Estimating Groundwater Levels in Tehran Province Using Ensemble Learning Algorithms

Document Type : Original Article

Authors

Faculty of Civil Engineering, K.N. Toosi University of Technology, Tehran, Iran

Abstract

The study of groundwater levels is of paramount importance due to its critical role in water resource management, agriculture, and ecosystem sustainability. This study focuses on predicting groundwater levels in observation wells across Tehran using machine learning algorithms. A range of input parameters, including satellite-derived data from GRACE, GLDAS, and ERA5, were employed to train models for estimating groundwater level fluctuations. The primary aim was to evaluate and compare the performance of 12 different machine learning models, including Random Forest, AdaBoost, Support Vector Machine, and Artificial Neural Networks, among others, in terms of their prediction accuracy. The results indicated that ensemble-based models generally outperformed individual algorithms, achieving the highest coefficients of determination (R²) and the lowest error metrics. Spatial analysis of the errors revealed that the northern part of the study area experienced higher prediction errors than the southern region, likely due to more significant groundwater level fluctuations, influenced by regional climatic conditions and topography. Furthermore, the study demonstrated that combining various input parameters, such as terrestrial water storage, total soil moisture, and precipitation, improved the accuracy of the groundwater level predictions. The models were evaluated using standard error metrics, including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Pearson Correlation Coefficient (R), with results showing strong agreement between predicted and observed data. The findings suggest that machine learning models, especially those leveraging high-resolution satellite and reanalysis data, can be highly effective for groundwater level prediction and management in regions with limited in-situ measurement data.

Keywords

References

[1]        Ashraf, S., Nazemi, A., & AghaKouchak, A. (2021). Anthropogenic drought dominates groundwater depletion in Iran. Scientific Reports, 11(1), 9135. doi:10.1038/s41598-021-88522-y.
[2]        Pinder, G. F. (2011). Groundwater hydrology. In Groundwater Quantity and Quality Management. John Wiley & Sons, Hoboken, United States. doi:10.1029/eo070i008p00114-04.
[3]        Frappart, F., Papa, F., Famiglietti, J. S., Prigent, C., Rossow, W. B., & Seyler, F. (2008). Interannual variations of river water storage from a multiple satellite approach: A case study for the Rio Negro River basin. Journal of Geophysical Research Atmospheres, 113(21). doi:10.1029/2007JD009438.
[4]        Syed, T. H., Famiglietti, J. S., Rodell, M., Chen, J., & Wilson, C. R. (2008). Analysis of terrestrial water storage changes from GRACE and GLDAS. Water Resources Research, 44(2). doi:10.1029/2006WR005779.
[5]        Velicogna, I., & Wahr, J. (2005). Greenland mass balance from GRACE. Geophysical Research Letters, 32(18), 1–4. doi:10.1029/2005GL023955.
[6]        Sun, A. Y. (2013). Predicting groundwater level changes using GRACE data. Water Resources Research, 49(9), 5900–5912. doi:10.1002/wrcr.20421.
[7]        Scibek, J., & Allen, D. M. (2006). Modeled impacts of predicted climate change on recharge and groundwater levels. Water Resources Research, 42(11). doi:10.1029/2005WR004742.
[8]        Kinzelbach, W., Bauer, P., Siegfried, T., & Brunner, P. (2003). Sustainable groundwater management — problems and scientific tools. Episodes, 26(4), 279–284. doi:10.18814/epiiugs/2003/v26i4/002.
[9]        Zhang, D., & Tong, J. (2023). Robust water level measurement method based on computer vision. Journal of Hydrology, 620. doi:10.1016/j.jhydrol.2023.129456.
[10]      Adamowski, J., & Chan, H. F. (2011). A wavelet neural network conjunction model for groundwater level forecasting. Journal of Hydrology, 407(1–4), 28–40. doi:10.1016/j.jhydrol.2011.06.013.
[11]      Barzegar, R., Fijani, E., Asghari Moghaddam, A., & Tziritis, E. (2017). Forecasting of groundwater level fluctuations using ensemble hybrid multi-wavelet neural network-based models. Science of The Total Environment, 599–600, 20–31. doi:10.1016/j.scitotenv.2017.04.189.
[12]      Moghaddam, H. K., Moghaddam, H. K., Kivi, Z. R., Bahreinimotlagh, M., & Alizadeh, M. J. (2019). Developing comparative mathematic models, BN and ANN for forecasting of groundwater levels. Groundwater for Sustainable Development, 9, 100237. doi:10.1016/j.gsd.2019.100237.
[13]      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 Science Informatics, 16(4), 3227–3241. doi:10.1007/s12145-023-01052-1.
[14]      Soltani, K., & Azari, A. (2022). Forecasting groundwater anomaly in the future using satellite information and machine learning. Journal of Hydrology, 612, 128052. doi:10.1016/j.jhydrol.2022.128052.
[15]      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. doi:10.1002/ird.2794.
[16]      Alizadeh, M. J., Rajaee, T., & Motahari, M. (2017). Flow forecasting models using hydrologic and hydrometric data. Proceedings of the Institution of Civil Engineers: Water Management, 170(3), 150–162. doi:10.1680/jwama.14.00146.
[17]      Motahari, M., Sotoodehnia, A., Nazari, B., & Yazdani, M. (2024). Development of a water resources utilization model and optimization of the patterns of rice genotypes with system dynamics approach. Applied Water Science, 14(11), 235. doi:10.1007/s13201-024-02295-z.
[18]      Iran Meteorological Organization, Tehran, Iran. Available online: https://data.irimo.ir/ (accessed on May 2025).
[19]      Iran Water Resources Management, Tehran, Iran. Available online: http://wrs.wrm.ir/amar/register.asp (accessed on may 2025).
[20]      Rodell, M., Houser, P. R., Jambor, U., Gottschalck, J., Mitchell, K., Meng, C. J., Arsenault, K., Cosgrove, B., Radakovich, J., Bosilovich, M., Entin, J. K., Walker, J. P., Lohmann, D., & Toll, D. (2004). The Global Land Data Assimilation System. Bulletin of the American Meteorological Society, 85(3), 381–394. doi:10.1175/BAMS-85-3-381.
[21]      Goddard Earth Sciences Data and Information Services Center (GES DISC), Greenbelt, United States. Available online: https://disc.gsfc.nasa.gov/datasets (accessed on may 2025).
[22]      Mousavimehr, S. M., & Kavianpour, M. R. (2025). A non-stationary downscaling and gap-filling approach for GRACE/GRACE-FO data under climatic and anthropogenic influences. Applied Water Science, 15(5), 1–15. doi:10.1007/s13201-025-02427-z.
[23]      Seber, G. A., & Lee, A. J. (2003). Prediction and Model Selection. Linear Regression Analysis, John Wiley & Sons, Hoboken, United States. doi:10.1002/9780471722199.ch12.
[24]      Hoerl, A. E., & Kennard, R. W. (1970). Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics, 12(1), 55–67. doi:10.1080/00401706.1970.10488634.
[25]      Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning. Springer Series in Statistics. Springerو New York, United States. doi:10.1007/978-0-387-84858-7.
[26]      Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. doi:10.1007/bf00994018.
[27]      Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (2017). Classification and regression trees. Chapman and Hall/CRC, New York, United States. doi:10.1201/9781315139470.
[28]      Haykin, S. (2009). Neural networks and learning machines, 3/E. Pearson Education India, Chennai, India.
[29]      Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. doi:10.1007/bf00058655.
[30]      Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. doi:10.1023/A:1010933404324.
[31]      Freund, Y., & Schapire, R. E. (1996). Experiments with a New Boosting Algorithm. Proceedings of the 13th International Conference on Machine Learning, 96, 148–156. doi:10.1.1.133.1040.
[32]      Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. doi:10.1214/aos/1013203451.
[33]      Friedman, J. H. (2002). Stochastic gradient boosting. Computational Statistics and Data Analysis, 38(4), 367–378. doi:10.1016/S0167-9473(01)00065-2.
[34]      Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. doi:10.1145/2939672.2939785.
[35]      Alizadeh, M. J., Kavianpour, M. R., Kisi, O., & Nourani, V. (2017). A new approach for simulating and forecasting the rainfall-runoff process within the next two months. Journal of Hydrology, 548, 588–597. doi:10.1016/j.jhydrol.2017.03.032.
[36]      Vabalas, A., Gowen, E., Poliakoff, E., & Casson, A. J. (2019). Machine learning algorithm validation with a limited sample size. PLoS ONE, 14(11), 224365. doi:10.1371/journal.pone.0224365.
[37]      Tao, H., Al-Sulttani, A. O., Salih Ameen, A. M., Ali, Z. H., Al-Ansari, N., Salih, S. Q., & Mostafa, R. R. (2020). Training and Testing Data Division Influence on Hybrid Machine Learning Model Process: Application of River Flow Forecasting. Complexity, 2020(1), 8844367. doi:10.1155/2020/8844367.
[38]      Müller, A. C., & Guido, S. (2016). Introduction to machine learning with Python: a guide for data scientists. O'Reilly Media, Inc, Sebastopol, United States.
[39]      Mahesh, B. (2020). Machine Learning Algorithms - A Review. International Journal of Science and Research (IJSR), 9(1), 381–386. doi:10.21275/art20203995.
[40]      Amanollah, H., Asghari, A., Mashayekhi, M., & Zahrai, S. M. (2023). Damage detection of structures based on wavelet analysis using improved AlexNet. Structures, 56, 105019. doi:10.1016/j.istruc.2023.105019.
 
Contributions of Science and Technology for Engineering
Volume 2, Issue 1
March 2025
Pages 51-63

Files

History

  • Receive Date: 03 April 2025
  • Revise Date: 01 May 2025
  • Accept Date: 04 May 2025
  • First Publish Date: 04 May 2025
  • Publish Date: 01 March 2025

Share

How to cite

Statistics