Please login first
An AI powered, low-cost, IoT node oriented to flood Early Warning Systems
* ,
1  Department of Surveying and Geoinformatics Engineering, School of Engineering, University of West Attica, Athens, Greece
Academic Editor: Stefano Mariani


Climate change is an undoubtable phenomenon. Extreme weather conditions occur at several locations throughout the globe. Prolonged and severe rainfalls, especially when combined to deforestation, often lead to massive river floods. Such natural disasters pose a great danger to humanity.

The present study aims to design a low-cost smart AI powered node, to serve as a flood Early Warning System complete solution. The node is designed to predict forthcoming flood events by capturing and combining critical data related to such phenomena. Such data are the water level at rivers or other water discharge basins, rainfall, soil moisture, and river bank slides. The node will autonomously monitor the above quantities at a high frequency rate, and selectively upload them to a server only when verified conditions for a forthcoming flood will exist. These conditions will be evaluated by the local ML model. Network access of the node is aided by the utilization of an LTE modem provided that cellular network is present.

Further on, datasets referring to actual flood phenomena will be used to train the tinyML AI flood prediction models. After the models are validated, the AI neural networks will be integrated to the node’s Firmware. This will allow each node to reliable predict flood events and issue local and remote alarms. Combination of several nodes at an area of interest will form a robust and reliable Early Warning System.

Keywords: Early Warning Systems; floods; AI; low-cost; IoT; nodes; sensors; cellular network