A Real Time Flood Detection System Based on Machine Learning Algorithms

Flood is expressed as water overflowing onto the ground that usually is dry or an increase of water that has a significant impact on human life and it is also declared as one of the most usually natural phenomenon, causing severe financial crisis to goods and properties as well as affecting human lives. However, preventing such floods would be useful to the inhabitants in order to get a sufficient time to evacuate in the areas that might be possible floods can happen before the actual floods happen. To address the issue of floods, many scholars’ proposed different solutions such as developing prediction models and building a proper infrastructure. Nevertheless, these proposed solutions are not efficient from an economic perspective in here, Somalia. Therefore, the key objective of this research paper is to intend a new robust model which is a real-time flood detection system based on Machine-Learning-algorithms; Random-Forest, Naïve-Bayes and J48 that can detect water level and measure floods with possible humanitarian consequences before they occur. The experimental results of this proposed method will be the solution of forth mentioned problems and conduct research on how it can be easily simulate a novel way that detects water levels using hybrid model based on Arduino with GSM modems. Based on the analysis, Random-Forest-algorithm were outperformed other machine-learning-methods in-terms of accuracy over other-classification with 98.7% accuracy in-comparison with 88.4% and 84.2% for NaiveBayes and J48 respectively. The proposed method has contribution to the field of study by introducing a new way of preventing floods in the field of Artificial, data mining.