Amirkabir University of TechnologyAmirkabir Journal of Civil Engineering2588-297X54320220522A Bayesian network approach for predicting groundwater level (Case study: Qazvin aquifer)A Bayesian network approach for predicting groundwater level (Case study: Qazvin aquifer)831850440910.22060/ceej.2021.19101.7067FABayramaliMohammadnezhadDepartment of Civil Engineering, Faculty of Technical Engineering, Qom University of Technology (QUT), Iran.0000-0003-3074-007XShayanSadegholvadMaster of Water Resources Management, Science and Research Branch, Islamic Azad University, Tehran, Iran.MortezaJiryaei SharahiDepartment of Civil Engineering, Faculty of Technical Engineering, Qom University of Technology (QUT), Iran.0000-0003-3775-6066Journal Article20201006<span style="letter-spacing: .05pt;">Excessive use of groundwater resources has put the aquifers in critical situations. This study provides a framework for using the Bayesian network for groundwater level estimation and aquifer hydrograph analysis. Five variables, temperature, the groundwater level in the previous month, groundwater withdrawal, aquifer feeding, and rainfall were used as input variables, and the groundwater level in the current month was used as an output variable in the Bayesian network simulations. A 10-year statistical data, 8 years of data for model training and 2 years of data for model validation were used. The Bayesian network model was implemented and analyzed in three explicit, clustering and two- and three-month delay states. Explicit simulation results showed that most of the wells have a good correlation between the simulation and observed data. Clustering results were less accurate than explicit ones. In the third case, two and three months delay data was used for simulations. The results showed that the correlation between observed and simulated groundwater levels decreased. At 1, 2 and 3 months delay statuses, Root Mean Square Error was 1.87 m, 3.76 m, and 6.42 m, respectively. Therefore, the one-month lag time was chosen for the simulations and the aquifer hydrograph was used to evaluate and estimate total aquifer variations. The results indicate the appropriate accuracy of the aquifer parameters estimation.</span><span style="letter-spacing: .05pt;">Excessive use of groundwater resources has put the aquifers in critical situations. This study provides a framework for using the Bayesian network for groundwater level estimation and aquifer hydrograph analysis. Five variables, temperature, the groundwater level in the previous month, groundwater withdrawal, aquifer feeding, and rainfall were used as input variables, and the groundwater level in the current month was used as an output variable in the Bayesian network simulations. A 10-year statistical data, 8 years of data for model training and 2 years of data for model validation were used. The Bayesian network model was implemented and analyzed in three explicit, clustering and two- and three-month delay states. Explicit simulation results showed that most of the wells have a good correlation between the simulation and observed data. Clustering results were less accurate than explicit ones. In the third case, two and three months delay data was used for simulations. The results showed that the correlation between observed and simulated groundwater levels decreased. At 1, 2 and 3 months delay statuses, Root Mean Square Error was 1.87 m, 3.76 m, and 6.42 m, respectively. Therefore, the one-month lag time was chosen for the simulations and the aquifer hydrograph was used to evaluate and estimate total aquifer variations. The results indicate the appropriate accuracy of the aquifer parameters estimation.</span>https://ceej.aut.ac.ir/article_4409_44d180fdea11b43afd44a8c807ace0b2.pdf