Freshwater salinization is a common issue that affects life in many aspects, such as infrastructure, food production, environment, biodiversity, and safe drinking water worldwide. Climate change has a wide range of salinization-related impacts, and this situation mainly affects the coastal areas. This problem in coastal locations is typically caused by 5 main sources: rising sea levels, the decline in upstream river discharges, excessive groundwater withdrawal, human activities, and storm surges that drive salt water further inland. As a consequence of these factors, saltwater intrusion puts pressure on the stakeholders who perform activities in these areas and depend on freshwater. 

The main objective of this research is to find the answer to the following question: “To what extent online sensor network data can be used to build (hybrid) water quality forecasting models that are adequate to optimize surface water management?” A rise in the salinity levels in rivers used for (drinking or industrial) water production will lead to increased water processing costs. Short-term water quality forecasting models that allow the prediction of future salinity levels would allow the optimization of water management policies. The development of these models and their application to improve management policies is the main objective of this work.