Acadlore takes over the publication of IJEI from 2025 Vol. 8, No. 5. The preceding volumes were published under a CC BY 4.0 license by the previous owner, and displayed here as agreed between Acadlore and the previous owner. ✯ : This issue/volume is not published by Acadlore.
Open AccessAI-Based Analysis and Forecasting of the Groundwater Quality Index for Irrigation in Anbar, Iraq
View Full Article|
Download PDFAbstract:
Groundwater quality monitoring and prediction for irrigation purposes is of utmost importance for water resources management. Data were collected for groundwater quality parameters from a number of wells in Anbar Governorate, western Iraq, to estimate and predict the groundwater quality index for irrigation purposes (IWQI) using three AI models: (ANN), (SVM), and (DL). The inputs represent ten water quality parameters, including: (EC), (TDS), (SAR), (K+), (Mg2+), (Ca2+), (Cl-), (HCO3-), and (SO42-). AI models were applied after dividing the data into 70% for training and 30% for testing. The performance of the models was evaluated by determining statistical indicators between the actual and expected values of IWQI. The correctness was demonstrated by the outcomes of AI models and their high performance in both the training and testing phases. In addition, the statistical indicators of the SVM model showed that it was the best model that gave appropriate performance with (R2 = 0.99, RMSE = 31.8). We conclude that AI models can be relied upon for integrated and sustainable water management.
