ML and IoT-based Flood-Safe Waterfalls Alert System
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Floods in waterfalls are a severe threat to ecosystems and tourists; a real-time and efficient prediction and alert system is needed. An ML and IoT-based Flood-Safe Waterfalls Alert System based on Machine Learning (ML) algorithms and Internet of Things (IoT) devices that monitor and predict flood risks in waterfall areas is proposed here. The Random Forest prediction model forecasts flood risks from real-time weather parameters to predict the present and next 24-hours flood prediction. The forecasted data is sent to a Firebase-based cloud platform, where it can be accessed through a web dashboard and also a mobile application for easy access. Advance warnings are triggered when conditions suggest likely flooding. The system utilizes real-time sensor data, such as water flow rate, collected with ESP8266 and LoRa, which is implemented at various levels along the path of waterfalls, gives warnings using buzzers and LED lights, which are placed at the local areas, and the data of various levels is sent to a Firebase-based cloud platform where it can be accessed through a web dashboard and mobile application. The accuracy of the system is improved by using the OpenWeatherMap API for live climate information. The solution is extremely scalable and can easily be extended to other waterfall sites, giving a cost-effective, efficient, and safe solution for early flood detection and public safety improvement.
Fields of Study & Subjects
Arduino and IoT Applications
Energy and Environmental Systems
Flood Risk Assessment and Management
Publication details
- Journal / source
- CRC Press eBooks
- Pages
- 334–339
- Publication date
- 31 March 2026
- Language
- EN
- Document type
- Book chapter