Examining the Role of Machine Learning Algorithms in Flood Monitoring Systems

Author(s): Junmin Quan

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.

Robotics and Intelligent Systems, Machine Learning, Graphical Neural Networks, Logistic Regression, Mathematics, Yangtze River, Banten Province

1. Al-Juaidi, A. E. M, Nassar, A.M, Al-Juaidi, O. E. M. Evaluation of flood susceptibility mapping using logistic regression and GIS conditioning factors. Arabian Journal of Geosciences, 11, 1-10 (2018). https://doi.org/10.1007/s12517-018-4095-0
2. Bentivoglio, R, Isufi, E, Jonkman, S. N, Taormina, Riccardo. Rapid spatio-temporal flood modelling via hydraulics-based graph neural networks. Hydrology and Earth System Sciences. 27, 4227-4246 (2023). https://doi.org/10.5194/hess-27-4227-2023
3. Hamilton, W. L. Graph Representation Learning. Morgan & Claypool. 14, 1-159 (2020). https://www.cs.mcgill.ca/~wlh/grl_book/
4. Ha, S, Liu, D, Mu, L. Prediction of Yangtze River streamflow based on deep learning neural network with El Niño–Southern Oscillation. Scientific Reports. 11, 1-23 (2021). https://doi.org/10.1038/s41598-021-90964-3
5. Jati, M. I. H, Suroso, Santoso, P. B. Prediction of flood areas using the logistic regression method (Case study of the provinces Banten, DKI Jakarta, and West Java). Journal of Physics: Conference Series. 1367, 1-14 (2019). https://iopscience.iop.org/article/10.1088/1742-6596/1367/1/012087
6. Ke, W, Ouyang, C, Li, Y, Chen, M, Ma, J, An, H, Zhou, S. Reflections on the Catastrophic 2020 Yangtze River Basin Flooding in Southern China. Innovation. 1, 1-2 (2020). 10.1016/j.xinn.2020.100038
7. Kazadi, A, Doss-Gollin, J, Sebastian, A, Silva, A. Flood Prediction with Graphical Neural Networks. Rice University. (2022). https://cs.rice.edu/~al110/pubs/ccai-neurips22.pdf
8. Khemani, B, Patil, S, Kotecha, K, Tanwar, S. A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data. 11, 1-43 (2024). https://doi.org/10.1186/s40537-023-00876-4
9. Mane, P, Katti, M, Nidgunde, P, Suve, A. Early Flood Detection and Alarming System Using Machine Learning Techniques. International Journal of Research in Engineering, Science and Management. 3, 29-32 (2020). https://journal.ijresm.com/index.php/ijresm/article/view/330
10. Thorn, J. Logistic Regression Explained. Medium. (2020). https://towardsdatascience.com/logistic-regression-explained-9ee73cede081
11. Kumar, Sachin, Tiwari, Prayag, Zymbler, Mikhail. Internet of Things is a revolutionary approach for future technology enhancement: a review. Journal of Big Data. 6, 111 (2019). https://doi.org/10.1186/s40537-019-0268-2