Advancing Flood predication based on integrating Traditional and Deep Learning Techniques

Muthana S. Mahdi; Ishraq Khudhair  Abbas; Ban M.  Muhammed; Hiba Abdulrazzaq  Abbas

doi:10.37899/journallamultiapp.v5i6.1520

Muthana S. Mahdi Department of Computer Science, College of Science, Mustansiriyah University, Baghdad, Iraq,
Ishraq Khudhair Abbas Department of Computer Science, College of Science, Mustansiriyah University, Baghdad, Iraq
Ban M. Muhammed Iraqi Commission for Computers and Informatics (ICCI), Baghdad, Iraq
Hiba Abdulrazzaq Abbas Department of Computer Science, College of Science, Mustansiriyah University, Baghdad, Iraq

DOI: https://doi.org/10.37899/journallamultiapp.v5i6.1520

Keywords: Floods, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²), hybrid Machine Learning (ML), DNNs

Abstract

Flood prediction is critical for reducing the negative effects of catastrophes. This study investigates the use of classical and deep learning algorithms to accurately anticipate flood levels using past ecological information. The study takes two approaches: linear regression and deep neural networks (DNN). These models are trained and evaluated using historical records stretching years, as well as moisture, temperature, and rainfall measurements. Visualization tools, such as development/validation reduction charts projected against real floodwater level graphs, can help understand model learning behaviors and efficacy. Furthermore, a combination model method is investigated, which combines forecasts from both approaches and has the promise to improve the accuracy of predictions. Future forecasts for the year 2025 can be generated using expected atmospheric conditions, illustrating the models' usefulness in projecting eventual floodwater levels. Measures of assessment and visualization results demonstrate the effectiveness of deep learning technologies in improving flooding predictions when contrasted with classic conventional techniques. This investigation advances flooding forecasting skills by combining known statistical approaches and new deep learning algorithms, thereby helping in active catastrophe control and vulnerability planning.

References

Anaraki, M. V., Farzin, S., Mousavi, S. F., & Karami, H. (2021). Uncertainty analysis of climate change impacts on flood frequency by using hybrid machine learning methods. Water Resources Management, 35, 199-223. https://doi.org/10.1007/s11269-020-02719-w

Chollet, F. (2017). Deep Learning with Python. Manning Publications.

Dtissibe, F. Y., Ari, A. A. A., Abboubakar, H., Njoya, A. N., Mohamadou, A., & Thiare, O. (2024). A comparative study of Machine Learning and Deep Learning methods for flood forecasting in the Far-North region, Cameroon. Scientific African, 23, e02053.‏ https://doi.org/10.1016/j.sciaf.2023.e02053

Duan, Q., Sorooshian, S., & Gupta, V. K. (2006). Effective and Efficient Global Optimization for Conceptual Rainfall-Runoff Models. Water Resources Research, 32(4), 101-110. https://doi.org/10.1029/96WR03180.

Habibi, A., Delavar, M. R., Nazari, B., Pirasteh, S., & Sadeghian, M. S. (2023). A novel approach for flood hazard assessment using hybridized ensemble models and feature selection algorithms. International Journal of Applied Earth Observation and Geoinformation, 122, 103443. https://doi.org/10.1016/j.jag.2023.103443

Habibi, A., Delavar, M. R., Sadeghian, M. S., Nazari, B., & Pirasteh, S. (2023). A hybrid of ensemble machine learning models with RFE and Boruta wrapper-based algorithms for flash flood susceptibility assessment. International Journal of Applied Earth Observation and Geoinformation, 122, 103401. https://doi.org/10.1016/j.jag.2023.103401

Herath, M., Jayathilaka, T., Hoshino, Y., & Rathnayake, U. (2023). Deep machine learning-based water level prediction model for Colombo flood detention area. Applied Sciences, 13(4), 2194.‏ https://doi.org/10.3390/app13042194

Hosseini, F. S., Choubin, B., Mosavi, A., Nabipour, N., Shamshirband, S., Darabi, H., & Haghighi, A. T. (2020). Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method. Science of the total environment, 711, 135161. https://doi.org/10.1016/j.scitotenv.2019.135161

Karim, F., Armin, M. A., Ahmedt-Aristizabal, D., Tychsen-Smith, L., & Petersson, L. (2023). A review of hydrodynamic and machine learning approaches for flood inundation modeling. Water, 15(3), 566.‏ https://doi.org/10.3390/w15030566

Li, L., & Jun, K. S. (2024). Review of machine learning methods for river flood routing. Water, 16(2), 364.‏ https://doi.org/10.3390/w16020364

Madsen, H., Lawrence, D., Lang, M., Martinkova, M., & Kjeldsen, T. R. (2014). Review of trend analysis and climate change projections of extreme precipitation and floods in Europe. Journal of Hydrology, 519, 3634-3650. https://doi.org/10.1016/j.jhydrol.2014.11.003

Mittal, S. (2020). A survey on modeling and improving reliability of DNN algorithms and accelerators. Journal of Systems Architecture, 104, 101689.

Mosavi, A., Ozturk, P., & Chau, K. W. (2018). Flood prediction using machine learning models: Literature review. Water, 10(11), 1536.‏ https://doi.org/10.3390/w10111536

Parashar, A., Raina, P., Shao, Y. S., Chen, Y. H., Ying, V. A., Mukkara, A., ... & Emer, J. (2019, March). Timeloop: A systematic approach to dnn accelerator evaluation. In 2019 IEEE international symposium on performance analysis of systems and software (ISPASS) (pp. 304-315). IEEE. https://doi.org/10.1109/ISPASS.2019.00042

Sit, M., Demiray, B. Z., Xiang, Z., Ewing, G. J., Sermet, Y., & Demir, I. (2020). A comprehensive review of deep learning applications in hydrology and water resources. Water Science and Technology, 82(12), 2635-2670.‏ https://doi.org/10.2166/wst.2020.369

Yosri, A., Ghaith, M., & El-Dakhakhni, W. (2024). Deep learning rapid flood risk predictions for climate resilience planning. Journal of Hydrology, 631, 130817.‏ https://doi.org/10.1016/j.jhydrol.2024.130817