Groundwater budget forecasting, using hybrid wavelet-ANN-GP modelling: a case study of Azarshahr Plain, East Azerbaijan, Iran

Gorgij, Alireza Docheshmeh; Kisi, Özgür; Moghaddam, Asghar Asghari

doi:10.2166/nh.2016.202

Cited by 36 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Amiri, Nakhaei, Lak, and Kholghi (, ) analysed groundwater in the western part of the Lake Urmia basin to conclude that recharge of groundwater was important in wet seasons. Gorgij, Kisi, and Moghaddam () used the hybrid wavelet‐artificial neural network‐genetic programming as a method to study the water budget in Azarshahr Plain at the eastern bank of Lake Urmia. Nourani and Mousavi () made spatial and temporal analysis of groundwater level using artificial intelligence in the eastern coast of the lake to conclude that groundwater, as a key role player in agricultural water demand, is very vulnerable.…”

Section: Introductionmentioning

confidence: 99%

Interaction of groundwater with Lake Urmia in Iran

Vaheddoost

Aksoy

2018

Hydrological Processes

View full text Add to dashboard Cite

Being a large hyper‐saline water body, Lake Urmia in north‐western Iran deals with a gradual decline in its water level. Most of the studies on Lake Urmia have neglected the groundwater issue. In this study, as a direct approach, the interaction between the groundwater level and the lake water level is investigated both in time and space by analysing the groundwater data compiled from observation wells surrounding the lake. Baseflow separation is considered as an indirect approach to understand the groundwater contribution to the river network flowing into the lake. It is determined that about 70% of run‐off in the rivers draining into the lake is born in the form of baseflow. An interaction between the lake and the groundwater storage is clearly seen from the analysis to conclude that groundwater has a potential to recharge the lake. Thus, the shrinkage of water level in Lake Urmia could be expected to accelerate with the drastic use of groundwater, which will be a disaster with no return.

show abstract

Section: Introductionmentioning

confidence: 99%

Interaction of groundwater with Lake Urmia in Iran

Vaheddoost

Aksoy

2018

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…The study area has a semi-arid and cold climate. In the Azarshar and Ajabshir planes the average annual temperatures are 13°C and 12°C and the average annual precipitations are 221.2 and 300 mm, respectively (Docheshmeh Gorgij & Asghari Moghaddam 2017;Gorgij et al 2017;Moghaddam et al 2018). The mean water table depths of the aquifers are in the range of 0.7-29.8 m in the Azarshar plane and 0.5-37.7 m in the Ajabshir plane (Rezaei & Gurdak 2020).…”

Section: Characteristics Of the Study Areamentioning

confidence: 99%

“…Since the study area is located in the vicinity of the hypersaline region of the Urmia Lake where there is an imbalance between precipitation and evaporation, its water consumption is completely dependent on groundwater resources (Gorgij et al 2019). For example, in the Azarshahr plane, 100% of the water for drinking, domestic, and industrial purposes and 80% of the water for agricultural purposes are supplied by the groundwater resources (Gorgij et al 2017).…”

Section: Characteristics Of the Study Areamentioning

confidence: 99%

Spatial and temporal assessment of groundwater quality and hydrogeochemical processes in Urmia Lake Basin, Iran

et al. 2021

View full text Add to dashboard Cite

The evaluation of groundwater quality and geochemistry have an important role in the management of water resources in arid and semi-arid regions. In the present study, the spatio-temporal assessment of groundwater quality and hydrogeochemical processes, as well as, statistical analyses in the Azarshahr and Ajabshir planes located in the Urmia Lake basin were investigated. The results revealed that within six years (from 2014 to 2019), the value of total hardness was higher than the permissible level and the quality of groundwater for drinking was very hard and fresh in both planes. In 2019, 84 and 67% of the samples fell within the range of good to poor groundwater quality in the Azarshahr and Ajabshir planes, respectively. The temporal assessment with the help of water quality index values for both planes revealed a good groundwater quality for the Azarshahr plane and a good to poor groundwater quality for the Ajabshir plane. However, deterioration of water quality was observed in both planes from 2014 to 2019. The level of water quality for irrigation was better in the Azarshahr plane than in the Ajabshir plane, due to the presence of fewer salty sites. In addition, Ca–Mg–HCO3 and rock dominance were identified as hydrochemical facies and controlling factor in the groundwater of both planes, respectively. Multivariate statistical analyses indicated both natural and anthropogenic sources (such as weathering, fertilizers, and wastewater) for hydrochemical parameters. It was suggested to develop a comprehensive regulation to control the entry of pollutants into the groundwater of the study area.

show abstract

“…Furthermore, wavelet transform combined with an NN also has important applications in groundwater modeling. For example, Gorgij et al (2017) used an NN based on wavelet analysis and a genetic program model to predict the water table in the eastern plain of Iran. Ebrahimi and Rajaee (2017) used NNs, multiple linear regression and support vector regression combined with wavelet analysis to predict the monthly water table of the Qom plain in Iran and have found that the wavelet transform analysis improved the prediction effect of these models.…”

Section: Introductionmentioning

confidence: 99%

Combined Wavelet Transform With Long Short-Term Memory Neural Network for Water Table Depth Prediction in Baoding City, North China Plain

Liang

Liu

et al. 2021

Front. Environ. Sci.

View full text Add to dashboard Cite

Accurate estimation of water table depth dynamics is essential for water resource management, especially in areas where groundwater is overexploited. In recent years, as a data-driven model, artificial neural networks (NNs) have been widely used in hydrological modeling. However, due to the non-stationarity of water table depth data, the performance of NNs in areas of over-exploitation is challenging. Therefore, reducing data noise is an essential step before simulating the water table depth. This research proposed a novel method to model the non-stationary time series data of water table depth through combing the advantages of wavelet analysis and Long Short-Term Memory (LSTM) neural network (NN). A typical groundwater over-exploitation area, Baoding, North China Plain (NCP), was selected as a study area. To reflect the impact of anthropogenic activities, the variables harnessed to develop the model includes temperature, precipitation, evaporation, and some socio-economic data. The results show that decomposing the time series of the water table depth into three sub-temporal components by Meyer wavelets can significantly improve the simulation effect of LSTM on the water table depth. The average NSE (Nash-Sutcliffe efficiency coefficient) value of all the sites increased from 0.432 to 0.819. Additionally, a feedforward neural network (FNN) is used to compare forecasts over 12-months. As expected, wavelet-LSTM outperforms wavelet-FNN. As the prediction time increases, the advantages of wavelet-LSTM become more evident. The wavelet-LSTM is satisfactory for forecasting the water table depth at most in 6 months. Furthermore, the importance of input variables of wavelet-LSTM is analysed by the weights of the model. The results indicate that anthropogenic activities influence the water table depth significantly, especially in the sites close to the Baiyangdian Lake, the largest lake in the North China Plain. This study demonstrates that the wavelet-LSTM model provides an option for water table depth simulation and predicting areas of over-exploitation of groundwater.

show abstract

Groundwater budget forecasting, using hybrid wavelet-ANN-GP modelling: a case study of Azarshahr Plain, East Azerbaijan, Iran

Cited by 36 publications

References 24 publications

Interaction of groundwater with Lake Urmia in Iran

Interaction of groundwater with Lake Urmia in Iran

Spatial and temporal assessment of groundwater quality and hydrogeochemical processes in Urmia Lake Basin, Iran

Combined Wavelet Transform With Long Short-Term Memory Neural Network for Water Table Depth Prediction in Baoding City, North China Plain

Contact Info

Product

Resources

About