Examining the Role of Machine Learning Algorithms in Flood Monitoring Systems

The unpredictable nature of floods often entails the process of monitoring them to be highly sophisticated. Issues with a country’s wellbeing and economic stability often ensue, necessitating newer machine learning algorithms like graphical neural networks (GNNs) and logistic regression model. The main purpose of this paper is to compare the role and effectiveness of the two machine learning algorithms in combating flooding. By exploring on the Yangtze River in China and the Banten province in Jakarta, it proposed positive impacts the GNN model and logistic regression model can have in enhancing flood monitoring systems worldwide. Through systematic selection and examination of existing literature, it found that a GNN model operated at 80-98% accuracy in flood prediction,7 while the logistic regression at 85.05% - 94.39%.5 Still, while there is room for the sphere of influence and accuracy of these models to be improved, they both have the capacity to contribute positively to existing flood monitoring systems due to the unique benefits they each provide. Overall, the paper seeks to add value into existing literature by making a personalized and substantiated judgement regarding the applicability of the GNN and logistic regression model to flood monitoring systems and their potential for future success.