A Comparative Analysis of Time-Series Models of ARIMA and Prophet IoT-Based Flood Forecasting in Sungai Melaka

Authors

  • Mazran Esro Technical University of Malaysia Melaka
  • Siva Kumar Subramaniam Sheffield Hallam University City Campus
  • Ahamed Fayeez Tuani Ibrahim Technical University of Malaysia Melaka
  • Yogan Jaya Kumar Technical University of Malaysia Melaka
  • Siti Aisyah Anas Technical University of Malaysia Melaka
  • Sujatha Rajkumar Vellore Institute of Technology

DOI:

https://doi.org/10.26877/asset.v7i4.1048

Keywords:

Prophet, ARIMA, IoT-based Flood Forecast, Sustainable Flood Management, AI-Driven Disaster Mitigation

Abstract

Flood prediction is essential for mitigating disasters, especially in low-lying areas. This study presents an IoT-driven flood forecasting system that utilizes ARIMA and Prophet models to predict water levels in Sungai Melaka, Malaysia. Sensor data collected from an IoT-based flood observatory system was used to train and evaluate both models. Performance analysis based on RMSE and MAPE revealed that while ARIMA captures short-term trends, Prophet outperforms it with a lower MAPE of 6% and RMSE of 5, demonstrating superior accuracy and adaptability. Prophet's advantage lies in its robust seasonality handling, flexible trend adjustments, and ability to incorporate external regressors, making it more effective for real-time flood monitoring. The study also highlights Prophet’s limitations in capturing abrupt water level spikes, suggesting that integrating environmental factors such as rainfall intensity and upstream discharge could enhance predictive accuracy. The findings contribute to the development of AI-driven flood warning systems, supporting urban disaster management strategies.

Author Biographies

  • Mazran Esro, Technical University of Malaysia Melaka

    Faculty of Electronics and Computer Engineering and Technology, Technical University of Malaysia Melaka, Malaysia

  • Siva Kumar Subramaniam, Sheffield Hallam University City Campus

    School of Engineering and Built Environment, College of Business, Technology and Engineering, Sheffield Hallam University City Campus, Sheffield S1 1WB, United Kingdom

  • Ahamed Fayeez Tuani Ibrahim, Technical University of Malaysia Melaka

    Faculty of Electronics and Computer Engineering and Technology, Technical University of Malaysia Melaka, Malaysia

  • Yogan Jaya Kumar, Technical University of Malaysia Melaka

    Faculty of Information and Communication Technology, Technical University of Malaysia Melaka, Malaysia

  • Siti Aisyah Anas, Technical University of Malaysia Melaka

    Faculty of Electronics and Computer Engineering and Technology, Technical University of Malaysia Melaka, Malaysia

  • Sujatha Rajkumar, Vellore Institute of Technology

    Department of Embedded Technology (IoT and sensors specialization), School of Electronics and Communication Engineering, Vellore Institute of Technology, India

References

[1] Abdul Rahim NF, Zulkifli SN, Ahmad AM, et al. Investigation Performance Analysis and Evaluation of VANET Routing Protocol on Urban Scenario Simulation: A Case Study of Melaka. J Adv Res Appl Sci Eng Technol, 2024;42(2):27-37.

[2] Minh HVT, Nhan DK, Luan LT, et al. Modelling and predicting annual rainfall over the Vietnamese Mekong Delta (VMD) using SARIMA. Discov Geosci, 2024;2(1):1-18.

[3] Opolski U, Ficek B, Król M, et al. Uniwersytet Opolski Publikacja / Publication Analysis Of The Housing Market Dynamics Using NARX Neural Network, 2024;38(1).

[4] Vidyalashmi K, Nakanishi A, Ishida K, et al. Analysing the performance of the NARX model for forecasting the water level in the Chikugo River estuary, Japan. Environ Res, 2024;251:118531.

[5] Wong WM. Flood Prediction using ARIMA Model in Sungai Melaka, Malaysia. Int J Adv Trends Comput Sci Eng, 2020;9(4):5287-95. doi: 10.30534/ijatcse/2020/160942020.

[6] Wong WM, Lee MY, Azman AS, et al. Development of Short-term Flood Forecast Using ARIMA. Int J Math Model Methods Appl Sci, 2021;15:68-75.

[7] Elneel L, Zitouni MS, Mukhtar H, et al. Examining sea levels forecasting using autoregressive and prophet models. Sci Reports, 2024;14(1):1-13.

[8] Bekkar A, Hssina B, Douzi S, et al. Forecasting Ozone Levels in Morocco: A Comparative Study of SARIMA and FB Prophet Models. IGI Global, 2024.

[9] Hasan MM, Ng KTW, Ray S, et al. Prophet time series modeling of waste disposal rates in four North American cities. Environ Sci Pollut Res, 2024;31(21):31343–54.

[10] Cheng J, Tiwari S, Khaled D, et al. Forecasting Bitcoin prices using artificial intelligence: Combination of ML, SARIMA, and Facebook Prophet models. Technol Forecast Soc Change, 2024;198:122938. doi: 10.1016/J.TECHFORE.2023.122938.

[11] Wang W, He N, Chen M, et al. Freight rate index forecasting with Prophet model based on multi-dimensional significant events. Expert Syst Appl, 2024;249:123451.

[12] Gannapathy VR, Narayanamurthy V. A Mobile and Web-Based Security Guard Patrolling, Monitoring and Reporting System to Maintain Safe and Secure Environment at Premises. Int J Interact Mob Technol, 2023;17(11):4-14.

[13] Mathew B, Krishnakanth G, Varshini V, et al. Smart Flood Prediction and Alert System. JETIR, 2019;6(5):153-5.

[14] Sankaranarayanan S, Prabhakar M, Satish S, et al. Flood prediction based on weather parameters using deep learning. J Water Clim Chang, 2020;11(4):1766-83. doi: 10.2166/WCC.2019.321.

[15] Darmawan RA, Hidayat EY. Comparison of Gradient Boosting and Random Forest Models in the Detection System of Rakaat during Prayer. Adv Sustain Sci Eng Technol, 2024;6(1):02401015. doi: 10.26877/ASSET.V6I1.17886.

[16] Pathan AI, Kulkarni AP, Gaikwad NL, et al. An IoT and AI based Flood Monitoring and Rescue System. www.ijert.org. 2024.

[17] Goymann P, Herrling D, Rausch A. Flood Prediction through Artificial Neural Networks A case study in Goslar, Lower Saxony.

[18] Hadi FAA, Shah A, Abdullah SA, et al. Machine learning techniques for flood forecasting. J Hydroinformatics, 2024;26(4):779–99. doi: 10.2166/HYDRO.2024.208.

[19] Sharfina H, Utami PY, Fakhruzi I. Prediksi Bencana Banjir Menggunakan Algoritma Deep Learning H2o Berdasarkan Data Curah Hujan. JATISI (Jurnal Tek Inform dan Sist Informasi), 2023;10(4):2407–4322.

[20] Morgenstern T, Grundmann J, Schütze N. Flood Forecasting with Deep Learning LSTM Networks: Local vs. Regional Network Training Based on Hourly Data.

[21] Zhou Q, Li K, Lin D, et al. A deep-learning-Technique-based data-driven model for accurate and rapid flood predictions in temporal and spatial dimensions. Hydrol Earth Syst Sci, 2023;27(9):1791–808. doi: 10.5194/hess-27-1791-2023.

[22] Sedighkia M, Datta B. Flood inundation modelling by a machine learning classifier. ISH J Hydraul Eng, 2023;29(5):652–60. doi: 10.1080/09715010.2022.2128906.

[23] Lopez-Fuentes L, Van De Weijer J, Bolaños M, et al. Multi-modal Deep Learning Approach for Flood Detection.

[24] Younis MC. Evaluation of deep learning approaches for identification of different corona-virus species and time series prediction. Comput Med Imaging Graph, 2021;90:101921. doi: 10.1016/J.COMPMEDIMAG.2021.101921.

[25] Al Qundus J, Dabbour K, Gupta S, et al. Wireless sensor network for AI-based flood disaster detection. Ann Oper Res, 2022;319(1):697–719.

[26] Xu Y, Goodacre R. On Splitting Training and Validation Set: A Comparative Study of Cross-Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning. J Anal Test, 2018;2(3):249–62. doi: 10.1007/S41664-018-0068-2/FIGURES/9.

[27] Fayeez ATI, Keedwell E, Collett M. Investigating Behavioural Diversity via Gaussian Heterogeneous Ant Colony Optimization for Combinatorial Optimization Problems. In: Proceedings of the 2nd International Conference on Advances in Artificial Intelligence - ICAAI 2018. 2018:46-50. doi: 10.1145/3292448.3292459.

[28] Lyla Y. A Quick Start of Time Series Forecasting with a Practical Example using FB Prophet | by Yang Lyla | Towards Data Science. Accessed Sep. 08, 2024. https://towardsdatascience.com/a-quick-start-of-time-series-forecasting-with-a-practical-example-using-fb-prophet-31c4447a2274.

Downloads

Published

2025-09-04

Issue

Vol. 7 No. 4 (2025): August-October

Section

Articles