Interpretation of Multi Sensor Measurement Results using Fuzzy Membership Function for Landslide Early Warning System

Central Java has several areas prone to landslides. One of them is in Tembalang District in Semarang City, Central Java Province, Indonesia .Landslides can be caused by very high rainfall and there are no trees to support the soil, resulting in land shifting. Landslaezdide disasters are very dangerous because they cause many casualties. Therefore, there is a need for an early warning system for landslides. The landslide early warning system uses several sensors, namely rainfall sensors. Therefore, there is a need for an early warning system for landslides. The landslide early warning system uses several sensors, namely rainfall sensors, soil moisture sensors and soil movement. The sensor data will be processed using fuzzy logic so that the results can be more accurate. Early warning of landslides has several conditions, namely low risk to very high risk. Based on the results of real-time data collection in the landslide disaster early warning system, the results obtained were that the sensors were working well and communication sending data to the website was running well. Data processing has been carried out and can be processed via a controller with a fuzzy logic logic algorithm. The results obtained were that based on sensor data taken early warning of landslides still had a low risk with a value of 0.5375 and a medium risk with a value of 0.5875. This is due to moderate rainfall and high soil moisture, as well as ground movement ≥ 0.1