Simulating groundwater level fluctuations using linear regression (SVR) and extreme learning (ELM) machine models

Document Type : Original Article

Authors

1 , Department of Water Engineering, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran.

2 Department of Water Engineering , Kermanshah Branch , Islamic Azad University, Kermanshah, Iran.

3 Department of Water Engineering, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran.

4 Depatrment of Water Engineering, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran.

5 Department of Water Engineering , Kermanshah Branch, Islamic Azad University, Kermanshah, Iran.

Abstract

Objective: In this study, two advanced machine learning methods, namely support vector machine (SVR) and extreme learning machine (ELM), are investigated for the groundwater level simulation.
 
Method: The SVR model performs well due to its ability to simulate complex and nonlinear relationships and the use of kernel functions for accurate prediction. The ELM model, with its high computational speed and structural simplicity, is suitable for processing large and complex data. In this study, 10-year data including groundwater level, precipitation, evaporation and temperature with monthly time steps were used to develop these models. All variables were normalized to the range of 0 to 1 to prevent bias in the models And RMSE, NSE and R² indices were used to evaluate the performance of the models.
 
Results: The results showed that the ELM model with polynomial activation function provided the best performance in both training and testing stages (Training: RMSE=0.1747, NSE=0.9045, R2=0.9097), (Test: RMSE=0.1675, NSE=0.9048, R2=0.9098). In contrast, the SVR model with the multi-attack kernel function showed the best accuracy in both stages (Training: RMSE=0.2246, NSE=0.8740, R2=0.9038), (Test: RMSE=0.2218, NSE=0.8758, R2=0.9048).
 
Conclusions:  The findings of this study indicate that the ELM model can be used as an effective tool in groundwater resources management. On the other hand, the poor performance of the SVR model with the linear kernel indicates its inefficiency in modeling nonlinear relationships in data from arid and semi-arid regions.

Keywords

Main Subjects

References

ملک‌زاده، مریم.، کاردار، سعید.، صائب، کیوان.، شعبانلو، سعید.، و تقوی، لعبت. (1397). پیش‏بینی تراز آب زیر زمینی با استفاده از مدل‏های مادفلو، ماشین آموزش نیرومند و ویولت-ماشین آموزش نیرومند. مجله تحقیقات منابع آب ایران، 14(5) ، 501-496. https://www. wrr.ir/article_66468.html
Afruzi, A., Zare Abyaneh, H., & Abdolabadi, H. (2021). Local strategies to manage groundwater depletion under climate change scenarios—a case study: Hamedan-Bahar Plain (Iran). Arabian Journal of Geosciences, 14(15), 1548. http://dx.doi.org/10.1007/s12517-021-07773-1
Ahmadi, A., Olyaei, M., Heydari, Z., Emami, M., Zeynolabedin, A., Ghomlaghi, A., Daccache, A., Fogg, G. E., & Sadegh, M. (2022). Groundwater level modeling with machine learning: a systematic review and meta-analysis. Water, 14(6), 949. https://doi.org/10.3390/w14060949
Ahmed, H. U., Mostafa, R. R., Mohammed, A., Sihag, P., & Qadir, A. (2023). Support vector regression (SVR) and grey wolf optimization (GWO) to predict the compressive strength of GGBFS-based geopolymer concrete. Neural Computing and Applications, 35(3), 2909-2926. https://doi.org/10.1007/s00521-022-07724-1
Alizamir, M., Kazemi, Z., Kazemi, Z., Kermani, M., Kim, S., Heddam, S., Kisi, O., & Chung, I.-M. (2023). Investigating landfill leachate and groundwater quality prediction using a robust integrated artificial intelligence model: Grey wolf metaheuristic optimization algorithm and extreme learning machine. Water, 15(13), 2453. https://doi.org/10.3390/w15132453
Aman Jalili, A., Najarchi, M., Shabanlou, S., & Jafarinia, R. (2023). Multiobjective optimization of water resources in real time based on integration of NSGA-II and support vector machines. Environ Sci Pollut Res, 30,16464–16475. https://doi.org/10.1007/s11356-022-22723-4
Amiri, S., Rajabi, A., Shabanlou, S. Yosefvand, F., & Izadbakhsh, M.A. (2023). Prediction of groundwater level variations using deep learning methods and GMS numerical model. Earth Sci Inform, 16, 3227–3241. https://doi.org/10.1007/s12145-023-01052-1
Azizi, E., Yosefvand, F., Yaghoubi, B., Izadbakhsh, M.A., & Shabanlou, S. (2023) Modelling and prediction of groundwater level using wavelet transform and machine learning methods: A case study for the Sahneh Plain, Iran. Irrigation and Drainage, 72(3), 747–762. https://doi.org/10.1002/ird.2794
Azizpour, A., Izadbakhsh, M. A., Shabanlou, S., Yosefvand, F., & Rajabi, A. (2021). Estimation of water level fluctuations in groundwater through a hybrid learning machine. Groundwater for Sustainable Development, 15, 100687. http://dx.doi.org/10.1016/j.gsd.2021.100687
Balali, H., & Kasbian Lal, F. (2022). Economic Valuation of Groundwater in Agriculture Sector (Case Study: Hamedan-Bahar Plain). Journal of Agricultural Economics and Development, 36(1), 37-48. https://doi.org/10.22067/jead.2022.72334.1079
Balogun, A.-L., Rezaie, F., Pham, Q. B., Gigović, L., Drobnjak, S., Aina, Y. A., Panahi, M., Yekeen, S. T., & Lee, S. (2021). Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms. Geoscience Frontiers, 12(3), 101104. https://doi.org/10.1016/j.gsf.2020.10.009
Band, S. S., Heggy, E., Bateni, S. M., Karami, H., Rabiee, M., Samadianfard, S., Chau, K.-W., & Mosavi, A. (2021). Groundwater level prediction in arid areas using wavelet analysis and Gaussian process regression. Engineering Applications of Computational Fluid Mechanics, 15(1), 1147-1158. http://dx.doi.org/10.1080/19942060.2021.1944913
Esmaeili, F., Shabanlou, S., & Saadat, M. (2021). A wavelet-outlier robust extreme learning machine for rainfall forecasting in Ardabil City, Iran. Earth Sci Inform. 14, 2087–2100. https://doi.org/10.1007/s12145-021-00681-8
Fallahi, M.M., Shabanlou, S., Rajabi, A., Yosefvand, F., & IzadBakhsh, M.A. (2023). Effects of climate change on groundwater level variations affected by uncertainty (case study: Razan aquifer). Appl Water Sci. 13(143). https://doi.org/10.1007/s13201-023-01949-8
Gaur, S., Johannet, A., Graillot, D., & Omar, P. J. (2021). Modeling of groundwater level using artificial neural network algorithm and WA-SVR model. Groundwater resources development and planning in the semi-arid region,  Springer, Cham, New York Sity, United states. https://dx.doi.org/10.1007/978-3-030-68124-1_7
Gharib, R., Heydari, M., Kardar, S., & Shabanlou, S. (2020). Simulation of discharge coefficient of side weirs placed on convergent canals using modern self-adaptive extreme learning machine. Appl Water Sci, 10, 50. https://doi.org/10.1007/s13201-019-1136-0
Ghobadi, A., Cheraghi, M., Sobhanardakani, S., Lorestani, B., & Merrikhpour, H. (2020). Hydrogeochemical characteristics, temporal, and spatial variations for evaluation of groundwater quality of Hamedan–Bahar Plain as a major agricultural region, West of Iran. Environmental Earth Sciences, 79(18), 428. https://link.springer.com/article/10.1007/s12665-020-09177-y
Huang, G.-B., Wang, D. H., & Lan, Y. (2011). Extreme learning machines: a survey. International journal of machine learning and cybernetics, 2, 107-122. http://dx.doi.org/10.1007/s13042-011-0019-y
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1-3), 489-501. https://doi.org/10.1016/j.neucom.2005.12.126
Jakeman, A. J., Barreteau, O., Hunt, R. J., Rinaudo, J.-D., & Ross, A. (2016). Integrated groundwater management. Springer Nature, Cham, New York Sity, United states. https://doi.org/10.1007/978-3-319-23576-9
Jalilian, A., Heydari, M., Azari, A., & Shabanlou, S. (2022). Extracting optimal rule curve of dam reservoir base on stochastic inflow. Water Resour Manage, 36, 1763–1782. https://doi.org/10.1007/s11269-022-03087-3
Kinzelbach, W., Bauer, P., Siegfried, T., & Brunner, P. (2003). Sustainable groundwater management—problems and scientific tools. Episodes Journal of International Geoscience, 26(4), 279-284. http://dx.doi.org/10.18814/epiiugs/2003/v26i4/002
Kumar, D., Roshni, T., Singh, A., Jha, M. K., & Samui, P. (2020). Predicting groundwater depth fluctuations using deep learning, extreme learning machine and Gaussian process: a comparative study. Earth Science Informatics, 13(4), 1237-1250. https://link.springer.com/article/10.1007/s12145-020-00508-y
Levintal, E., Kniffin, M. L., Ganot, Y., Marwaha, N., Murphy, N. P., & Dahlke, H. E. (2023). Agricultural managed aquifer recharge (Ag-MAR)—a method for sustainable groundwater management: A review. Critical Reviews in Environmental Science and Technology, 53(3), 291-314. https://doi.org/10.1080/10643389.2022.2050160
Li, J., Lu, W., Wang, H., Fan, Y., & Chang, Z. (2020). Groundwater contamination source identification based on a hybrid particle swarm optimization-extreme learning machine. Journal of Hydrology, 584, 124657. https://doi.org/10.1016/j.jhydrol.2020.124657
Malekzadeh, M., Kardar, S., Saeb, K., Shabanlou, S., Taghavi, L. (2019). 'Prediction of Groundwater Level using MODFLOW, Extreme Learning Machine and Wavelet-Extreme Learning Machine Models. Iran-Water Resources Research, 14(5), 496-501. (In Persian) https://www.iwrr.ir/article_66468.html
Mallick, J., Naikoo, M. W., Talukdar, S., Ahmed, I. A., Rahman, A., Islam, A. R. M. T., Pal, S., Ghose, B., & Shashtri, S. (2022). Developing groundwater potentiality models by coupling ensemble machine learning algorithms and statistical techniques for sustainable groundwater management. Geocarto International, 37(25), 7927-7953. http://dx.doi.org/10.1080/10106049.2021.1987535
Mazraeh, A., Bagherifar, M., Shabanlou, S., & Ekhlasmand, R. (2023). A hybrid machine learning model for modeling nitrate concentration in water sources. Water, Air, & Soil Pollution, 234(11), 721. http://dx.doi.org/10.1007/s11270-023-06745-3
Mazraeh, A., Bagherifar, M., Shabanlou, S., & Ekhlasmand, R. (2024). A novel committee-based framework for modeling groundwater level fluctuations: A combination of mathematical and machine learning models using the weighted multi-model ensemble mean algorithm. Groundwater for Sustainable Development, 24, 101062. https://doi.org/10.1016/j.gsd.2023.101062
Mirarabi, A., Nassery, H., Nakhaei, M., Adamowski, J., Akbarzadeh, A., & Alijani, F. (2019). Evaluation of data-driven models (SVR and ANN) for groundwater-level prediction in confined and unconfined systems. Environmental Earth Sciences, 78, 1-15. https://link.springer.com/article/10.1007%2Fs12665-019-8474-y
Moghadam, R.G., Yaghoubi, B., Rajabi, A., Shabanlou, S., & Izadbakhsh, M.A. (2022). Evaluation of discharge coefficient of triangular side orifices by using regularized extreme learning machine. Appl Water Sci, 12, 145. https://doi.org/10.1007/s13201-022-01665-9
Mohammed, K.S., Shabanlou, S., Rajabi, A., Yosefvand, F., & Izadbakhsh, M.A. (2023). Prediction of groundwater level fluctuations using artificial intelligence-based models and GMS. Appl Water Sci, 13, 54 (2023). https://doi.org/10.1007/s13201-022-01861-7
Norouzi Khatiri, K., Nematollahi, B., Hafeziyeh, S., Niksokhan, M. H., Nikoo, M. R., & Al-Rawas, G. (2023). Groundwater management and allocation models: a review. Water, 15(2), 253. https://doi.org/10.3390/w15020253
Panahi, J., Mastouri, R., & Shabanlou, S. (2022). Insights into enhanced machine learning techniques for surface water quantity and quality prediction based on data pre-processing algorithms. J Hydroinf, 24(4), 875–897. https://doi.org/10.2166/hydro.2022.022
Panahi, M., Sadhasivam, N., Pourghasemi, H. R., Rezaie, F., & Lee, S. (2020). Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression (SVR). Journal of Hydrology, 588, 125033. https://doi.org/10.1016/j.jhydrol.2020.125033
Rafieemehr, H., Kozegarkaleji, L. (2021). Analyzing spatiotemporal relationship between land use changes and groundwater quantity in Hamadan north plains. Environmental Sciences, 19(1), 259-276. https://doi.org/10.52547/envs.29307
Roshni, T., Mirzania, E., Hasanpour Kashani, M., Bui, Q.-A. T., & Shamshirband, S. (2022). Hybrid support vector regression models with algorithm of innovative gunner for the simulation of groundwater level. Acta Geophysica, 70(4), 1885-1898. https://doi:10.1007/s11600-022-00826-3
Shabanlou, S. (2018). Improvement of extreme learning machine using self-adaptive evolutionary algorithm for estimating discharge capacity of sharp-crested weirs located on the end of circular channels. Flow Measurement and Instrumentation, 59, 63-71. https://doi.org/10.1016/j.flowmeasinst.2017.11.003
Shahbazi, M., Zarei, H., & Solgi, A. (2023). De-noising groundwater level modeling using data decomposition techniques in combination with artificial intelligence (case study Aspas aquifer). Applied Water Science, 13(4), 88. https://doi.org/10.1007/s13201-023-01885-7
Singh, A., Patel, S., Bhadani, V., Kumar, V., & Gaurav, K. (2024). AutoML-GWL: Automated machine learning model for the prediction of groundwater level. Engineering Applications of Artificial Intelligence, 127, 107405. http://dx.doi.org/10.1016/j.engappai.2023.107405
Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and computing, 14, 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
Sun, J., Hu, L., Li, D., Sun, K., & Yang, Z. (2022). Data-driven models for accurate groundwater level prediction and their practical significance in groundwater management. Journal of Hydrology, 608, 127630. http://dx.doi.org/10.1016/j.jhydrol.2022.127630
Tang, W., Zhao, X., Motagh, M., Bi, G., Li, J., Chen, M., Chen, H., & Liao, M. (2022). Land subsidence and rebound in the Taiyuan basin, northern China, in the context of inter-basin water transfer and groundwater management. Remote Sensing of Environment, 269, 112792. https://doi.org/10.1016/j.rse.2021.112792
Tao, H., Hameed, M. M., Marhoon, H. A., Zounemat-Kermani, M., Heddam, S., Kim, S., Sulaiman, S. O., Tan, M. L., Sa’adi, Z., & Mehr, A. D. (2022). Groundwater level prediction using machine learning models: A comprehensive review. Neurocomputing, 489, 271-308. https://doi.org/10.1016/j.neucom.2022.03.014
Zhang, F., & O'Donnell, L. J. (2020). Support vector regression. Machine learning, Elsevier,        Amsterdam, Netherlands. 123-140.http://dx.doi.org/10.1016/B978-0-12-815739-8.00007-9
Advanced Technologies in Water Efficiency
Volume 5, Issue 3
September 2025
Pages 1-19

Files

History

  • Receive Date: 20 January 2025
  • Revise Date: 19 March 2025
  • Accept Date: 10 April 2025

Share

How to cite

Statistics