Jamal Al Qundus, Kosai Dabbour, Shivam Gupta, Régis Meissonier, Adrian Paschke
The study proposes a wireless sensor network decision model for the detection of flood disasters by observing changes in weather conditions compared to historical information at a given location. To this end, we collect data such as air pressure, wind speed, water level, temperature and humidity (DH11), precipitation (0/1) from sensors located at several points in the area under consideration and obtain sea level air pressure and rainfall from the Google API. The collected data is then transmitted via a LoRaWAN network implemented in Raspberry-Pi and Arduino. The developed SVM model includes a number of coordinators responsible for a number of sectors (locations), sends the binary decisions with accuracy of 98% of flood or non-flood to a cloud server connected to monitoring rooms where a decision can be made regarding the response to a possible flood disaster.