July 2024
·
1 Read
Jurnal Teknologi Sistem Informasi dan Aplikasi
Flooding is a natural disaster that most often affects Indonesia. South Sumatra is one of the areas that experienced recurrent flooding from 2023 to 2024. Monitoring of water levels at a point is often lacking, so that during high rainfall, water often overflows and causes flooding. Uncontrolled water discharge due to heavy rainfall can cause flooding and impact the local community due to lack of information. To solve this problem, machine learning technology can be used as a flood detection and early warning tool. The SVR (Support Vector Regression) algorithm is one example. This research classifies flood status into three categories: "Safe, Alert, and Danger." The flood status prediction model is built using SVR (Support Vector Regression) integrated with a flood detection device consisting of Arduino Uno, NodeMCU, and two sensors, namely an ultrasonic sensor and a rainfall sensor, which are installed above 1 metre from the ground. The test results show that this device can detect flood status based on the water level. When the distance between the water surface and the sensor is 80-100 cm and the rainfall is 0-20 mm, the status is safe, if the water distance is 50-80 cm and the rainfall is 21-30 mm, the status is alert, while if the water distance is 0-50 cm and the rainfall is 31-100 mm, the status is dangerous. The flood status detected by this tool will then be sent via the Telegram application as a notification to facilitate effective flood monitoring.