Modeling water table depth using adaptive Neuro-Fuzzy Inference System

Evaluating the Impacts of Pumping on Aquifer Depletion in Arid Regions Using MODFLOW, ANFIS and ANN

“…Recently, Gao et al [29] used GRU for solving a similar problem in Luoyang, China. Although the application of these deep learning arterial intelligence models in the field of groundwater predictions is relatively rare to date, some researchers used the ANN, ANFIS, and SVR to simulate groundwater-levels [30][31][32][33][34][35][36]. The modeling of aquifers becomes highly challenging if the boundary conditions are not well defined for their certain parts.…”

“…Data of a specific aquifer are used to predict the future water levels and quality parameters in ANN/ANFIS application. [8,10,32,33,39] Model Type Physically distributed Black-box (data driven) -Hydraulic models incorporate physical processes and laws involved in predicting groundwater levels and quality parameters. -ANN/ANFIS are data-driven models and do not involve any physical processes.…”

“…These models only use the data observed during training, testing, and predictions. [10,32,33,39] Model bias Moderate to good Good for specific data but limited in generality -The biases are of varying magnitude (wide range of variation) in hydraulic model projections.…”

“…The biases are limited to a certain range in most cases of data-driven model projections, but ANNs/ANFIS lack generality. [8,10,32,33,39] Long-term future predictions…”

“…Expertise is required for the normalization and de-normalization of data. [8,10,32,33,39] The third objective of this study is the use of ANN/ANFIS models for long-term future predictions of groundwater levels to explore the aquifer depletion. Most of the Gulf countries are water-stressed and require sustainable groundwater planning and management [40].…”