https://doi.org/10.1002/hyp.6625
Huo X, Liu Z, Duan Q, Hao P, Zhang Y, Hao Y, Zhan H (2016) Linkages between large-scale climate patterns and karst spring discharge in Northern China. J Hydrometeorol 17:713–724. https://doi.org/10.1175/JHM-D-15-0085.1
Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence [Book Review]. IEEE Trans Automat Contr 42:1482–1484. https://doi.org/10.1109/TAC.1997.633847
Kalteh AM (2015) Wavelet genetic algorithm-support vector regression (Wavelet GA-SVR) for monthly flow forecasting. Water Resour Manage 29:1283–1293. https://doi.org/10.1007/s11269-014-0873-y
Khalil B, Broda S, Adamowski J, Ozga-Zielinski B, Donohoe A (2014) Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models. Hydrogeol J 23:121–141. https://doi.org/10.1007/s10040-014-1204-3
Kisi Ö, Tombul M (2013) Modeling monthly pan evaporations using fuzzy genetic approach. J Hydrol 477:203–212. https://doi.org/10.1016/j.jhydrol.2012.11.030
Koncar N (1997) Optimisation methodologies for direct inverse neuro-control. Dissertation, University of London
Li PH, Kwon HH, Sun L, Lall U, Kao JJ (2010) A modified support vector machine based prediction model on streamflow at the Shihmen Reservoir, Taiwan. Int J Climatol 30:1256–1268
Li Z, Xu X, Liu M, Li X, Zhang R, Wang KL, Xu C (2017) State-space prediction of spring discharge in a karst catchment in southwest China. J Hydrol 549:264–276. https://doi.org/10.1016/j.jhydrol.2017.04.001
Madsen KM, Perry AE (2010) Using genetic algorithms on groundwater modeling problems in a consulting setting. In Proceedings of the Annual International Conference on Soils, Sediments, Water and Energy 15:1–11
Maiti S, Tiwari RK (2013) A comparative study of artificial neural networks Bayesian neural networks and adaptive neuro-fuzzy inference system in groundwater level prediction. Environ Earth Sci 71:3147–3160. https://doi.org/10.1007/s12665-013-2702-7
Malagò A, Efstathiou D, Bouraoui F, Nikolaidis NP, Franchini M, Bidoglio G, Kritsotakis M (2016) Regional scale hydrologic modeling of a karst-dominant geomorphology: The case study of the Island of Crete. J Hydrol 540:64–81. https://doi.org/10.1016/j.jhydrol.2016.05.061
Malik A, Bhagwat A (2021) Modelling groundwater level fluctuations in urban areas using artificial neural network. Groundw Sustain Dev. https://doi.org/10.1016/j.gsd.2020.100484
Maroufpoor S, Maroufpoor E, Bozorg-Haddad O, Shiri J, Yaseen ZM (2019) Soil moisture simulation using hybrid artificial intelligent model: Hybridization of adaptive neuro fuzzy inference system with grey wolf optimizer algorithm. J Hydrol 575:544–556. https://doi.org/10.1016/j.jhydrol.2019.05.045
Marquez R, Coimbra CF (2011) Forecasting of global and direct solar irradiance using stochastic learning methods ground experiments and the NWS database. Sol Energy 85:746–756. https://doi.org/10.1016/j.solener.2011.01.007
Meng X, Huang M, Liu D, Yin M (2021) Simulation of rainfall–runoff processes in karst catchment considering the impact of karst depression based on the tank model. Arab J Geosci 14:250. https://doi.org/10.1007/s12517-021-06515-7
Mirarabi A (2020) Replication data for: a comparative analysis of data-driven models (SVR, ANFIS, and ANNs) for daily karst spring discharge prediction. Harvard Dataverse, V1. https://doi.org/10.7910/DVN/GTMRLH, UNF:6:XtSM5JzdOJKUnfH9upk/HA== [fileUNF]
Mirarabi A, Nassery HR, Nakhaei M, Adamowski J, Akbarzadeh AH, Alijani F (2019) Evaluation of data-driven models (SVR and ANN) for groundwater-level prediction in confined and unconfined systems. Environ Earth Sci 78:489. https://doi.org/10.1007/s12665-019-8474-y
Mokhtarzad M, Eskandari F, Vanjani NJ, Arabasadi A (2017) Drought forecasting by ANN ANFIS and SVM and comparison of the models. Environ Earth Sci 76:729. https://doi.org/10.1007/s12665-017-7064-0
Montaseri M, Ghavidel SZZ, Sanikhani H (2018) Water quality variations in different climates of Iran: Toward modeling total dissolved solid using soft computing techniques. Stoch Environ Res Risk Assess 32:2253–2273. https://doi.org/10.1007/s00477-018-1554-9
Nayak PC, Sudheer KP, Rangan DM, Ramasastri KS (2004) A neuro-fuzzy computing technique for modeling hydrological time series. J Hydrol 291:52–66. https://doi.org/10.1016/j.jhydrol.2003.12.010
Noori R, Karbassi A, Sabahi MS (2009) Evaluation of PCA and Gamma test techniques on ANN operation for weekly solid waste prediction. J Environ Manage 91:767–771. https://doi.org/10.1016/j.jenvman.2009.10.007
Nourani V, Mogaddam AA, Nadiri AO (2008) An ANN-based model for spatiotemporal groundwater level forecasting. Hydrol Process 22:5054–5066. https://doi.org/10.1002/hyp.7129
Pi H, Peterson C (1994) Finding the embedding dimension and variable dependencies in time series. Neural Comput 6:509–520. https://doi.org/10.1162/neco.1994.6.3.509
Roshni T, Jha MK, Drisya J (2020) Neural network modeling for groundwater-level forecasting in coastal aquifers. Neural Comput Applic 32:12737–12754. https://doi.org/10.1007/s00521-020-04722-z
Rath JS, Hutton PH, Chen L, Roy SB (2017) A hybrid empirical-Bayesian artificial neural network model of salinity in the San Francisco Bay-Delta estuary. Environ Model Softw 93:193–208. https://doi.org/10.1016/j.envsoft.2017.03.022
Remesan R, Mathew J (2015) Hydrological data-driven modeling (a case study approach). Springer International Publishing, Switzerland
Rumelhart DE, McClelland JL, James L (1986) Parallel distribution processing: exploration in the microstructure of cognition. MIT Press, Cambridge, MA
Safavi HR, Esmikhani M (2013) Conjunctive use of surface water and groundwater: application of support vector machines (SVMs) and genetic algorithms. Water Resour Manage 27:2623–2644. https://doi.org/10.1007/s11269-013-0307-2
Sahoo S, Jha MK (2015) On the statistical forecasting of groundwater levels in unconfined aquifer systems. Environ Earth Sci 73:3119–3136. https://doi.org/10.1007/s12665-014-3608-8
Sanikhani H, Kisi Ö (2012) River flow estimation and forecasting by using two different adaptive neuro-fuzzy approaches. Water Resour Manage 26:1715–1729. https://doi.org/10.1007/s11269-012-9982-7
Shirmohammadi B, Vafakhah M, Moosavi V, Moghaddamnia A (2013) Application of several data-driven techniques for predicting groundwater level. Water Resour Manage 27:419–432. https://doi.org/10.1007/s11269-012-0194-y
Sreekanth PD, Sreedevi PD, Ahmed S, Geethanjali N (2010) Comparison of FFNN and ANFIS models for estimating groundwater level. Environ Earth Sci 62:1301–1310. https://doi.org/10.1007/s12665-010-0617-0
Stefánsson A, Končar N, Jones AJ (1997) A note on the Gamma test. Neural Comput Appl 5:131–133. https://doi.org/10.1007/BF01413858
Sujay Raghavendra N, Deka PC (2015) Forecasting monthly groundwater level fluctuations in coastal aquifers using hybrid Wavelet packet–Support vector regression. Cogent Eng 2:999414. https://doi.org/10.1080/23311916.2014.999414
Tague C, Grant GE (2004) A geological framework for interpreting the low-flow regimes of Cascade streams, Willamette River Basin, Oregon. Water Resour Res 40. https://doi.org/10.1029/2003WR002629
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans Syst Man Cybern Syst 15:116–132. https://doi.org/10.1109/TSMC.1985.6313399
Tian J, Li C, Liu J, Yu F, Cheng S, Zhao N, Jaafar W (2016) Groundwater depth prediction using data-driven models with the assistance of gamma test. Sustainability 8:1076. https://doi.org/10.3390/su8111076
Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, New York
Wei A, Li D, Dai F, Lang X, Ma B, Wang Y (2021) An optimization method coupled the index-overlay method with entropy weighting model to assess seawater intrusion vulnerability. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-021-13229-6
White WB (2002) Karst hydrology: Recent developments and open questions. Eng Geol 65:85–105. https://doi.org/10.1016/S0013-7952(01)00116-8
Yager RR, Filev DP (1994) Approximate clustering via the mountain method. IEEE Trans Syst Man Cybern Syst 24:1279–1284. https://doi.org/10.1109/21.299710
Yan Q, Ma C (2016) Application of integrated ARIMA and RBF network for groundwater level forecasting. Environ Earth Sci 75:396. https://doi.org/10.1007/s12665-015-5198-5
Zadeh LA (1973) Outline of a new approach to the analysis of complex systems and decision processes. IEEE Trans Syst Man Cybern Syst 3:28–44. https://doi.org/10.1109/TSMC.1973.5408575
Zhang YX (2007) Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis. Talanta 73:68–75. https://doi.org/10.1016/j.talanta.2007.02.030
Zounemat-Kermani M, Kisi Ö, Adamowski J, Ramezani-Charmahineh A (2016) Evaluation of data-driven models for river suspended sediment concentration modeling. J Hydrol 535:457–472. https://doi.org/10.1016/j.jhydrol.2016.02.012
Acknowledgements
We acknowledge the Water Resources Management Company that provided us with secondary data for our research work.
Funding
No funds, grants, or other support was received.
Author information
Authors and Affiliations
Contributions
Conceptualization: Akram Rahbar, Ail mirarabi; Methodology: Akram Rahbar, Ali Mirarabi; Formal analysis and investigation: Mohammad Nakhaei, Mahdi Talkhabi, Maryam Jamali; Writing—original draft preparation: Akram Rahbar, Ail mirarabi; Writing—review and editing: Mohammad Nakhaei, Mahdi Talkhabi, Maryam Jamali.
Corresponding author
Ethics declarations
Ethics Approval
Not applicable.
Consent to Participate
Not applicable.
Consent for Publication
Not applicable.
Conflicts of Interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rahbar, A., Mirarabi, A., Nakhaei, M. et al. A Comparative Analysis of Data-Driven Models (SVR, ANFIS, and ANNs) for Daily Karst Spring Discharge Prediction. Water Resour Manage 36, 589–609 (2022). https://doi.org/10.1007/s11269-021-03041-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11269-021-03041-9