Water quality management and wastewater recycling optimization are critical challenges in groundwater management, especially under climate change. This study investigated key water quality parameters, including pH, EC, BOD5, COD, and microbial indicators such as E. coli and Coliform, during the storage-recovery phase of wastewater recycling. The analysis was based on data from a 60-day field experiment in the Chalous aquifer, where domestic wastewater was injected and water quality was regularly monitored.

To model and predict aquifer behavior, a Multi-Layer Perceptron (MLP) with three hidden layers was developed and compared with the MODFLOW numerical model. The MLP, trained on 70% of the data and validated on the remaining 30%, showed superior predictive performance and reduced modeling errors by about 20% compared with MODFLOW.
The study also assessed the impacts of climate change on groundwater recharge and contamination risk for the period 2030-2050. Future climate conditions were generated using LARS-WG 8 and the MRI-ESM2-0 climate model under SSP1-2.6, SSP2-4.5, and SSP5-8.5 scenarios. Results showed that groundwater recharge may decrease by 13% to 25%, leading to a projected groundwater level decline of 1.1 to 1.7 m by 2050. Under constant pollutant loading, this decline could increase concentrations of BOD5, COD, EC, Coliform, and E. coli by 15% to 28%, significantly degrading groundwater quality. Overall, the findings emphasize the need for climate-resilient strategies to protect groundwater quality in the future.