Journal of Ecohydrology

Journal of Ecohydrology

Monitoring and forecasting the spatio-temporal changes of groundwater storage in the Kuhdasht aquifer

Document Type : Research Article

Authors
Mahdi Soleimani-Motlagh 1
Ali Haghizadeh 1
Tayebeh Sepahvand 2
Negar Arjmand 2
1 Department of Watershed Management Engineering, Faculty of Natural Resources, Lorestan University, Khorramabad, Iran
2 Ph.D Student, Department of Watershed Management Engineering, Faculty of Natural Resources, Lorestan University, Khorramabad, Iran
10.22059/ije.2026.415775.1915
Abstract
Introduction: Drought and excessive extraction of groundwater in recent decades has led to a groundwater decline, and negative water balance. Kuhdasht Plain in Lorestan Province, despite having relatively suitable hydrological conditions, has not been exempt from this rule, and its groundwater resources have shown a decreasing trend.
Objectives: The aim of this study is to quantify and predict changes in groundwater storage in Kuhdasht Plain by analytical models, time series, and machine learning.
Materials and Methods: The hydrograph of the Koohdasht aquifer was plotted based on monthly water level data from 13 piezometric wells, and the annual changes in aquifer storage volume were calculated using a two-dimensional analysis method within a GIS environment. To predict fluctuations in groundwater level and storage, time series models including AR, MA, ARMA, ARIMA, and SARIMA were combined with machine learning algorithms such as Linear Regression, Random Forest, and Gradient Boosting.
Results: The results showed that the groundwater level of the plain has decreased by an average of 0.37 m/year and the balance deficit in dry years has reached about 15 MCM. Negative values of the SPEI-12m (≤-1.5) better reflected the impact of drought in dry years on the status of the groundwater. However, increased withdrawal from wells in dry years are important factor of groundwater decline. Evaluation of machine learning algorithms demonstrated the high accuracy of combining linear regression with different time series models in all piezometric wells (R2>0.98 and RMSE <0.4 m in some wells) to predict groundwater levels. The optimal time series model for Khoshnamvand, Sari, Omur Ashayer, Zaq Zalyab, Boglan, Qaralyvand, Jadhe Keshavarzi wells and for other wells were determined as AR(2), AR(3), ARIMA(2,1,2), MA(2), SARIMA(0,1,1)(0,1,1,12), ARMA(1,1), Optimized SARIMA, and Optimized ARIMA, respectively.
Final Conclusion: The findings indicated a 9.5-meter drop in groundwater level over 15 years and a storage deficit of up to 15 MCM in dry years. Despite a relative recovery in wet years, the downward trend in groundwater level is still persistent, which is most likely controlled by the increase in exploitation of groundwater resources. The combination of time series models with linear regression algorithm was selected as the best model and predicted aquifer storage deficit for the water years 1404-05 and 1405-06 to be about -0.7 and -1.22 million cubic meters, respectively. In such circumstances, a fundamental revision of the exploitation pattern, installation of smart meters, and watershed management measures to implement artificial recharge plans is inevitable.
Keywords
Groundwater Monitoring
Time Series Forecasting
Machine Learning
Storage Deficit
Kohdasht Plain
Subjects
1.      Adam, M. A., Scheiber-Enslin, S. E., & Ali, K. A. (2026). Application of random forest modeling to evaluate groundwater storage changes in the Breede Water Management Area, South Africa. Hydrogeology Journal, 1-16.
2.      Afzaal, H., Farooque, A. A., Abbas, F., Acharya, B., & Esau, T. (2020). Estimation of annual groundwater depletion using machine learning algorithms in the Prince Edward Island, Canada. Water, 12(9), 2445.
3.      Ahmadipour, M.R., Ebrahimi, B., Haghiabi,A.H., and Hashemi, P. (2002). Balance of the Kohdasht Aquifer. Lorestan University.
4.      Ashraf, S., Nazemi, A. & AghaKouchak, A. 2021. Anthropogenic drought dominates groundwater depletion in Iran. Sci Rep 11, 9135.
5.      Asrade, T. M. (2025). Application of machine learning in python for temporal groundwater level prediction. Solid Earth Sciences, 10(3), 100261.
6.      Azizi,H R and Nejatian,N . (2021). Computation of groundwater balance in Varamin plain. Geography and Human Relationships, 3(3), 189-204. doi: 10.22034/gahr.2021.263228.1487
7.      Bayazidi, M. and Kaki, M. (2021). Storage Volume and Exploitation Changes of Aquifers in the Eastern Plains of the Kurdistan Province. Journal of Ecohydrology, 8(1), 57-72. doi: 10.22059/ije.2021.307139.1360.
8.      Breiman L (2001) Random forests. Mach Learn 45:5–32
9.      Clark, S. R., Pagendam, D., & Ryan, L. (2022). Forecasting multiple groundwater time series with local and global deep learning networks. International Journal of Environmental Research and Public Health, 19(9), 5091. https://doi.org/10.3390/ijerph19095091
10.   Consulting Engineers for Water and Sustainable Development. (2015). Report on the Water Resources Balance of the Kohdasht Study Area (2207), 77 pages.
11.   Dandapat, A. K., Panda, P. K., Sankalp, S., Kisi, O., Kraiem, H., Kucher, O. D., & Tariq, A. (2025). Ensemble deep learning framework for groundwater storage forecasting under hydrological variability. Acta Geophysica, 74(1), 1.
12.   Davari, S., Eslamian, S., Jamali, M., & Safavi, H. R. (2025). Application of machine learning algorithms for groundwater level prediction in the Najafabad plain. Scientific Reports.
13.   Ebrahimi khusfi,Z. , Vali,A. A. , Ghazavi,R. and Khosroshahi,M. (2019). An investigation of the changes in the water table and the storage of western aquifers of Gavkhouni wetland during 1981-2013. Iranian Water Research Journal, 13(4), 113-123.
14.   Ebrahimi,E. , Roozbahani,A. and Banihabib,M. E. (2018). Groundwater Level Prediction Using Dynamic Bayesian Networks Based on Sensitivity Analysis (Case Study: Birjand Plain). Iranian Water Research Journal, 12(2), 91-100.
15.   Ehteram, M., & Banadkooki, F. B. (2023). A developed multiple linear regression (MLR) model for monthly groundwater level prediction. Water, 15(22), 3940.
16.   El-Yaouti F, Mandour AEl, Khattach D and Kaufmann O, 2008. Modelling groundwater flow and advective contaminant transport in the Bou-Areg unconfined aquifer (NE Morocco). Journal of Hydro-environment Research 2: 192- 209.
17.   Eslamian, S.S., Nasri, M., and Rahimi, N. 2009. Wet and Dry Periods and its Effects on Water Resources Changes in Buin Plain Watershed. Geography and Environmental Planning, 33: 75-90. (In Persian)
18.   Fijani, E., Alikhani Joudaki, S., & Mozafari, M. (2021). Investigating the Factors Affecting Groundwater Level Decline in Kouhdasht Aquifer, Lorestan Province. Civil Infrastructure Researches, 6(2), 95-105. doi: 10.22091/cer.2021.6978.1253
19.   Fitts. C. R. 2002. Groundwater Science. Second Edition, UK, Academic Press. 450
20.   Gaur S, Chahar B and Didier R, 2011. Graillot, Combined use of groundwater modeling and potential zone analysis for management of groundwater. International Journal of Applied Earth Observation and Geoinformation 13: 127– 139.
21.   George, J., Yadav, J., Nair, A. M., MV, P., Alapatt, B. P., & Baby, R. (2024, September). Improving Groundwater Forecasting Accuracy with a Hybrid ARIMA-XGBoost Approach. In 2024 3rd International Conference for Advancement in Technology (ICONAT) (pp. 1-7). IEEE.
22.   Gong, Y., Wang, Z., Xu, G., & Zhang, Z. (2018). A comparative study of groundwater level forecasting using data-driven models based on ensemble empirical mode decomposition. Water, 10(6), 730. https://doi.org/10.3390/w10060730
23.   Hadipour, H. Z., Nassery, H., & Alijani, F. (2018). The Hydrogeochemical processes of Kuhdasht aquifer.
24.   Hoseini, S. M. and khoshsimaie chenar, M. (2025). Application of machine learning algorithms in groundwater level prediction in the Ardabil aquifer. Iranian Journal of Soil and Water Research, 56(4), 1041-1057. (In Persian)
25.   Kardan Moghaddam, H., Rahimzadeh Kivi, Z., Bahreinimotlagh, M., & Alizadeh, M. J. (2019). Developing comparative mathematic models, BN and ANN for forecasting of groundwater levels. Groundwater for Sustainable Development, 9, 100237. 
26.   Khorasani, M., Ehteshami, M., Ghadimi, H. et al. Simulation and analysis of temporal changes of groundwater depth using time series modeling. Model. Earth Syst. Environ. 2, 90.
27.   Konikow, L. F. (2015). Long‐term groundwater depletion in the United States. Groundwater, 53(1), 2-9.
28.   Lenters JD, Cutrell GJ, Istanbulluoglu E, Scott DT, Herrman KS and Irmak A, 2011, Eisenhauereasonal energy and water balance of a Phragmitesaustralis -dominated wetland in the Republican River basin of south-central Nebraska (USA). Journal of Hydrology 408: 19–34.
29.   Maqbool, S., Khan, M. I., Raza, A., Saddique, N., Saddique, Q., Dong, L., ... & Buttar, N. A. (2024). Spatiotemporal Assessment and Machine Learning-Based Future Forecasting of Groundwater Hydro chemical Dynamics and Drawdown Variability.
30.   Mesmarian Z, Massahbavan A, Javadipirbazari S. (2016). Climate change impact on Groundwater budgetof ShahreKord plain in the future period.  Iranian Journal of ECO Hydrology; 3 , 233-242. (In Persian).  
31.   Mirkamandar, B., Rahnama, M.B. & Zounemat-Kermani, M. (2025). Spatio-temporal assessment of groundwater and agricultural land using remote sensing in a semi-arid region. Environ Earth Sci 84, 440.
32.   Mohammadi Ghaleni, M., Ebrahimi, K., & Araghinejad, S. (2013). Evaluation impact of drought, extraction and construction of dam on the groundwater drop-case study Saveh aquifer. Journal of Water and Soil Conservation, 19(4), 189-200.
33.   Nury, A. H., Taher, A., Alam, S., Afroz, R., Anti, S. D., Majumdar, S. N., & Munna, G. M. (2025). Assessment of groundwater variability using ARIMA, random forest, and LSTM-RNN in the northeastern region of Bangladesh. H2Open Journal, 8(5), 336-360.
34.   Poormohammadi, S. , Dastorani, M. T. , Jafari, H. , Rahimian, M. O. H. , Goodarzi, M. , Mesmarian, Z. and Baqeri, F. (2015). Investigation of groundwater balance in Tuserkan plain of Hmaedan using MODFLOW. Journal of Ecohydrology, 2(4), 371-382. doi: 10.22059/ije.2015.58063
35.   Saadatmand, E., and Komasi, M. (2024). A hybrid ensemble learning wavelet-GARCH-based artificial intelligence approach for streamflow and groundwater level forecasting at Silakhor plain, Iran. Environmental Earth Sciences, 83(3), 1-17.
36.   Shakiba, A., Mirbagheri, B., and Kheiri, A. 2010. Drought analysis using SPI index and its effects on groundwater resources in East of Kermanshah, Iran. Geograph. J. 25: 105-124. (In Persian)
37.   Shirafkan, M., and Jafari.H. (2013). Evaluation of the hydrogeological balance of the Bahabad aquifer in Yazd province. 8th Iranian Conference on Engineering and Environmental Geology, Ferdowsi University of Mashhad.
38.   Soleimani-Motlagh, M., Soleimani-Sardo, M. & Mossivand, A.M. (2022). The efficiency of the Standardized Evapotranspiration Deficit Index (SEDI) in assessing the impact of drought on vegetation cover. Environ Monit Assess 194, 299. https://doi.org/10.1007/s10661-022-09972-z
39.   Vicente-Serrano, S. M., Beguería, S., & López-Moreno, J. I.  (2010). A multiscalar drought index sensitive to global warming: The standardized precipitation evapotranspiration index. Journal of Climate, 23(7), 1696–1718.
Journal of Ecohydrology
Volume 13, Issue 3
Summer 2026
Pages 1480-1511

  • Receive Date 09 July 2026
  • Revise Date 05 August 2026
  • Accept Date 25 August 2026
  • First Publish Date 23 September 2026
  • Publish Date 23 September 2026