Jerime Chris F. Mendez

Coastal aquifers are essential freshwater sources for domestic, agricultural, and industrial use, particularly in regions where surface water is limited. However, these systems face growing stress from saltwater intrusion, climate-driven reductions in recharge, sea level rise, and intensified groundwater extraction. This review synthesizes recent research on coastal aquifer responses to these pressures, highlighting the interplay between natural hydrogeologic conditions and human-induced demand. Across deltaic and sedimentary systems, studies consistently show declining groundwater levels, the landward migration of saline interfaces, and reduced aquifer buffering capacity, especially in areas with high evaporation and limited recharge. The review also evaluates emerging strategies to preserve coastal groundwater security. Integrated hydrological models, managed aquifer recharge (MAR), optimized abstraction schemes, and remote sensing-based monitoring are advancing adaptive management capabilities. In parallel, policy and nature-based interventions—such as aquifer protection zoning, wetland rehabilitation, and dune system restoration—support long-term resilience by enhancing natural recharge and reducing vulnerability. The overall findings reveal the need for climate-informed and locally tailored groundwater management. Future efforts should prioritize coupling high-resolution climate projections with aquifer system models, evaluating MAR viability in saline-prone environments, and strengthening collaborative governance frameworks to ensure sustainable and equitable use of coastal aquifers.

Streamflow prediction in ungauged watersheds remains a critical challenge in hydrological science due to the absence of in situ measurements, particularly in remote, data-scarce, and developing regions. This review synthesizes recent advancements in artificial intelligence (AI) for streamflow modeling, focusing on machine learning (ML), deep learning (DL), and hybrid modeling frameworks. Three core methodological domains are examined: regionalization techniques that transfer models from gauged to ungauged basins using physiographic similarity and transfer learning; synthetic data generation through proxy variables such as NDVI, soil moisture, and digital elevation models; and model performance evaluation using both deterministic and probabilistic metrics. Findings from recent literature consistently demonstrate that AI-based models, especially Long Short-Term Memory (LSTM) networks and hybrid attention-based architectures, outperform traditional conceptual and physically based models in capturing nonlinear hydrological responses across diverse climatic and physiographic settings. The integration of AI with remote sensing enhances generalizability, particularly in ungauged and human-impacted basins. This review also addresses several persistent research gaps, including inconsistencies in model evaluation protocols, limited transferability across heterogeneous regions, a lack of reproducibility and open-source tools, and insufficient integration of physical hydrological knowledge into AI models. To bridge these gaps, future research should prioritize the development of physics-informed AI frameworks, standardized benchmarking datasets, uncertainty quantification methods, and interpretable modeling tools to support robust, scalable, and operational streamflow forecasting in ungauged watersheds.