River flooding is a condition when the water in a river overflows and exceeds its normal capacity, thereby flooding the surrounding area. This flood disaster has been a known problem for a long time and causes great damage in the affected areas. Flood events inRivers are influenced by many factors, such as climate change, rapid urbanization, inappropriate land use, ineffective water management patterns, as well as uncontrolled addition of hard soil surfaces. Flood conditions in rivers involve complex processes and are influenced by various factors components, such as rainfall, water flow, topography, vegetation, and many other factors. Therefore, this research is very urgent because it can help reduce the negative impacts of flooding, increase public safety, become a basis for decision making, save costs and resources and make a positive contribution to technological development. This study aims to create a prototype of a flood early warning system. The system is based on a wireless sensor network whose interconnections are connected by a star topology. Every node is a combination of several sensors (sensor fusion) that are related to detecting floods, such as: height sensors, water flow speed sensors and rainfall intensity sensors. Design of hardware (hardware) and software (software) will be done. A classification mechanism based on Fuzzy Logic will be used to estimate flood conditions based on existing data. Flood estimation will determine the time and distance of flood events that will occur. Several experiments in the laboratory will be carried out to determine the performance of the designed system.